CAPTURING TACIT KNOWLEDGE FOR AI AGENTS

A rulebook can be copied, but a veteran operator's ear for a failing bearing cannot.

That difference is part of what makes tacit knowledge so valuable – and so difficult for organisations to preserve.

Michael Polanyi, who coined the phrase in the 50s, later put it in eight words: 'we can know more than we can tell'.

Which makes it a blind spot for AI agents. If you can't capture it, how do they learn from it?

Our new paper proposes a practical way in: the tacit fragment.

A bounded record of one piece of practice – where it came from, when it applies, how strong the evidence is, and who reviewed it.

We're also introducing Metis. An open reference architecture for capturing and validating these fragments, then governing when agents may use them.

Read about it in our latest Substack.