Category: Product & Building

Product craft and the things I’ve built. What makes a product worth shipping, and what shipping under real constraints teaches you.

  • Check what your AI cites, down to the page

    Check what your AI cites, down to the page

    Your teams already ask AI to read the documents you trust: incident reviews, standards, the books your leaders quote. The answers sound right and arrive with citations. Checking them is the hard part. A citation that opens a whole book, or a passage near the claim rather than on it, leaves the reviewer doing the work the tool was meant to save. In one of my tests, Gemini Notebook wrote that developers lose 20–40% of their day to context switching, and cited a passage that gives no such number.

    I built grounded-forge to make that check quick. It’s an open-source tool (MIT) for assistants that answer only from sources you chose. In its verbatim mode, every citation opens the author’s own sentence, highlighted on the printed page, and code, not the model, places every quotation. It runs inside Claude Code, on a Claude plan you may already pay for.

    What I measured

    Between 31 October and 6 November 2026, I put the same practitioner questions to grounded-forge, Google’s Gemini Notebook and Open Notebook, a popular open-source notebook tool, over the same 31 public sources. Two AI models from different companies, Claude and OpenAI’s, checked every citation against the books. Here is how often a citation said what the sentence beside it claimed:

    • grounded-forge: 86–96%, depending on the mode and the grader.
    • Open Notebook, on the same Claude model, told to cite only what a passage says: 93%.
    • Gemini Notebook, given the same instruction: 64–67%.
    • Gemini Notebook, as it comes: 35–37%.

    All 94 quotations in grounded-forge’s verbatim reports matched the source word for word, because code places them. Told to quote only exact words, Gemini got 9 of 11 right. grounded-forge’s answers also carried more of the library’s supported ideas than either notebook’s.

    Open Notebook came close on citations, which suggests much of Gemini’s gap is the model and the instructions. But each of Open Notebook’s citations names a whole source, with no page or highlighted passage, so the reviewer still has to search for the line. In my test, that meant a catalogue of 266 practices.

    Four answers per tool are too few for a firm rate. The two graders differ by up to 9 points, one of them is the Claude model that wrote grounded-forge’s answers, and no human has graded the citations yet. The full results cover where Gemini led, how I improved both tools between rounds, a private library, and an ungraded side check of Google’s newest model.

    A fix you can use today

    For most uses, Gemini Notebook will be adequate, and one paragraph of instructions roughly doubled how often its citations held up. Set it as a custom chat style:

    Attach a citation only to a sentence that says what the cited passage itself says. Do not add numbers, percentages, causes, examples, or applications to the user's situation that the passage does not contain, and do not make the passage's claim stronger or broader than it is. When you apply a source to the user's case, or draw your own conclusion, put that in a separate sentence that starts "My inference:" and carries no citation. Put words in quotation marks only when they appear word for word in a source. If no passage supports a point, say that no source in this notebook covers it rather than citing a nearby passage. Keep the answer in the chat.

    For work where a wrong citation is costly, grounded-forge is worth serious consideration, because every citation in a verbatim report opens the exact passage on the printed page.

    How it works

    A general-purpose model gives you the most-published answer, and the most-published writer is rarely the original thinker (a corollary to Larman’s Laws of Organizational Behavior). So you pick the sources you trust. A model reads each one in full and writes a reference with every claim traced to the text, and a fresh model audits those claims against the source before anything ships.

    The audit isn’t a truth oracle. A fresh audit by a different model family found 97.45% of 9,364 reference claims free of hard errors before repair. It lets you check that the assistant sticks to the sources you chose. Whether those sources are right about the world stays your call.

    In a verbatim report, the model writes the argument and picks the passage each point rests on, and code places the author’s sentence and records its page. (KR Labs’ open-source Verbatim RAG and Invetech’s “deterministic quoting” rest on the same idea.)

    What you can do with it

    Once your sources are in the library, you can use it three ways:

    • Ask it questions while you work. In Claude Code, it answers from the sources you chose and cites them.
    • Write verbatim reports. For a memo going to a decision-maker, verbatim mode builds the answer around the authors’ own sentences, each one a click from its place on the printed page. Here’s one, on Marine Corps doctrine and management writing.
    • Build assistants for one job. One build command compiles the same audited library into an assistant per job. AAR Maker is one: a coach for after-action reviews that you can add to Claude as a connector (aar.groundedforge.com/mcp).

    Throughout, I put the model where it earns its place and keep code where consistency, audit and cost matter.

    Where it wins, and where it doesn’t

    It costs more up front. Reading every source in full, under audit, takes about 1% of a week’s allowance on a Claude subscription for a 70,000-word book, and each verbatim report takes 13–23 minutes, unattended. Gemini Notebook needs nothing but the files uploaded. The trade pays off for a library your team will question often, on work where a wrong citation costs more than the reading.

    On well-known public books with descriptive file names, a plain model reading the files did as well as the prepared library in my tests. Grounding earns its keep on your own material, the engagement documents and incident histories no model was trained on. Placing quotations by code also didn’t make citations hold up more often than grounded-forge’s standard mode, and in one round 20 placed passages lost words before a fix. Its gain is that each citation is quick to check.

    For builders

    The demo library ships 31 open sources prepared for five jobs, compiled into five assistants from one build command. Fork it, strip the demo content in one command, and add your own sources. The code is MIT, and everything is plain markdown, so your library leaves with you. The repo is at github.com/chrisgagne/grounded-forge.

    If you want this for your own documents

    If your team answers from documents you’d stake a decision on, I can build a library from them and test its citations against your own questions, the way I tested it here. It runs in your own Claude Code, so your documents stay in your repository and go only to the model provider you already use. Tell me which documents and which questions, and I’ll scope it with you.

  • Agentics NZ wayfinding: what members said

    From the member survey (13 responses, 21 October to 1 November 2026) and the online session on 5 November 2026. Prepared by Chris Gagné for Agentics NZ.

    TL;DR

    • Direction: “We build in the open, solo and together, in service to Aotearoa New Zealand.” Show, don’t tell: the art of the possible, with meaning.
    • Where the vision votes went: using AI to break NZ’s low-productivity cycle (5 votes), NZ as a leader in practical AI (4) and sovereign AI (3). Add the tech-sovereignty sticky’s 2 and sovereignty ties for first.
    • What’s in the way: unclear purpose and focus (4 votes), then mainstream NZ not ready for AI, fizzling out without a big win, and too few hands-on and in-person sessions (3 each). Counting two new stickies on the same theme, purpose and focus drew 8 of the round’s votes.
    • The Agentics Foundation: the chat check was “pretty much unanimous” that the affiliation isn’t adding much. No formal decision; Chris Barlow takes it forward, along with whether to pick a new name.
    • Next: one flagship project that solves a real NZ problem (6 votes), hackathons and show-and-tells (5) and an agentic ecosystem (4) came top. The first step is an online hackathon, as a possible start on the flagship. Sam and Vince lead it, Sam is starting a WhatsApp chat, and the check-in is on 19 November.
    • Parked: funding beyond the first hackathon, and the legal entity that funding would need.
    • From the literature: go for an early win that’s small and visible, hand the organising out, and agree how the pieces connect before building them.

    The stickies on the Mural board came from the survey, so the sections below lead with what people said in the session and quote the survey only where it adds something.

    Indented lines are people’s own words. Survey answers, anonymous, labelled with the question they answered. The session, labelled with the speaker and the time in the recording. Published sources, in the literature section. A sticky from the Mural board. The plain text between them is mine.

    The elephant in the room

    Before any voting, I asked what surprised people or named an elephant in the room. Purpose came up first.

    “One thing that strikes me is that there's a lot of enthusiasm. There's, I think, a good sense of community.”Sam · session, 26:05
    “But there is a bit of a vagueness as to what this is all for.”Sam · session, 26:05
    “Are we ready to trust the agents?”Vince · session, 25:04

    Ben pointed out how much the group already has.

    “It's very rare to actually get this level of engagement from zero to one.”Ben · session, 26:05
    “Bringing people together is hard, keeping them together is harder.”Survey · What’s working well?

    Where we’re heading

    Everyone had three votes for the vision stickies. Using AI to break NZ’s low-productivity cycle came top with 5, and Chris Barlow spotted that the two sovereignty stickies added up to the same.

    “It kind of looks like a you got a first equal there for sovereign AI. So if you add those two sovereign ones together, you get five”Chris Barlow · session, 31:08

    Ben and Sam took sovereign AI further than data centres.

    “I wouldn't confuse sovereign AI with data centers either”Ben · session, 32:25
    “We are a group that help people understand why maybe sovereign AI is worth investing in.”Sam · session, 33:26

    I heard four rough directions in the discussion (build together, teach, influence, a peer community) and asked everyone to type their pick in the chat and press return together. Build won clearly, with influence next. Sam asked what build means.

    “Do we mean like working on a project together as like a flagship project?”Sam · session, 42:51
    “I think we should all be building our own things and that's clearly working. But then how do we actually coordinate that build activity”Chris Barlow · session, 44:29
    “If you were to say which of the three of those is the kind of essence of the group and the others are kind of bolt-ons. That might be helpful.”Sam · session, 1:08:49

    The room settled on a direction, and it went on the board:

    We build in the open, solo and together, in service to Aotearoa New Zealand

    Two riders came with it. One was show, don’t tell, and Chris Barlow added the other:

    “It's the art of the possible with purpose. You know, it's art of the possible with meaning.”Chris Barlow · session, 59:59

    What’s in the way

    The anchors-and-risks vote put unclear purpose and focus on top with 4, and two stickies added in the session on the same theme took 2 each. In the discussion, Paul added a word to the list: protect.

    “Now we could all spend like six months working on a project and then the next release comes out doing it.”Paul · session, 48:38
    “There's a kind of a general mental health issue for the whole community which you guys could show some leadership on, you know.”Paul · session, 50:14

    That raised whether the group should bring mainstream NZ along or support the people at the pointy end.

    “Just do not underestimate the inertia of the New Zealand economy and broader institutions to adopt this”Ben · session, 55:25
    “Is the purpose of this group to drag the laggards along or is the purpose of this group to have like peer support for everybody at the pointy end of things?”Sam · session, 55:25
    “"Hey, this AI thing, it's really good, right?" You know, that's not a message that's going to land anymore.”Blair · session, 57:48
    “Let's build things at the pointy end that are like instantly relatable and people go, "Wow, that is awesome."”Chris Barlow · session, 57:48

    Ben pointed to Audrey Tang’s work in Taiwan as a model, and Alex and Jerry described the gap in government.

    “Just publish code that sort of reimplements government and suggest improvement.”Ben · session, 59:59
    “One of the challenges they are having is the managers don't know what the hell is GenAI, what the hell is AI.”Alex · session, 1:01:02
    “It's probably more at the DCE level and CE level that this guidance is required and they're getting it at the moment mainly from the big four”Jerry · session, 1:03:26

    The Agentics Foundation

    Two of the 13 survey responses raised the Foundation, one for and one against. In the session, Chris Barlow gave the background and his own view.

    “What value are we getting from that affiliation? And I'd argue not much.”Chris Barlow · session, 1:12:42

    Everyone typed wind, anchor or not sure in the chat and pressed return together.

    “Wow, that's pretty much unanimous.”Chris Barlow · session, 1:12:42
    “I don't want to burn bridges but I think that's right like we do have a very much a Kiwi focus”Chris Barlow · session, 1:15:27

    It wasn’t put to a formal decision. Ben raised the chance of a new name, and that goes to the follow-up conversation about the Foundation.

    What we’re doing next

    For the last vote, everyone backed only what they’d put their own time into. One flagship project that solves a real NZ problem came top with 6 votes, then hackathons and show-and-tells (5) and building an agentic ecosystem (4).

    “A hackathon might be the place at which you could get started on a flagship project”Sam · session, 1:22:27
    “Would we want to start like the first hackathon just be online only? It means you don't have to like go through the rigmarole of venue hiring”Sam · session, 1:27:36
    “Always opportunities for people to meet up with others in the city that they're in”Ben · session, 1:28:19

    Marc explained the agentic ecosystem sticky, and Chris Barlow may have a sponsor for it.

    “It's legislation that requires big data holders like banks and electricity retailers to share their customers data. And so I look at that and think, how could we make an agentic version of that?”Marc · session, 1:26:37
    “They can only do what you allow them to do”Marc · session, 1:26:37
    “You could throw in some malicious actors and try and get them to do stuff they shouldn't do.”Marc · session, 1:27:36

    Sam and Vince are leading the first hackathon, Chris Barlow is keen to help, and Sam is starting a WhatsApp chat. The check-in with Sam is on 19 November.

    Parked for later: funding beyond the first hackathon, which Ben raised, and the legal entity that funding would need.

    “These things take time, effort, resource to get going and it relies entirely on volunteers.”Ben · session, 1:29:02

    What the literature offers

    I put four of the session’s open questions to a reference library of books and papers on organisations, leadership and change. None of these sources is about a community quite like this one, so read each as a prompt for the next conversation, not an answer. Copyrighted books are paraphrased in my words; only openly licensed sources are quoted. The library has nothing on hackathons, open-source community governance, New Zealand, or how a volunteer group should fund itself or become a legal entity. It also doesn’t hold Geoffrey Moore’s Crossing the Chasm.

    Picking a lane

    The sources disagree, usefully. Richard Rumelt (Good Strategy / Bad Strategy, 2011) argues for choosing: when a group keeps every option open, nobody has to make the case for any of them. His test is to imagine you could have only one goal you could actually reach soon, and ask which would change the most. Jim Collins, in his monograph for non-profits (Good to Great and the Social Sectors, 2005), says a volunteer group runs on people’s time and goodwill as much as money, and should turn down projects that pull it away from what members care about most and could be best at.

    Collins and Jerry Porras (Built to Last, 1994) take the other side: hold one fixed purpose and let the activities vary, keeping each only if it works and fits. Mary Parker Follett questions the framing itself. Making one lane the essence and the rest bolt-ons means someone wins or everyone gives ground; she argues for finding out what each side actually wants and designing something with room for all of them.

    “a solution has been found in which both desires have found a place, that neither side has had to sacrifice anything.”Mary Parker Follett, Dynamic Administration (1941), public domain

    Read together, my take is one purpose, one near-term goal, and the other directions run as experiments, each judged on whether it works and whether it fits. The Fifth Discipline Fieldbook (Senge and others, 1994) covers the step from words to work: name four or five pieces of work the direction can’t happen without, give each an owner, and review them six to nine months later.

    Bringing mainstream New Zealand along

    The library’s closest case is the team that rescued Healthcare.gov (Robinson Meyer in The Atlantic, 2015). They got a new tool used inside the US government by using it themselves, then letting a few interested staff try it, then widening out. They chose not to ask for a mandate, because a mandated tool would have been one more rule and nobody would have seen what it was good for.

    Thomas Kuhn (The Structure of Scientific Revolutions) describes new ways of working winning not by argument but by early backers building them out until others can see them working, while some established experts never switch. Jeffrey Pfeffer and Robert Sutton (The Knowing-Doing Gap, 2000) add that beliefs tend to change after people act differently, which favours builds newcomers can try with their own hands over demos they only watch. Walter Powell and Paul DiMaggio (The New Institutionalism in Organizational Analysis, 1991) explain Jerry’s point about the big four: organisations unsure what works copy peers that look legitimate, with consultancies as the carriers, so a credible, visible alternative is itself a lever.

    Two cautions. GM had a working Toyota-run plant, NUMMI, on its doorstep for 25 years, and visitors copied what they could see while missing what made it work (This American Life, 2015). And Carlota Perez (Technological Revolutions and Financial Capital, 2002) shows institutions changing far more slowly than technology, which argues for having working alternatives ready before the mainstream is willing to look.

    Keeping it going

    The library’s closest case to Agentics NZ is WIKISPEED, about 200 unpaid volunteers around the world building a fuel-efficient car (Mary and Tom Poppendieck, The Lean Mindset, 2014). It didn’t win the competition it entered, but the attempt drew publicity and new volunteers, and the group kept going on a steady rhythm of visible progress: regular demos by the people who did the work, a weekly check-in, rotating pairs, and making it easy to join or leave.

    Chip and Dan Heath (Switch, 2010) tell of a day in Miner County, South Dakota, when about 50 volunteers cleared 400 old tree stumps from one small town, and the county’s wider revival grew from it. Their point is that the first win needn’t be big: it needs to come soon and be seen. Ronald Heifetz and colleagues (The Practice of Adaptive Leadership, 2009) say part of an organiser’s exhaustion comes from doing what others could do for themselves, so the work is to hand tasks back and hold back when things wobble. A member who isn’t the host leading the hackathon is that move. Follett adds that people come on board by shaping something from the start, not by approving it at the end.

    “consent is not part of the process, it comes at the end of or after the process. Participation is not only part of the process; it should begin with the beginning of the process.”Mary Parker Follett, Dynamic Administration (1941), public domain

    Building together

    Follett’s advice for work that adds up is to bring the builders together while their plans are still forming, because people who arrive with finished plans find agreement hard.

    “But if the head of the production department, while he is forming his policy, meets and discusses with the other heads the questions involved, a successful co-ordination is far more likely to be reached.”Mary Parker Follett, Dynamic Administration (1941), public domain

    WIKISPEED split its car into modules owned by small teams and agreed the interfaces between modules before anything else; each team then worked freely inside its own. That fits Marc’s theme of agents acting under published contracts. The Marine Corps’ doctrine manual (MCDP 1 Warfighting, 1997) offers a way to keep separate projects pointed the same way: name one main effort, and have everyone else ask how their work can feed it.

    “We seek unity not principally through imposed control, but through harmonious initiative and lateral coordination within the context provided by guidance from above.”US Marine Corps, MCDP 1 Warfighting (1997), US government work

    Two sources disagree on where to start. Peter Senge (The Fifth Discipline, 2006) says a shared goal holds when it grows out of what each person already wants, so members needn’t give up their own projects. Rumelt says to start with one near target a group can actually hit, nearer the more uncertain things are. For a first online hackathon, that suggests a brief small enough to finish in the time. Amy Edmondson (Right Kind of Wrong, 2023) would run it as a pilot designed to learn: as small as it can be while still teaching something, at a normal volunteer pace, with agreement beforehand on what will change depending on how it goes.

    Vote counts

    From Mural’s voting results. Each person had three votes per round and could put more than one on a sticky. Stickies with a single vote are left out; survey counts are taken off the sticky text.

    Where we’re heading

    StickyVotesVoters
    Use AI to break NZ's low-productivity cycle55
    NZ as a leader in practical AI43
    Sovereign AI: build and own it here, not rent it from Big Tech, nation down to individual33
    Responsible, trustworthy agents by design22
    Contribute to Tech Sovereignty conversation: by doing22

    What’s in the way

    StickyVotesVoters
    Unclear purpose and focus44
    Mainstream NZ not ready, or turning against AI33
    Fizzling out without a big win33
    Too few hands-on and in-person sessions33
    Mental health22
    Without a focus, we remain just an interest group22
    Without a clear purpose or focus, risk of group disbanding over time22
    Security and trust in autonomous agents22
    AI gains concentrated, jobs lost22
    Organising rests on one person22

    What we’re doing next (only what you’d put time into)

    StickyVotesVoters
    One flagship project that solves a real NZ problem66
    Hackathons / Show and tells54
    Build an agentic ecosystem44
    Partner with agencies, universities and other forums33
    Regular hands-on sessions33
    Help members connect, collaborate and onboard33
    Big Demo: Envision Agentic Aotearoa22
    Demo of an agent acting with clear, revocable authority22

    How this was made. Survey quotes are word for word from the survey export. Session quotes come from the Google Meet transcript of Chris Barlow’s recording, with filler words and repeated words taken out and a few mis-heard words corrected (“lagards” to “laggards”, “G AI” to “GenAI”). Session times are the start of the transcript block a quote falls in. A script checked every quote against its source before rendering, and the page shows only quotes that passed. The literature section draws on a private reference library: copyrighted books are paraphrased, and only openly licensed sources are quoted.

    The checking approach is open source in grounded-forge.

  • AI, taste and the quality without a name

    AI, taste and the quality without a name

    In The Timeless Way of Building, Christopher Alexander describes having strawberries for tea with a friend in Denmark. She slices them almost paper-thin. When he asks why she takes the extra time, she explains that this exposes more surface to taste. He writes: “I learned more about building in that one moment, than in ten years of building.”

    For me, this is immediate, direct contact with what she’s doing. The way the fruit will be eaten guides the cut. It’s a small decision, but it helps me think about what we mean by taste when we’re making things with AI.

    Alexander was trying to describe a quality that makes a place feel alive, with its parts belonging together and to the life lived there. He called it the “quality without a name” because words such as beautiful or comfortable each miss something. He also finds it in waves and a well-made fire. A fire can be too hot for comfort without losing that aliveness.

    Think of a product that’s a joy to use, perhaps even a janky old motorcycle with worn paint and a few quirks. Something about the way it responds to you just… feels right. I think that can be a taste of the quality Alexander describes.

    A product can look attractive and still be awkward to live with. Judging it involves paying attention to what happens when someone actually uses it, including things we might struggle to explain in a design brief.

    The philosopher Eugene Gendlin describes how we can work with that difficulty. When searching for words, we can sense that a phrase doesn’t quite fit before we know what to say instead. He asks us to attend to a felt sense, the body’s sense of a whole situation, including more than we’ve already put into words. Trying another phrase can help us discover what we meant. In design, that might mean realising that the brief itself needs to change.

    A language model can explain Alexander’s story and suggest cutting fruit that way. This doesn’t establish that it has tasted a strawberry, or that it can check its words against the bodily sense Gendlin describes.

    A model could nevertheless learn useful distinctions from people who have those experiences. When we choose one design over another, we supply information even if we can’t fully explain the choice. I think a model could learn from those choices to propose things we value and help decide what to develop.

    Perhaps some of what we call AI slop is work in which we feel this quality is missing. When we’re handed something that looks finished but leaves us struggling to make it useful, it can feel as though our time and circumstances weren’t worth much care.

    Suppose a support team uses AI to draft courteous, accurate replies directing customers to another department. The departments close their tickets while the customer keeps having to explain the same unresolved problem to someone new.

    If we’re reviewing only the replies, we might spend our time improving the tone. Following one customer’s attempt to get help could reveal that nobody has responsibility for resolving the whole problem. We might need to give one person responsibility for the case and authority to coordinate across departments.

    The customer’s anger could help us notice this. Trying to make every exchange pleasant might mean soothing a justified complaint while leaving its cause untouched.

    AI could help with that investigation as well as with writing replies. We could ask it to look across the case histories for repeated explanations or unresolved hand-offs, then check its findings with the people involved.

    We could try a change on a recurring enquiry, then check whether people needed fewer repeat contacts and whether their problems were resolved. Staff and customers would need a way to tell us where the new arrangement still didn’t fit their needs.

    Perhaps this fitness grows through contact: with the material, with the circumstances, and with the people who will live with what we make. We discover something we couldn’t fully specify beforehand, and allow it to change the work. Ideally, the people building the software encounter those situations directly: watch someone use it, hear what matters to them, and have the authority and supporting system to quickly respond to what they discover.

  • grounded-forge, by example

    grounded-forge, by example

    I’ve open-sourced grounded-forge, a working example of grounding an AI assistant in sources you trust. This post introduces it through one session, receipts included.

    grounded-forge is my answer to the problem in the last post: an AI assistant defaults to the most-published take, not the best one, because the consultant layer outwrites the original thinkers and the models inherit the ratio. Ask a stock model about mission command and you get the LinkedIn consensus on mission command. The fix is to take source selection back.

    The tool is open source. You pick the material you’d stake a real decision on. A model reads each source in full under a structured nine-pass protocol that checks every quotation verbatim against the text, then projects the source onto the tasks your assistant serves, once, at ingestion time. At runtime the assistant answers from that pre-audited material; the expensive, error-prone reshaping is already done.

    What follows is the transcript of one session, working notes first, then the essay. I want to be plain about authorship: the transcript in the card below was generated by the model, and it matches the copy that ships in the repo; apart from trimming the lens list to the four the public repo ships, I have not touched it. The slate notes labelled “Chris” are mine, added afterwards to narrate what the system is doing at each step. My contribution otherwise is the question, the choice of sources, and the system underneath, which is built to ground every load-bearing claim in a source passage and to mark verified quotations as it goes.

    The corpus behind the session is the demo library that ships with the repo (27 sources at the time), among them MCDP 1: Warfighting, the US Marine Corps’ capstone doctrine (public domain), and the OpenStax business textbooks, the standard management curriculum (openly licensed). My prompt was one line: “Please draw some interesting parallels between US Marines war-fighting doctrine and modern ‘textbook’ business administration.”

    The [V] markers in the essay mean verbatim: checked against the ingested source text by a source-only audit at ingestion, before any question existed. (The auditor is itself a model working under protocol; no human read every line. What the marker buys you is a specific file and a specific passage to check when a claim looks wrong.) The trace at the bottom names which projections were read in full, and the closing section declines the one transfer the sources themselves don’t support. The transcript itself, without my notes, ships in the repo as a captured session. Where a [BT] appears, the idea is borrowed through the source from an author the corpus does not hold, and labelled as such.

    Source-grounded synthesis · Protocol S (Synthesis) · 2026-07-23 · Claude Fable 5

    USER · /answer-from-corpus

    Please draw some interesting parallels between US Marines war-fighting doctrine and modern “textbook” business administration.

    ASSISTANT

    I’ll answer this by drawing on the corpus. First, let me classify the query shape and check for applicable lenses.

    Shape: This is a Synthesis question — it asks what the corpus says across two domains (Marine warfighting doctrine, textbook business administration) and wants parallels drawn between them. Breadth across sources is the point.

    Chris: It has detected this is a synthesis query. That is one of three shapes it routes: a named lookup reads one source and stops; a diagnostic maps your situation into one task domain; synthesis wants breadth across the corpus. The shape decides which indexes get read and in what order.

    Tool calls – Read lens-index.json (full) — four lenses now: builder, pm-bounded-by-ba-role, agentic-builder, chris-gagne-consultant-coach.

    Lens-applicability check: Lens-neutral. The query asks for an intellectual synthesis between two doctrines — not a role-bound artefact, not a reader-typed deliverable, and not an application of the named-person lens. No lens applies.

    Chris: It has decided not to apply a lens, as none fits the question. A lens reweights what a distillation surfaces for a particular role (a CTO and a builder need different salience from the same source), and the check runs before decomposition, while it can still shape the sub-claims. It declines the four on offer rather than forcing one.

    Sub-claims (the parallels to test):

    1. Nature of the decision environment — friction and uncertainty vs bounded rationality and scarcity
    2. The decision cycle — OODA vs the textbook multi-step process
    3. Who decides — mission command vs centralisation/decentralisation
    4. Priority-setting — Schwerpunkt vs the textbook prioritisation apparatus
    5. Error asymmetry — inaction vs commission
    6. Doctrine as thinking vs framework as tool
    7. Limits of transfer — the adversarial Zweikampf frame

    Tool calls – Read slug-table.json (full) — 27 sources; 00q = mcdp1-warfighting, plus the OpenStax family. – Read concept-index.json (full; exceeded the single-read cap — two paginated reads, 4,210 lines). – Read distillations/decision-making/task-index.json (full; two paginated reads, 1,809 lines).

    Chris: This is the routing pass, and the reads are whole-file by rule. The concept index is bigger than a single read allows, so it paginates to the end rather than grepping for a likely key. Grep answers the question you thought to ask; a full read is what lets the index volunteer sources you didn’t think to ask for, which is exactly what happens next.

    Routing findings. The concept index carries a dense MCDP-1 concept family (ooda-loop, mission-tactics-auftragstaktik, intent-two-levels-up, schwerpunkt-main-effort, leniency-overbold-severity-inaction, zweikampf-violent-struggle) and routes the business side beyond the management shelf: theory-of-constraints and relevant-costs/sunk-costs live in 00b (Principles of Accounting Vol 2), and sunk-cost, opportunity-cost, and marginal-analysis concepts live in 00e (Principles of Economics 3e). One gap to report honestly: the task index carries no rows for 00q at all — the situation router does not yet cover the corpus’s newest source. Routing for the Marine side therefore rests on the concept index and slug-table, which is sufficient here.

    Chris: The payoff of the full reads is in the findings above: accounting and economics surfaced for a Marines question, which no skim of filenames would suggest. And when the router itself had a hole (no task-index rows for the Warfighting source), the session reported the gap instead of papering over it. That is the no-silent-degradation rule doing its job; I fixed the index the same day.

    Candidate set and dedup. 00q (Warfighting), 00j (Principles of Management), 00h (Organizational Behavior), 00g (Introduction to Business), 00b (Accounting Vol 2), 00e (Economics 3e). 00c (Business Ethics) matched on stakeholder-theory for sub-claim 7, but 00h (Follett) and 00j (Freeman) already carry that sub-claim — skipped under the diversity-aware dedup rule.

    Tool calls – Read mcdp1-warfighting-decision-making.md (full). – Read openstax-principles-management-decision-making.md (full). – Read openstax-organizational-behavior-decision-making.md (full). – Read openstax-introduction-business-decision-making.md (full). – Read openstax-accounting-vol2-decision-making.md (full). – Read openstax-economics-3e-decision-making.md (full).

    Every sub-claim now has the Warfighting side and at least two textbook-side sources, with convergence and divergence both represented. The accounting and economics rows extend the comparison well beyond the management shelf. Let me write the essay.

    Chris: Six distillations read in full, not as retrieved chunks: the four any skim would find, plus the accounting and economics volumes the concept index surfaced. Each is a source already projected onto decision-making at ingestion, quotes checked and marked in place. The costly work ran once, before any question existed. It also declined a seventh read: Business Ethics matched, but the stopping rule found the sub-claim already carried.

    Two Doctrines of Deciding Under Uncertainty

    Read MCDP 1: Warfighting against the OpenStax business shelf — not just the management row, but the accounting and economics rows beside it — and the same question keeps surfacing from both sides: how do you decide well when you can’t see the whole board? The parallels are real and useful. So are the divergences. And one claim the narrower comparison invites turns out to be wrong once the whole shelf is on the table.

    Where they agree: the constraint is permanent

    MCDP 1 names the environment before naming any method: war is friction, uncertainty, fluidity, disorder — constitutive features, not exceptions. The doctrine is blunt that “no degree of technological development or scientific calculation will diminish the human dimension in war” [V]. Decision frameworks that assume the world is reducible will fail, because the world isn’t.

    The management texts arrive at the same place through cognitive science. Bounded rationality anchors both OpenStax management volumes: “for complex issues we cannot be completely rational because we cannot fully grasp all the possible alternatives, nor can we understand all the implications of every possible alternative” [V]. And the economics text arrives through a third door, defining its whole subject as “the study of how humans make decisions in the face of scarcity” [V] — adding that “the ultimate scarce resource is time — everyone, rich or poor, has just 24 expendable hours in the day” [V]. Three disciplines, one founding condition: the limit on the decider is permanent, so you decide inside it. Introduction to Business concedes the same about control: “managers are primarily adapters to, rather than agents of, change” [V]. Neither tradition believes the decider owns the field.

    The decision cycle: same skeleton, different clock

    MCDP 1 credits Boyd for Observe–Orient–Decide–Act and stakes its claim on tempo: the side that completes the cycle faster, or that the adversary cannot orient to, wins. The textbooks run the same loop at lower velocity — recognise, generate alternatives, analyse, select, implement, evaluate in the management volumes; a five-step variant closing with feedback in Introduction to Business, which warns that managers can get dangerously stuck at any stage. Analysis paralysis is a slow OODA loop by another name.

    The first-order emphasis gap is real: the management version optimises the quality of each step, the Marine version the speed of the whole loop relative to the opponent’s. But the economics row complicates the neat contrast, because it prices delay explicitly: “the opportunity costs of waiting time can be just as important as costs that involve direct spending” [V]. The textbook shelf does carry a clock; it lives in the economics text rather than the management one, and it prices your waiting against your own alternatives rather than against an adversary’s cycle.

    Who decides: mission command in three vocabularies

    MCDP 1’s answer to who should decide what is mission tactics: the senior gives the what and the why — the commander’s intent — never the how, and intent must be understood two levels up. Decentralisation works only when subordinates hold the intent; without it you get incoherence, not empowerment.

    Introduction to Business debates the same trade-off as centralisation vs decentralisation — warning both that centralisation can prevent quick local decisions in dynamic environments and that decentralisation without skills or training can produce costly mistakes — and renders it structurally as organic versus mechanistic design. The accounting volume adds a third vocabulary the narrower read missed: responsibility centres, which align decision authority with information access and accountability. That is the information-logic of mission command in accounting dress: push the decision to where the information lives, and hold the decider accountable for what they control. What the textbook shelf still lacks is MCDP 1’s sharpest instrument — intent two levels up as the specific content the empowered subordinate must hold. The textbooks say decentralisation needs skills; the Marines say precisely which skill: the boss’s boss’s purpose.

    Priorities: the textbooks have a Schwerpunkt after all

    Here the whole shelf corrects the essay a narrower read produces. Compare MCDP 1’s Schwerpunkt — name one main effort; everything else supports it; supporting yields when they conflict — with the management shelf alone, and the textbooks look like better-prioritisation people: Drucker’s eight goal areas, SWOT, weighted analysis. Prioritising better preserves the multi-priority frame; naming a main effort breaks it.

    But managerial accounting carries the textbook tradition’s own one-filter discipline: constrained-resource allocation. When a resource binds, rank every product by contribution margin per unit of the constraining resource — not by unit margin. The highest-margin product is often the wrong priority; what matters is yield against the single binding constraint. The volume carries this from Goldratt’s Theory of Constraints [BT], and it does to product-mix decisions exactly what Schwerpunkt does to operations: one thing governs, everything else is ranked against it.

    The residual difference is sharper for being narrower. The Marine main effort is chosen — a bid, an act of will that can be shifted mid-fight as gaps appear. The accounting constraint is discovered — an empirical fact about capacity you find and exploit. One tradition names its focus; the other finds it. That is the true divergence, and it is smaller than the one the management shelf alone suggests.

    The asymmetry on inaction: the mirror has a crack

    MCDP 1 rejects zero-defects outright: severity on errors of inaction, leniency on overbold errors. The management texts brake in the opposite direction, and for cause: their catalogued failures are failures of commission — escalation of commitment, “the tendency of decision makers to remain committed to poor decision, even when doing so leads to increasingly negative outcomes” [V], groupthink [V], and the remedies are devil’s advocates and precommitted monitoring.

    Yet the economics row again refuses the clean mirror, because it carries anti-hesitation machinery of its own. It names why waiting feels safe: loss aversion — a loss pains roughly 2.25 times more than an equivalent gain helps [BT] — and it orders the release: “the lesson of sunk costs is to forget about the money and time that is irretrievably gone and instead to focus on the marginal costs and benefits of current and future options” [V]. The accounting volume drums the same refrain into every short-term decision category. So the honest contrast is institutional, not intellectual: the textbook shelf hands the manager tools against both failure directions and leaves the calibration to judgment; the Marines legislate the asymmetry as policy, because their characteristic death is hesitation. The tools exist on both sides. Only one side turned them into doctrine.

    Doctrine as thinking: three-way agreement

    MCDP 1’s most general claim — doctrine is a way of thinking, not a checklist — turns out to be the one the whole shelf endorses. The management texts warn against running frameworks mechanically and insist a good process can yield a bad outcome under uncertainty. The accounting volume makes the same move in its own material: costs are not intrinsically fixed or variable — the classification is decision-relative, and the practitioner’s question is “fixed for what decision?” A label that must be re-derived per decision is judgment wearing a taxonomy. The framework is scaffolding; judgment is the thing. On this, no daylight.

    The one parallel that doesn’t hold

    MCDP 1 frames war as Zweikampf — a violent struggle between two hostile, irreconcilable wills — and its edge follows from that frame: tempo, surfaces-and-gaps, getting inside the opponent’s cycle. The Warfighting distillation itself flags this as the piece that usually does not transfer. The textbook shelf encodes the opposite cosmology three times over. The management row offers Follett’s integration — both parties reaching the creative agreement that satisfies both [BT] — as the strongest conflict outcome, and flatly rejects harming stakeholders for shareholder return: “increasing the wealth of shareholders is not an acceptable reason for causing harm to others” [V]. And the economics row is built on the founding scene of mutually beneficial exchange: comparative advantage says the counterparty is a trading partner whose different opportunity costs are the very reason to deal, not a will to break.

    So the synthesis holds, sharpened: the machinery transfers — OODA, mission command, constraint-governed priority, the case against hesitation, doctrine-as-judgment — and much of it has closer textbook cousins than a narrow read reveals. The cosmology does not transfer. Reach for the Marine playbook when there is genuinely an adversary and a clock; reach for the shelf when the room holds stakeholders and trading partners, which for most of management is most of the time. The mistake that survives every widening of the corpus is the same one: using the Zweikampf frame on people who were never your enemy.


    Trace [Synthesis, Depth-over-breadth, lens: none, corpus: demo]: Pass 1 (lens-index + slug-table + concept-index (2 paginated reads, 4,210 lines) + decision-making/task-index (2 paginated reads, 1,809 lines); gap noted: task-index carries no rows for 00q) → sub-claims: environment (00q + 00j/00h bounded-rationality + 00g + 00e scarcity); cycle (00q + 00j/00h six-step + 00g five-step + 00e waiting-cost); decentralisation↔mission-command (00q + 00g + 00b responsibility-centres); priority/Schwerpunkt↔constrained-resource (00q + 00j + 00b ToC-[BT]); inaction-asymmetry (00q + 00j/00h escalation + 00e loss-aversion/sunk-cost + 00b sunk-cost); doctrine-as-thinking (00q + 00j + 00b decision-relative-costs); Zweikampf-limit (00q + 00j Follett/shareholder-rejection + 00e comparative-advantage) → dedup: 00c matched (stakeholder-theory) but skipped, 00h+00j already carry the sub-claim → Pass 2 (6 distillations read in full: 00q, 00j, 00h, 00g, 00b, 00e) → verbatim [V] markers surfaced in-band from the distillations. Lens-neutral: no role-bound reader, no lens applied (4 lenses checked).
    Chris: The trace is the receipt: protocol, corpus, the lens ruling, which sources fed each sub-claim, what was read in full, and even the read it declined. It is what lets you audit the answer instead of taking its fluency on trust. A trace that names what was read shows what wasn’t.

    That’s the whole exchange, trace and all. The build system, the 9-pass ingestion protocol, and the evaluation showing where the architecture wins, and where a naive corpus read beats it, are open at github.com/chrisgagne/grounded-forge.

    If your work leans on sources you actually trust (doctrine, standards, your own case notes), the pattern transfers: each source is read once under audit and projected onto the tasks you repeat, and answer time becomes a lookup. I run the same machinery for After-Action Review and retrospective facilitation. My hunch is that the audit trail matters more than the essay. Fluent prose from a model is cheap now; what I wanted was prose I can check.

  • Wastes caused by context switching

    Wastes caused by context switching

    I first published a version of this piece on LinkedIn in 2021, when the argument ran on Weinberg’s table and Kniberg’s prioritisation illustrations alone. They carry the “don’t do everything at once” point well enough. What I have built since is a working cost-of-delay tool, grounded in Don Reinertsen’s Principles of Product Development Flow—the source of both the cost-of-delay economics and the WSJF / CD3 prioritisation heuristic⁠—and the practical cost-of-delay work of Joshua Arnold, who did as much as anyone to turn it into something teams actually use. The “cost of delay” is no longer a rhetorical lever for me: the tool ranks every story by it, and where the business states what the work is worth, it can put an estimated dollar figure on the delay. Also, the Cost of Delay work has shown me that most of the value comes from focus, not necessarily getting the prioritisation perfect.

    Gerald Weinberg’s book “Quality Software Management: Systems Thinking” is more than 30 years old. While it’s not one of the most highly-read and recommended classics in the adaptive canon, it’s the source of a frequently quoted table of data:

    Weinberg, Gerald M. (1992) Quality Software Management: Systems Thinking. Dorset House, p. 284.

    Visualised as a graph, the waste caused by context switching really stands out:

    Worse, the waste caused by project switching isn’t due only to the losses related to cognitive overhead. Failure to prioritise often leads to less revenue and even building the wrong product.

    (Credit where credit is due: I first saw a version of the following illustrations presented by Jeff Sutherland, who adapted it from Henrik Kniberg. I’ve created new illustrations and expanded on them a bit. Kniberg’s own video on this exact topic is very much worth a watch.)

    Let’s suppose your company wishes to ship three products: A, B, and C. To ship a product, a development team must complete tasks 1, 2, and 3 corresponding to that product:

    Most companies are not very good at prioritising work. As a consequence, the prevailing belief is: “Everything is important. Get started on everything immediately!” The traditional delivery timeline might look like this:

    Depending on your software and how you break down your work, your roadmap probably looks like:

    Either way, notice that we are interleaving each task and that products A, B, and C are ready at roughly the same time, several months after we started.

    The adaptive approach is very different. Instead, we proactively prioritise the work and focus on limiting our work in process:

    There are at least three significant advantages to this adaptive approach: lower cost, more revenue, and better product/market fit.

    Lower cost of development

    We lose 20% or more of our productivity in the traditional approach due to context switching waste. In this example, the company could go about twice as quickly if they switched to developing one product at a time instead of three.

    More revenue, earlier

    The switching waste is the smaller loss. Because we have nearly finished products B and C before finishing A, we had to do nearly three times the work (not including the context-switching waste) before we could ship Product A (in late May). Had we prioritised and focused, we would have been able to ship Product A in early February. Had we done so, we may have been able to collect revenue and feedback from our customers starting nearly four months earlier. In fact, the savings from not context-switching between projects may mean that we could ship products A, B, and C before we would have been able to ship just A in the traditional model.

    Better product/market fit

    Products are rarely independent, and building the wrong product can be costly. In this example, we believed before starting the work that the customer needed Product C. We took the adaptive approach and built A (more valuable and/or cheaper) first. When we delivered A to our customers in early February, we learned that they liked it a lot and didn’t need C after all. Instead, they wanted us to work on D. We took February to finish most of B and get the initial prototypes for D built.

    We can see that prioritisation and focus serve everyone: developers, stakeholders, and customers.

    Good prioritisation is not a zero-sum game

    Further, good prioritisation is usually not a zero-sum game. Many stakeholders will argue aggressively for their product to be worked on right away (and it’s no surprise: they may even have a bonus tied to it being completed by a certain date). However, the waste caused by project switching and the cost of delay is so significant that failure to prioritise may make all stakeholders worse off. In this case, the stakeholders behind projects A, B, and C agreed to prioritise based on the cost of delay and all were better off than if they had insisted that everyone’s work be tackled at once.

    The same three epics, priced

    Five years on, this argument became software. The infographic below, from my Delivery Intelligence work, prices the same scenario with cost of delay: keeping all three epics in flight collects $42.50 of value by the end of July; finishing one at a time collects $138.75 in the worst order and $176.25 in the best. In this toy scenario that is roughly 3–4× the value, and the ordering mattered far less than the focus.

    Feel it in five minutes: the character factory game

    You don’t have to take my word for any of this, or Weinberg’s. Grab a pen, a sheet of paper with three columns, and a one-minute timer. Three customers each want a complete set of 25 characters⁠—letters, numbers, vowels⁠—and nothing partial counts. Round 1: keep all three orders moving by writing one character for each customer in turn. Round 2: finish one customer’s set before starting the next. One minute each. (The game is Henrik Kniberg’s multitasking name game, with a modification I learned from Monica Yap and a further modification of my own.)

    The card assumes the same writing speed in both rounds. Focus still wins⁠—two complete sets against none⁠—because a complete set is what a customer can actually use. Run it live and a second effect appears: your total character count drops in round 1, because every switch costs a beat. That drop is Weinberg’s table on one sheet of paper, and the delivered sets are the revenue argument in miniature. Try it with your team this week.

    Some book links here are Amazon affiliate links; if you buy through them I may earn a small commission, at no cost to you.

  • Output vs outcome: Judge engineering by what customers can now do, and tell the board

    Output vs outcome: Judge engineering by what customers can now do, and tell the board

    You shipped more this quarter than last. Your customers are no better off. Which number is the work actually being judged on?

    Again, find the axis where your claimed pole and your lived pole pull apart, then give yourself to that analysis. If output-versus-outcome is already the tension eating your quarter, this is your chapter. If it isn’t, read it lightly and save your energy for the axis that is.


    Chapter 8 argued for subordinating the non-constraints. That pays off only when the constraint serves the right number. Output and outcome are different numbers, and the gap between them is where feature factories live.


    The two poles

    Pole A: output. The unit of management is velocity, units shipped, features released, work completed.

    Pole B: outcome. The unit of management is customer progress, market position, mission impact.

    This axis is well known among engineering leaders. The vocabulary⁠—feature factory, output vs outcome, customer progress—has been in circulation for well over a decade.

    Where Pole A is right

    Pole A is right when output and outcome have been shown to track each other tightly in the relevant domain. In a sales organisation with a mature product, deals booked may convert predictably to revenue over months. In a fulfilment operation, units shipped may equal customer demand met, provided return rates remain low and margins stable, and in a regulatory pipeline, filings submitted may track approvals secured when the regulator’s response time is well-characterised over multiple cycles.

    The metric I was judged on was velocity. Wherever it became the watched number, estimates grew to meet it; I once saw a team carrying a velocity in the hundreds, the number climbing while nothing shipped any faster. Metrics like these earned their place first: deals booked, units shipped, and features released were proxies that tracked the customer outcome closely enough that managing the proxy amounted to managing the outcome.

    None of that discipline was wasted. Counting output is part of what makes anything ship at all. A team that can’t count what it has produced can’t tell learning from activity.

    Pole B doesn’t abandon counting. It asks you to notice when output stops tracking the outcome.

    Where Pole B is right

    Pole B is right whenever the firm produces more output and gets worse outcomes. This is the empirical pattern in feature-factory product organisations. The velocity’s high and the customers still leave. In one adoption I coached, the teams had been quick before the change, but they were building the wrong product quickly. Afterwards they were slower, and the quality was better at the end. Pole B costs the leader something real: standing in front of a falling output number on purpose.

    In Clayton Christensen’s Jobs to Be Done theory, laid out in Competing Against Luck, the customer isn’t buying your feature. The customer is hiring your product to make progress on a job.

    The classic example is the milkshake a fast-food chain sold in surprising numbers before 9 a.m. to commuters buying nothing else. Commuters hired the milkshake to keep a long, boring drive interesting, one-handed, and to hold off the mid-morning hunger. The milkshake was hired because it outlasted every competitor⁠—a thick shake takes 20 minutes through a thin straw⁠—and the cup fit the cup-holder.

    Improving the milkshake meant making it last longer, not making it taste better. The Pole A move (survey the customers, ask how to improve the shake: cheaper, chunkier, chocolatier) produced changes that didn’t move sales. The Pole B move (understand the job) produced an actionable insight.

    Marquet: redwork and bluework

    David Marquet’s Leadership Is Language names an operational discipline that fits the output-outcome distinction. Redwork is execution under pressure: doing what has been decided. Bluework is judgement and pause: deciding what to do.

    The Industrial-Age inheritance divided planning from doing. A few people decided; everyone else executed. Marquet recasts those activities as bluework and redwork, then argues that work now requires everyone to do both.

    In Marquet’s terms, the language of prove and perform gives way to the language of improve and learn.

    The Pole A leader who manages to features-shipped runs in pure red mode. The team decomposes the goal into tasks, executes them, and reports completion. Bluework has no place to happen because the language of the work has no opening for judgement.

    The Pole B leader inserts bluework into the cadence. The team pauses, checks whether the output delivered the outcome it was meant to serve, and changes the next round of redwork based on what it learned.

    We committed to ship X by Q3 closes the loop on redwork. We hypothesised that shipping X would produce outcome Y by Q3; what did we learn? opens the loop into bluework.

    Marquet’s own protocol on the USS Santa Fe, replacing “request permission to…” with “I intend to…”, moves the judgement to the person closest to the work; chapter 17 runs it in full. The leader states what military doctrine calls commander’s intent: a plan that specifies the steps dies the moment events outrun it, and the statement that survives is the goal and the end-state, compact enough that people down the line can improvise toward it.

    Innovation accounting

    Eric Ries’s accounting discipline for Pole B distinguishes vanity metrics, which rise regardless of whether anything is working, from actionable metrics, which show clear cause and effect, so you know what to do next.

    Here’s the test I use to tell them apart, built on Douglas Hubbard’s point that a measurement earns its keep only if it could change a decision. Pick the metric. Predict what it will do over the next two weeks or months. Look at it. Did the prediction match? If it didn’t, what would you do differently?

    If the answer to that last question is nothing, or you can’t say what moved the number, the metric is vanity: you’re not running on data, you’re running on its appearance.

    On StubHub’s recommendations engine, where I was product lead in 2013, we built telemetry in from the start. We tracked whether people clicked on recommendations and whether those who clicked converted at a higher rate, and we A/B tested recommendations on the home page and similar surfaces to see what showing them did to overall conversion. As I remember it, those results justified keeping recommendations across the site and building more of them.

    Innovation accounting, Ries’s system of learning milestones for measuring validated learning against the investment, converts Pole B into language the Pole A board can use without losing accountability. It is the chapter-7 board script again: commit to learning a named thing, by a date, at a cost, then report what was learned and what to test next.

    Cagan: valuable, usable, feasible, viable

    Marty Cagan’s four big risks, the simplest test I have seen for product work, ask whether a feature is valuable, usable, feasible, and viable; he wants them answered in discovery, before the team builds.

    Valuable means it produces an outcome the customer cares about. Usable means the customer can access that value. Feasible means the team can build and operate it within the firm’s constraints. Viable means the business itself can sustain it.

    A Pole A team may optimise for feasible, building what it can build and shipping features that are technically clean but irrelevant to customers. The most user-research-heavy teams sometimes over-rotate on valuable and ship features the team can’t operate at scale.

    A feature is worth shipping only if it meets all four. Run the four-part test on last quarter’s releases and count how many clear all four.

    Edmondson’s intelligent failure

    Fail fast becomes operational only when a failure meets Edmondson’s four criteria for an intelligent failure, which chapter 10 walks in full. Until then it is a slogan a Pole A leader can adopt while keeping the old metrics: failed experiments per quarter is an output number too, and it passes the vanity test no better than features shipped.

    A representative case

    Picture a SaaS product team that has been measuring features shipped per quarter for two years. The number goes up steadily. The customer churn rate also goes up steadily.

    The CEO can’t reconcile the two numbers. Engineering leadership points at the customer success function; the customer success function points at product. The board is being told we are shipping faster than ever in the same quarter that renewals have started falling.

    The Pole B move arrives through a customer advisory board. Several customers on the board, on separate calls, name the same pattern: the product has grown surface area faster than they can absorb it. The features they asked for two years ago are buried under features they didn’t ask for, and the team they originally trained on the platform has churned. The outcome is being eaten by their accumulation.

    The retrospective surfaces the structural problem. Every feature shipped had been valuable, usable, feasible, and viable at the time it was scoped. Nobody had re-evaluated it against the integrated product experience.

    Apple is the clearest counter-example I know. A pair of AirPods is not judged on its own feature list. It is judged on what happens when the same person picks up a phone, then a laptop, then a watch, and the audio follows them without anyone even touching a button. That is a test applied to the whole. Applied feature by feature, as this team applied it, the four-part test can tell you a feature is locally optimal; it says nothing about the whole it joins.

    The fix wasn’t to abandon shipping. The team introduced a quarterly outcome review alongside the existing roadmap review and asked, for each major feature shipped over the past four quarters, whether customers were using it, whether that use produced the outcome the feature was supposed to deliver, whether the maintenance cost still tracked the value, and what customers could now do end to end across the product.

    Half the features failed the test. A third were deprecated. The next quarter’s roadmap was leaner, and the cohort that had been churning steadied.

    The engineering leader running the original output count wasn’t a bad leader. The previous CEO had measured them on output. The investor decks had measured them on output. The internal performance reviews had measured them on output. The system around the leader had reinforced Pole A for years.

    So name what the discipline got the team⁠—predictable cadence, investor confidence, a high-trust engineering culture⁠—and then name what the new conditions required. The leader needed a different measurement system, and time to adjust to it.

    The diagnostic

    Three questions for last Tuesday’s launch celebration.

    • Which pole was I claiming? In the language I used about the launch, did I name what the customer would now be able to do, or did I name what the team had shipped?
    • Which pole did the team’s behaviour show? Look at where the team’s attention went in the week after the launch. Did it go to customer use or to the next item on the roadmap?
    • Which pole does the work actually require? If output and outcome track tightly in your domain, Pole A is legitimate. If you are shipping more and the customer outcomes are flat or worse, Pole A has stopped being a proxy and started being a substitute.

    The board deck often locks in this distinction. Whether the CEO or CTO owns the page, the metric used to describe engineering shapes incentives below. If you run engineering, the metric your CEO uses to describe your function to the board governs the output-versus-outcome question.

    Put the metric that currently judges your function beside the metric that tracks customer progress. In most software-dependent organisations, these are different numbers. A CEO who describes engineering to the board in features-shipped vocabulary creates Pole A incentives three layers down, usually without intending to.

    Ask for one sentence in the next board update that names what customers can now do, not what the team shipped. That is Pole B at board level. The team will read the update.

    Give your CEO this sentence: “This quarter [N] customers began to [do the job] for the first time; from [next quarter] that count replaces features shipped in this report.”

    The exercise

    Rewrite a recent feature as a job to be done. Christensen’s test is specific: a job is the progress a person is trying to make in a particular circumstance; state it in verbs and nouns, and check that candidates for the job come from different product categories.

    The job-story template⁠—“when [situation], I want to [motivation], so I can [expected outcome]”—is a usable scaffold. It comes from the job-story tradition, not from Christensen. The format forces the team to name what the customer is hiring the feature for.

    Notice how often the feature solves the firm’s job rather than the customer’s. When my quarterly performance review is approaching, I want to ship a visible feature, so I can demonstrate productivity to my manager is a job. It belongs to the employee, not the customer.

    Run a companion vanity-vs-actionable metric audit. List your top five metrics. Mark each as vanity (it goes up regardless of whether anything is working) or actionable (you can trace what moved it, and it changes what you do). Defend each judgement to the team.

    The usual engineering ones rarely survive it. Velocity moves whenever estimates move, and stories shipped is the same count in different units. Utilisation is worse than either: queues lengthen as it rises, so a high number is as likely to be a warning as a win.

    If leader-follower dynamics turn out to be your live axis, run Marquet’s “I intend to…” protocol for a week. Chapter 17 lays out the full version. Even one week of replacing “request permission to…” and “recommend that we…” with “I intend to…” shifts who carries the cognitive load of the decision; run it and watch where decisions get made.

    Going upstream

    In-text: Clayton Christensen, Competing Against Luck, on Jobs to Be Done; David Marquet, Turn the Ship Around! and Leadership Is Language, on redwork and bluework and the language of intent.

    Also touched: Eric Ries, The Lean Startup, on innovation accounting and vanity metrics; Douglas Hubbard, How to Measure Anything, on the test that a measurement only earns its keep if it changes a decision; Marty Cagan, Inspired, on valuable / usable / feasible / viable; Jeff Patton, User Story Mapping, and the talk Output vs Outcome & Impact (11 min, watch); Amy Edmondson, Right Kind of Wrong, on the four criteria for intelligent failure (developed in chapter 10).

    Go deeper: Chip and Dan Heath, Made to Stick, on commander’s intent in organisational-messaging terms; USMC, MCDP-1 Warfighting, Ch 4, on mission tactics and commander’s intent; Frederick Taylor, The Principles of Scientific Management (1911), on the planning/doing division Marquet recasts as bluework and redwork; Alan Klement, Replacing the User Story with the Job Story (2013), on the job-story form, which originated at Intercom.

    Manage to outcomes and some of them will miss. Watch what you defend when yours does. The call you made was a testable bet; the thing you protect in the review is usually your identity, and the second job eats the first. In chapter 10 you sit with that review, the one after a decision fails, and ask what the miss costs you next time: whether you spend it shielding the person who made the call or finding out what the call was worth.


    I work with CTOs and CPOs at software companies with roughly 25–500 engineers, where the engineers are faster with AI and the business isn’t yet seeing the full value. When the team ships more and customers are no better off, I help leaders judge engineering by what customers can now do, and report that to the board. If it’s live for you, book a free 30-minute call at hi.chrisgagne.com and bring the one question that would make it worth your time. If you know a CTO or CPO in that spot, pass this chapter on. If you’d rather read on than talk, the newsletter goes on past chapter 23, monthly, at https://www.linkedin.com/newsletters/come-prepared-to-die-7472144387981062144/

    Some book links here are Amazon affiliate links; if you buy through them I may earn a small commission, at no cost to you.


  • On Doing Versus Being Agile

    On Doing Versus Being Agile

    [May 2026] I now reach for Schein on culture, Westrum on generative-vs-pathological organisations, Edmondson on psychological safety, Senge on learning-organisation discipline, and Galbraith’s Star Model alongside Org Topologies for structure as the more rigorous current vocabulary for what this post calls “structure and culture.” The doing-vs-being distinction still holds; the toolkit has matured. I’ve also since added a fifth box at the cheap end of the diagram, to the left of tools: “terms,” changing the words you use. It’s the easiest change and the emptiest one, and I can’t claim much originality for it. Craig Larman named this years ago in the second of his Laws of Organisational Behaviour: any change initiative gets reduced to redefining or overloading the new terminology to mean basically the same as the status quo. New words, same operating model.

    [August 2026] The NUMMI listening questions I set out here, about what changed in the plant and what GM could not replicate elsewhere, are the ones I work through at length in Chapter 3 of Come Prepared to Die. Same plant, read the other way round: the chapter takes NUMMI as the inverse case, where GM copied the production system and left the structure alone. AI now hands you the tools-and-process win almost for free, which leaves the structure you never touched as where most of the remaining gain sits. I came back to that plant from a different angle in the Team Member Handbook post.

    Are you doing Agile, or have you become Agile?

    The difference seems pedantic at first…

    You are doing Agile when you’ve changed your tools and processes. This is relatively easy to do but doesn’t offer much in the way of benefits. You’ve become Agile when you’ve changed you structure and culture too. This is relatively hard to do, but offers significant benefits.

    Agile isn’t just a process. It’s a complete framework that brings together a shift in culture, structure, and processes. This framework is supported by tools such as Rally and other Agile Lifecycle Management (ALM) tools.

    (more…)
  • The Three Most Important Aspects of a Successful Product

    The Three Most Important Aspects of a Successful Product

    [May 2026] The three-part frame (delight, value, good) still anchors how I think about products and AI tools alike. The “create value” section has matured into Reinertsen’s flow economics and cost-of-delay weighting; the “do good in the world” section has become more important, not less, as AI raises the externalities question.

    My elevator speech back then went like this: “I design, develop, and ship innovative products that delight customers, create value, and do good in the world.”

    Those last three components⁠—delight customers, create value, and do good in the world⁠—are the three most important aspects of a successful product. Here’s why I think so.

    (more…)
  • “Silent Lens” Wins Google Ideas challenge at the Google “Develop for Good” Global Hackathon

    “Silent Lens” Wins Google Ideas challenge at the Google “Develop for Good” Global Hackathon

    [May 2026] Silent Lens didn’t ship; for off-grid mesh comms today I’d point at Meshtastic, with the caveat that Meshtastic isn’t hardened against adversarial regimes the way this design aimed to be. The public-key crypto for evidence, immune-system trust gradient, and courier-fallback delivery were all aimed at a much harder problem, and the architecture still seems plausible to me.

    I attended the Google I/O Extended “Develop for Good” hackathon in San Francisco in late June. We were asked to create a solution for one of three challenges:

    • Google Politics & Elections: Citizen Engagement for Politics & Elections
    • Google Ideas: Conflict Reporting for Blackout Situations in Repressive Regimes
    • Google Green: Help us all be a little greener!

    Our team won the Google Ideas challenge! My sincere congratulations to my team mates Perry Chow, Ansgar Halbfas, Ryan Quellet, and Andrew Song.

    (more…)
  • The Customer is the Marshmallow

    The Customer is the Marshmallow

    [May 2026] This argument still holds. Both “ship quickly and often” and “defer commitment” remain true today; cost-of-delay weighting (Reinertsen, Fox & Gregory) and real-options framing are the sharper economic vocabulary that grounds them.

    [August 2026] “They build slowly and test often” is the practitioner’s version of an argument I make more formally in Chapter 7 of Come Prepared to Die: a plan held as a commitment kills the learning, and a plan held as a hypothesis invites it. The marshmallow is what a premature commitment feels like when it lands.

    Many of you will be familiar with Peter Skillman’s Marshmallow Challenge, an exercise frequently given to teams and business school students. Teams of four are given 20 pieces of spaghetti, 1 yard of tape, one yard of twine, and a marshmallow. They are then given 18 minutes to build a free-standing structure that places the marshmallow as high off of the table as possible. The team with the highest marshmallow wins.

    If you haven’t seen it already, Tom Wujec’s TED talk is a good place to learn about the challenge. And if you haven’t introduced your team(s) to it, take 45 minutes out of one of your days to administer the challenge and see what revelations you get.

    (more…)