Use Cases
Your next AI session should start with the work you chose to keep.
Recall selected durable context across projects and sessions, then correct or forget what no longer applies. Analytics and HubSpot reconciliation remain specialist use cases.
Start with the work that crosses sessions: a confirmed launch decision, a writing preference, a project constraint or a lesson learned the hard way. Save it in one authorized space, then recall, correct or forget it as the work changes.
Analytics has a more specialized moment: “why don’t these two numbers match?” ClariLayer reconciles a saved definition against supported warehouse or row-free HubSpot evidence and flags conflicts as caveats — checked, not blindly asserted. And when two teams' numbers disagree, the same engine scales up: the Governed Context Edge is a private pilot with no public price.
Analytics · worked example
“Net revenue” — two numbers, one caveat
Your dashboard reports $1.42M in net revenue for the quarter. The query your agent just wrote returns $1.51M. A $90K gap, and the QBR is in an hour. Which one is right?
You ask your agent to reconcile the saved net_revenue definition against the warehouse. It runs the stored SQL with its own access and reports the result shape back to ClariLayer, which compares the saved definition's declared signals — the columns, grouping, and aggregates its SQL implies — against the shape your agent actually got back. They don't line up: the live result is missing a column the saved definition expects, so reconcile records a caveat. That's the signal to look closer — not a ruling on which dollar figure is right.
The caveat is what sends your agent digging. With its own warehouse access it traces the $90K back to the cause: the ad-hoc query never joined the refunds table, so it reported gross, not net. The caveat caught the $90K discrepancy an hour before the QBR — flagged the moment the live result drifted from the saved shape. You ship the refund-adjusted $1.42M, then remember the correction once — “net revenue must net refunds” — so next quarter the agent starts from it instead of rediscovering it. ClariLayer never held your warehouse credentials and never ran the SQL itself — your agent was the connector.
reconcile
Why don't these two numbers match?
The moment
Two reports that should agree don't. Your dashboard says one revenue figure, the ad-hoc query you just ran says another, and you have no idea which one to trust — or where the gap crept in.
With ClariLayer
Ask your agent to reconcile the saved definition against your real warehouse result. Your agent runs the stored SQL with its own access and reports back the result shape; ClariLayer compares what the definition declares against what actually came out. A mismatch surfaces as a caveat — so you and your agent know exactly which number to treat with care, and why.
What actually happens
- 1In this personal flow, your agent runs the stored SQL itself — ClariLayer never holds your warehouse credentials and never executes SQL server-side.
- 2Declared-vs-actual mismatch is flagged as a caveat; a clean pass leaves the entry asserted (the honest baseline).
- 3The caveat travels with the definition, so the next session starts from the discrepancy instead of rediscovering it.
HubSpot CRM reconcile
Your playbook says one stage. HubSpot still uses two.
The moment
A deal-stage property has a canonical internal value, but an old alias is still populated. Labels look friendly in the UI while workflows and integrations depend on exact internal values, so drift can stay invisible until it breaks reporting or automation.
With ClariLayer
Save a row-free HubSpot property contract, then let your agent inspect the provider with its own access. It sends only bounded property metadata and value distributions. ClariLayer compares expected values, the canonical value, deprecated aliases, and labels; a mismatch becomes a caveat and a clean check remains asserted.
What actually happens
- 1ClariLayer receives no HubSpot credentials or CRM records and never calls HubSpot; the agent is the connector.
- 2In a complete distribution, an exact zero means absent from observed records — not missing from HubSpot configuration.
- 3HubSpot CRM reconcile is live for authenticated organizations.
recall + remember
A launch decision survives the next session
The moment
The team decided to lead with the product demo and move technical detail into the docs. A new session drafts the page from scratch and reverses that choice because the reasoning stayed in an old chat.
With ClariLayer
Save the confirmed decision in the selected project space. A compatible AI client can recall it with its source and applicability attached, then use it in the new task without treating it as a rule for unrelated work.
What actually happens
- 1Recall is limited to the selected authorized space; it does not search every space.
- 2Remember supports durable facts, preferences, decisions, rules and lessons, with source and applicability attached.
- 3Correction and scoped forget keep an old decision from becoming permanent folklore.
selected history
Bring forward only the history you choose
The moment
Useful decisions are spread across old local conversations, but importing an entire archive without review would create noise and an unacceptable privacy boundary.
With ClariLayer
Choose supported local history, use a qualified extraction provider, and inspect the exact initial proposal before accepting it. Source support and provider qualification are separate checks; connecting an AI client grants neither.
What actually happens
- 1Claude CLI is the qualified extraction provider; Cursor history import has limited support.
- 2The preview is bounded and exact: nothing enters the selected space until you accept the proposal.
- 3Later capture is optional and configured separately rather than implied by the first import.
correct + forget
The plan changed. The old rule should stop returning.
The moment
A launch rule was right last month and wrong today. Leaving both versions active would make recall less trustworthy than the chat history it replaced.
With ClariLayer
Correct the durable entry with the new decision, or forget it within the relevant scope. ClariLayer preserves enough source and applicability context for later work to understand what changed and where the replacement applies.
What actually happens
- 1Corrections are explicit updates, not a promise that memory will infer every change automatically.
- 2Scoped forget and exclusions prevent material from returning where it no longer belongs.
- 3A completion receipt can record the agent's declaration, but it does not independently certify that external work happened.
bounded capture
Keep future work only after you configure the boundary
The moment
After the initial history review, you may want later supported sessions to contribute durable candidates without repeating the import workflow each time.
With ClariLayer
Configure optional capture separately, with an explicit scope, limits and exclusions. This is a bounded collector path, not universal automatic capture or a promise that every useful detail will be retained.
What actually happens
- 1Initial import acceptance does not authorize later capture.
- 2Collector reports and exclusions make the configured boundary inspectable.
- 3Recall remains subject to the selected space, access, lifecycle and applicability filters.
Reconciled, not blindly asserted
In Analytics, a hand-written CLAUDE.md of claimed definitions has the same trust problem as the original numbers — it’s just asserted text. ClariLayer can reconcile a definition against a warehouse result or bounded, row-free HubSpot observations, and surfaces conflicts as caveats so you know where to look. A clean reconcile leaves the entry asserted. Those are the public statuses today; verified is not a live status.
For teams · the Governed Context Edge · private pilot
Yours today, your team’s tomorrow.
ClariLayer starts with personal context. The Governed Context Edge accepts deliberate proposals into a shared, governed team canon. It is a private pilot with a few design-partner teams and has no public price. Personal context is not promoted automatically.
Two VPs, two numbers, same metric
The problem
The board meeting stalls while Finance and Marketing debate whose revenue number is correct. Both pulled from the warehouse. Both are technically right. Neither is governed.
A person can deliberately propose selected context into the team layer. ClariLayer keeps canonical definitions with managed variants, while personal context stays separate unless it is proposed.
Audit and approval trails
The problem
The auditor asks who approved the revenue-recognition metric and when. The answer is scattered across Slack threads, email chains, and someone's memory.
Once context is team-owned, every definition carries version history, an approval chain, and the conversation behind it — the 'why', not just the 'what' — so a change stays inspectable when it's deployed, deprecated, or rolled back.
Start with one decision worth carrying forward.
The personal offer starts free with no credit card. Connect a compatible AI client, choose the space, and save one confirmed rule.