How it works
Curated context
Documents record what was decided. They don't record why, or what was considered and rejected, or what changed two weeks later. By the time knowledge makes it into documentation, the thinking that produced it has already moved on.
Curated context starts earlier, at the moment of thinking rather than the moment of writing.
Workflow · Create a goal
Create goal
Write a goal directly to your workspace
Increase customer retention by 50% by end of Q3
We've recruited a Forward Deployed Engineer to work on key customer accounts this FY; their contributions should help increase retention.
Ship customer-requested improvements from FDE account reviews
shipped per quarter → 3 1
Close FDE-raised product gaps within 30 days
median days to close → 30 62
Authored, not extracted.
Engramic's knowledge graph is built from typed topics: goals, constraints, decisions, concepts. Each one is authored deliberately by a human, by an agent, or by both working together. It's put there intentionally, with the reasoning attached, rather than pulled from a document corpus or inferred from usage patterns.
That distinction matters. An extracted knowledge base tells you what your organisation has written. A curated knowledge graph tells you what your organisation has decided, what it's committed to, and what it's still working through. Those are different things, and agents need the latter.
Knowledge that knows what time it is.
A knowledge base is static. Engramic's graph has a sense of time. Temporal events record what happened, when, and why, layered on top of the topics they relate to. When a goal changes, the change is recorded. When a decision gets revisited, the prior version is preserved alongside the new one.
This means the graph accumulates the history of how the organisation came to know what it knows. When something conflicts with what was previously agreed, it surfaces, rather than quietly undermining an agent that had no way of knowing things had changed.
Conflicts appearing in the graph aren't a sign the system is broken. They're a sign it's working.
- 16:48Q3 forecast committed — 18% over planPlan Agent
- 14:32Conflict surfaced — Tier B vs Q3 planAgent
- 14:22Pricing tier A revisedGeorge Harrison
- 11:05How will Tier B affect annual contracts?Paul McCartney
- 09:42Initial pricing model committedFinance Team
- 09:15Tier B raised — 12% uplift agreedJohn Lennon
AI Fluency · 4D Framework
A practical model for working with AI deliberately — referenced in our own approach to authoring context.
Delegation
what to ask of AI
Description
how to frame the task
Discernment
what to trust in the answer
Diligence
staying accountable for the outcome
The platform works best when the people using it do too.
Curated context is only as good as the conversations that produce it. The humans authoring knowledge need to be comfortable collaborating with AI deliberately.
The 4D AI Fluency Framework — Delegation, Description, Discernment, and Diligence — developed by Prof. Rick Dakan and Prof. Joseph Feller in partnership with Anthropic, is a practical starting point. It's free, model-agnostic, and designed for exactly this: helping people develop the judgement to work with AI effectively. AI Fluency: Framework & Foundations is available on Anthropic Academy →
Knowledge improves by asking questions.
Engramic's agent, Alia, is designed to help fill knowledge gaps, for agents being onboarded and for the humans building the graph. When a topic is underspecified, when a goal lacks a constraint, when two decisions look like they might conflict, Alia asks.
This means the knowledge graph gets richer as it grows and work gets done. The act of answering a well-formed question surfaces knowledge that would otherwise have stayed in someone's head, and puts it somewhere agents can use it.
On the write side, Alia proposes what belongs in the record and a human approves it. Asking her is the read side of the same job. Meet Alia →
12 open · 8 answered (24h) · 5 topics sharpened
How does this interact with existing annual contracts?
Triggered by Tier B raised — 12% uplift. The graph has 23 active annual contracts on Tier B. Mid-term uplift may conflict with the renewal clause in the standard MSA.
Once the knowledge is in the graph, the next question is how it reaches an agent before it acts.
That's what agent onboarding does