The Knowledge Exchange

Knowledge platforms fail because nobody tends them.

The Knowledge Exchange pairs a small team of trusted human curators with AI agents that handle the routine work of keeping knowledge connected, current and useful. The humans hold the judgement. The agents make the tending affordable.

How to start Why it works

Five things make this one different.

01 · Human curators

One to five trusted people make every call.

A named lead gardener is accountable for everything the agents do. Anything sent to a person is sent by a person.

Humans hold the judgement
02 · AI agents

Agents do the routine tending, day and night.

They repair links, spot stale content, draft welcomes and flag what people keep searching for and not finding.

Drafts only — never sends
03 · No new destination

It lives in Teams, Slack and email.

The exchange meets practitioners where they already work. In shared channels, agents only speak when spoken to.

No new platform to adopt
04 · Reversible by design

Every action is logged and can be undone.

Each connection the exchange draws explains itself, and one click reverses any agent's work.

Tested before launch, watched after
05 · Built-in measurement

It records how practice spreads.

Every applied piece of knowledge becomes evidence of change moving through the sector. The data belongs to you.

Collected with consent
THE EXCHANGE — RUNS INSIDE YOUR ENVIRONMENT, ON YOUR IDENTITY The gardeners One to five trusted humans. They review, steer and overrule. Anything sent to a person is sent by a person. The agents They connect, scan and draft, around the clock. Plain scheduled code first; AI only where judgement is needed. The knowledge graph Stories, contexts and connections — an index over your existing systems. decisions & sends ↓ ↑ proposals & drafts connect · scan · retrieve The solo practitioner Searching in plain language, getting help to apply knowledge. The exchange remembers their context. The community spaces Teams, Slack and email — where people already work. Agents only speak when spoken to. conversation answers, on request agents introduce people to each other

How it works, in one picture. Practitioners meet the exchange where they already work. Agents do the continuous background work. One to five gardeners make every decision that reaches a person. The dashed line matters most: when the best answer is another practitioner, the agents make the introduction.

The problem

The sector keeps building knowledge hubs that go quiet within a year.

The evidence is clear about why. These platforms don't fail on technology. They fail because nobody is paid to keep them alive: to welcome contributors, connect new material to the people who need it, and notice what's missing. That work is called curation and facilitation, and it's almost never funded past the launch grant.

What's left behind is familiar to every practitioner: a well-built site full of well-written reports that nobody reads. A bookshelf with analytics.

Our answer is to make the tending affordable, so it never stops.
First principles

Knowledge is only worth something when someone uses it.

Before designing anything, we asked what's true about knowledge in practitioner communities, regardless of technology. Four things held up.

One

Value comes from application.

A report that changes what a practitioner does tomorrow is worth more than a hundred that don't. Application is the only honest measure of quality.

Two

What works in one place must be matched to another.

A practice transfers when it fits the new community's situation, constraints and capacity. Today that matching happens by luck, or not at all.

Three

Human attention is the scarcest resource.

Curation and facilitation are what keep an exchange alive, and both take time from people. This is exactly what the sector doesn't fund.

Four

People trust people, not platforms.

Practitioners trust named peers and known intermediaries. A design that asks a community to trust software directly won't get that trust.

Keeping an exchange alive means doing four jobs, every day.

A platform dies when any one of these jobs goes undone. The empty bookshelf is what remains when all four stop.

Connecting

Linking knowledge to the people and places that need it. Left undone, knowledge piles up in an archive.

Noticing

Spotting what's going stale, what's missing and what people keep asking for. Left undone, the exchange goes silent.

Welcoming

Thanking contributors, filling gaps, improving what's there. Nobody writes for a place that doesn't write back.

Earning trust

Built slowly through reliability and human presence. Lost instantly with one wrong answer in the wrong place.

How it works

Human curators do the judging. AI agents do the legwork.

At the centre are one to five trusted humans we call the gardeners. The agents work around them: scanning for broken links and stale content, suggesting connections, drafting welcome messages and requests for contributions, and flagging what practitioners keep searching for and not finding.

The gardeners review, approve and overrule through a dashboard built for the job. A named lead gardener is accountable for everything the agents do, and anything sent to a person is sent by a person. When investment grows, it buys more human gardening before it buys more automation, because five part-time gardeners spread across the field hear more, and are trusted by more people, than one full-time curator.

A week of tending looks like this.

Working alone

The exchange remembers who you are and what you're working on.

A practitioner searching on their own gets a conversation, not a list of documents. The exchange knows their context from previous visits and helps them work out how to apply what they find.

In shared spaces

In group channels, agents only speak when spoken to.

In the Teams channels, Slack workspaces and email threads where the community already gathers, the rule is simple and enforced in software: agents answer questions and fetch material when asked. They never start conversations, never correct anyone in public, and never pretend to be members of the community.

When the best answer is a person, the agents find the practitioner who has already done the thing and make the introduction.
Safety

Every agent action is logged, explained and can be undone.

We don't claim the agents will never make a mistake. We've designed the system so that no mistake is permanent, and most of the system isn't AI at all. Six commitments hold this together.

Plain code first, AI second.

Routine work like link checks and content scans runs as ordinary scheduled code. AI is used only where a task needs judgement.

Small, tested models over expensive ones.

We use the smallest model that passes our tests, and we test again every time anything changes. This keeps running costs sustainable for the long term.

Everything is logged and reversible.

Every action is attributed and can be undone with one click. Nothing is ever deleted, except when a contributor asks for their material to be removed. That request is always honoured.

Every connection shows its working.

When the exchange links a story to a practitioner, it says why. There are no unexplained recommendations.

Tested before launch, watched after.

The agents pass a test suite before anything goes live, and the gardeners review their work as a weekly habit.

Some knowledge is off limits to automation.

Community-valued material is a protected class the agents cannot alter or retire. The defaults are conservative on purpose.

We also ran the design through a pre-mortem: eight plausible ways a platform like this fails, each answered by a decision already in the architecture. And the whole exchange runs inside your existing IT environment and identity, so there is no new system for your technology partner to host, secure or say no to.

Measurement

Each time knowledge gets used, the exchange records how change spreads.

Change in this sector shows up first in relationships and practice, long before it shows up in population data. No current tool can see that layer. A working exchange can, because seeing it is a side effect of doing its job: when a practitioner finds a practice, adapts it and reports how it went, that's a record of practice spreading through the sector.

Each record answers five questions.

  • What travelled — the story or practice, and the form it took.
  • Where it came from — the community it started in, and the context it worked in there.
  • Where it went — the community that adopted it, and how their situation differed.
  • What they changed — the adaptations made to fit, which is knowledge in its own right.
  • What happened — the reported result, including "it didn't work here". Failures teach the sector more than successes.

This data is collected with practitioners' knowledge, aggregated before it travels, and belongs to you alone. And it compounds: every month of operation makes the record more valuable, which is a reason to start sooner rather than later.

The knowledge itself

The exchange holds practitioners' stories, sorted by where they'll work next.

Quality

Useful beats recent.

A 2019 story that fits a practitioner's situation is worth more than this quarter's report that doesn't. So the agents spend their effort on matching stories to contexts, not on tidying. Old content isn't pruned by default; its connections are tested and renewed.

Contribution

Gaps are advertised. Voices are protected.

Where practitioners keep searching and finding nothing, the exchange says so, and asks a named person to fill the gap. Quality checks appear as friendly prompts ("this story would travel further with an outcome note"), never as gates. And the agents never rewrite a contributor's words, because a community stops recognising itself in sanitised prose.

Three problems we haven't solved yet.

  • Consent around measurement. What gets collected, what practitioners are told, and what they can decline needs to be worked out with practitioners, not for them.
  • Protecting small communities. Small communities can be identified from the detail in a story. Which stories travel openly, which travel in aggregate and which stay home is real design work, and it will follow Indigenous data sovereignty principles, with communities holding authority over their own stories.
  • Measuring the early period. Evidence of practice spreading takes time to build. We agree what success looks like at each stage with you up front, rather than arguing about it later.
Getting started

It starts with a short sprint, then a pilot inside your walls, then the sector.

Nobody should buy this on faith. Each stage produces the evidence that justifies the next, and each has an agreed point where you decide whether to continue.

1

A sprint builds working prototypes.

A short first engagement produces working prototypes on realistic material: conversational search, agent-assisted curation and the gardeners' dashboard. It ends with a demonstration on a set date, judged against go or no-go criteria we agree at the start.

2

The first deployment runs inside your organisation.

Your staff become the first community of practice, on your existing systems. The approach gets tested with a forgiving audience, and the evidence builds before anything faces the sector.

3

Once proven, the exchange opens to the sector.

It goes public carrying test results, trained gardeners and a real track record instead of promises. This is also when the measurement record switches on.

You own the specification and the data throughout. The design can be rebuilt on any platform, everything exports in open formats, and we name an archival home for the stories from day one. A design built on the observation that platforms die owes you an answer about where the knowledge goes if this one ever does.

The Knowledge Exchange

Ready to change? We're ready to help.

Practitioners will never see any of this architecture. They'll only notice whether the exchange feels looked after, current and worth returning to. We'd like to show you how it stays that way.

Get in touch