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.

Ben pointed out how much the group already has.

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.

Ben and Sam took sovereign AI further than data centres.

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.

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

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

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.

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

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

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.

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

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).

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

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.

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.

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.

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.

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.

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

What’s in the way

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