Your agents don’t need to persist. Your purpose does.
How do I know what to put in my board pack?
This archived article remains available at its original address. Unl, your why agent, carries the decisions you settle and why into your AI work. See how it works.
Most founders answer this with a template: metrics slide, product slide, hiring slide, risks slide. Templates fill space reliably and answer the wrong question. What belongs in a board pack is whatever crosses a line you told the board mattered — and a generic checklist has no way to know what that line is.
A board pack earns its length one slide at a time, and the test for each slide is the same: does this cross a commitment the board is tracking? Unl holds that commitment, so the question “what goes in” has a specific answer instead of a template’s worth of standard sections.
Why does a template answer the wrong question?
A standard board-pack template — metrics, product, hiring, risks — is built to be safe rather than useful. It fills every category so nothing looks obviously missing, but it has no mechanism for deciding which of this quarter’s facts the board actually needs to see, because a template doesn’t know what your board is watching.
The result is packs that are complete by category and thin on judgement. Every section has content; almost none of it says plainly whether the thing the board cares about is holding or slipping.
What does the real filter look like?
Say you're running a vertical SaaS company, whose board-level commitment is explicit: logo churn under 2% a month, the survival metric I told the board. This quarter’s activity produces dozens of updates worth a slide by template logic — a new hire, a feature launch, a partnership conversation.
Measured against your own commitment, only one of them clears the bar for the pack: “Churn 2.7% against your under-2% commitment — that’s the slide that matters.” Everything else can wait for a conversation; that line can’t.
Why can’t a template, or a general-purpose model, apply that filter?
Neither a template nor a general-purpose model can know that 2% monthly churn is your survival line, because that’s a decision you made and told your board directly — it isn’t written anywhere a generic system could discover it. A model asked to draft the pack will fill the standard sections competently and still miss the one number that actually needed to lead.
Measured context holds your commitment and applies it to the quarter’s facts, so the pack’s contents are decided by what crosses your own line — not by which category happened to have something to say.
What belongs in a board pack is whatever crosses a commitment you told the board mattered, not whatever fills a template’s standard sections; measured context holds that commitment, so the pack’s contents are decided by what actually crossed a line.
Reads through Unl arrive with measured context — in the presence of the decisions you’ve already settled. It works today: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.
Read further
Questions people ask
What should actually go in my board pack?
Whatever crosses a commitment you told the board mattered — not a generic template’s worth of standard sections. For one founder that meant a single churn figure crossing their own survival line, while a template would have buried it under an unrelated hiring update. Measured context holds the commitment so the filter is your own line, not a checklist.
Why does my board pack feel padded with slides nobody needed?
Because a template fills every category to look complete, regardless of whether anything in that category actually crosses a line the board is tracking. The pack ends up thick with content and thin on judgement — every section says something, but rarely the one thing the board actually needed to hear.
Can AI decide what belongs in my board pack?
It can fill a standard template competently, but it can’t know which commitment you told your board mattered — a churn line, a runway floor — because that’s a decision made in conversation, not something discoverable in the data. Measured context supplies the commitment so the pack surfaces what actually crossed it. It works today: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.
What if the board asks for something that none of my commitments cover?
Then it belongs in the pack because they asked, but it is context rather than a verdict. If they keep asking for it, that is a sign it should become a commitment with its own line, and making it one is your call with them.
What this is
Your agents don’t need to persist. Your purpose does.
Save the thoughts, decisions and targets worth keeping, each with its reasoning, carried into every AI session the moment they matter. A new unit of exchange between you and your AI: the Settled Why with standing that travels. Unprompted.
Your whole AI world. What you decided at the epicentre. It works inside Claude, Claude Code, ChatGPT and Cursor, and connects in a couple of steps.
MCP native·Human settled·Model agnostic·Your data
Measured Context
Connect Unl to bring the right information into the moment.
Your sources, read against the criteria you set.
The full product, open. Free to start. Paid plans from $10 a month.