Use Cases

Why don't these two numbers match?

Connect ClariLayer to Claude Code, Cursor, Codex, or claude.ai. Analysts and RevOps operators can recall durable context, check warehouse or HubSpot definitions, and carry the decision into the next session.

These are the moments an analyst or RevOps operator hits in their own agent, against often messy warehouse or HubSpot definitions. No governance program or procurement cycle. Just your working context, the source access you already have, and your agent.

The acute one is the first reconcile: “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 in private pilot now.

A 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

  1. 1In this personal flow, your agent runs the stored SQL itself — ClariLayer never holds your warehouse credentials and never executes SQL server-side.
  2. 2Declared-vs-actual mismatch is flagged as a caveat; a clean pass leaves the entry asserted (the honest baseline).
  3. 3The caveat travels with the definition, so the next session starts from the discrepancy instead of rediscovering it.
See how reconcile works

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

  1. 1ClariLayer receives no HubSpot credentials or CRM records and never calls HubSpot; the agent is the connector.
  2. 2In a complete distribution, an exact zero means absent from observed records — not missing from HubSpot configuration.
  3. 3HubSpot CRM reconcile is live for authenticated organizations.
See the HubSpot reconcile recipe

recall + remember

New agent session, zero re-explaining

The moment

Every fresh chat starts from nothing. You re-type which table is canonical, which join is the right one, that refunds shouldn't count in revenue — the same context, session after session, before you can ask the real question.

With ClariLayer

ClariLayer connects over MCP to Claude Code, Cursor, Codex, or claude.ai. From then on your agent can pull relevant context mid-task and save each confirmed correction so it sticks. Exact names lead, use-case scoping stays explicit, and the response tells the agent when potentially useful context was scoped away.

What actually happens

  1. 1Recall deterministically prioritizes exact named entries and relevant saved context, with provenance and status attached.
  2. 2Remember saves a single definition, schema note, join path, or gotcha so it persists — default status asserted, provenance you.
  3. 3Local coding agents use a context key; claude.ai connects as an OAuth custom Connector with no context key.
See recall and remember

bootstrap

Start from the SQL you already have

The moment

A blank context store is its own kind of friction — and hand-typing a CLAUDE.md of every definition is the documentation graveyard all over again. You want day-1 value, not a cold empty store you have to fill by hand.

With ClariLayer

Point ClariLayer at the work you already have: SQL, dbt models, CLAUDE.md or freeform notes, a codebook or data dictionary, and a semantic model. SQL, dictionaries, and semantic models become structured context; dbt and notes are imported too. Day one, your agent starts from your world instead of a blank store.

What actually happens

  1. 1Bootstrap accepts five sources today: SQL, dbt models, CLAUDE.md / freeform notes, a codebook / data dictionary, and a semantic-layer artifact (a Databricks Metric View or dbt semantic models).
  2. 2SQL, the dictionary, and the semantic model are structured (SQL is server-parsed; a codebook maps into one schema-note per variable; a semantic model maps into one canonical metric definition each); dbt and CLAUDE.md are stored as raw schema-notes and notes you can reconcile later.
  3. 3Your agent supplies the content — ClariLayer doesn't connect to your warehouse or filesystem directly.
See bootstrapping your context

completion receipt

Did the agent's context declaration make it into the record?

The moment

The agent used a durable rule, discovered a correction, and then declared the task finished. Next session, you cannot tell whether it declared context updated or no update required.

With ClariLayer

Managed instructions guide supported local agents through recall, a confirmed live context update when needed, and context_checkpoint before completion. The receipt persists the agent's context_updated or no_update_required declaration and validates the ownership and eligibility of referenced ClariLayer entries; it does not independently prove an entry changed.

What actually happens

  1. 1The receipt records the agent's bounded managed-protocol declaration; it is not a generic task-success certificate or independent proof of a change.
  2. 2It does not prove code deployed, a query is correct, a warehouse check passed, or saved context matches an external system.
  3. 3Managed instructions are a behavioral protocol for supported local agents, not a hard gate every MCP client must obey.
See the completion checkpoint loop

compounds

Your agent stops making your data mistakes

The moment

It keeps reaching for the wrong table. It joins on the column that looks right but isn't. It counts refunds in revenue — the exact mistake you corrected last week, and the week before that.

With ClariLayer

Every correction you make, every reconcile, every note quietly persists. Your agent grounds on more of your context over time, so it gets progressively more right about your data — the wrong-table, wrong-join, refunds-in-revenue mistakes stop repeating. The longer you use it, the more it feels like Claude Code finally understands your project.

What actually happens

  1. 1Corrections accumulate through remember and recall — the context you build is the moat.
  2. 2Caveats from earlier reconciles keep steering the agent away from the definitions you've already flagged.
  3. 3More grounded every week: the value compounds the longer the context layer rides along.
See how context compounds

Reconciled, not blindly asserted

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 as your personal context layer. Everything you establish solo is what your team inherits: the Governed Context Edge promotes your reconciled definitions into a shared, governed team canon — built, in private pilot with a few design-partner teams, and open for early-access requests now.

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.

As personal context merges into shared team context, ClariLayer keeps canonical definitions with managed variants — both versions stay transparent, but only the approved, owned definition is marked the board-ready source of truth.

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.

Recognize any of these moments?

If you already live in Claude Code, Cursor, Codex, or claude.ai against warehouse or HubSpot context, connect ClariLayer and stop re-explaining the same durable rules.