Features · selected memory for AI work
Choose an authorized space, recall durable facts, preferences, decisions, rules and lessons, then correct or forget them as the work changes. Selected history import and later capture each stay explicit and bounded.
One layer, two clear jobs
The working loop
Select the space, keep what matters, use it where it applies, and correct it when the work changes.
recall_contextBring relevant facts, preferences, decisions, rules and lessons from the selected authorized space into a new project or session. Source and applicability stay attached so the agent can judge where each item belongs.
rememberSave a confirmed correction, preference or project rule when it becomes useful beyond the current chat. Later corrections remain explicit, and scoped forget or exclusions remove work that should no longer return.
review historySelected supported local history can produce a bounded preview. You accept the exact initial proposal before import. Ongoing capture is optional, configured separately and limited by its own authorization and exclusions.
reconcileFor Analytics work, reconcile compares a saved definition with a warehouse result shape or bounded, row-free HubSpot property metadata and distributions. A mismatch becomes a caveat; otherwise the entry remains asserted.
Beyond the core loop
CRM evidence, an explicit completion checkpoint, and an inspectable Console make the surrounding context decision visible without pretending every check is a verification stamp.
HubSpot CRM
Store expected internal values, canonical values, deprecated aliases, and labels. Your agent reads HubSpot with its own access and sends bounded metadata and distributions; in the personal MCP path, ClariLayer receives no CRM credentials or records and never calls HubSpot.
Completion receipt
Managed instructions guide a supported local agent through recall, confirmed context maintenance, and context_checkpoint. The durable, idempotent receipt persists the agent's context_updated or no_update_required declaration and validates ownership and eligibility of referenced ClariLayer objects; it does not independently prove an entry changed or certify code, query correctness, deployment, or an external system. Proposal-only work and update_failed cannot complete the loop.
Context Console
Review proposals, inspect the recall activity and Replay graph, compare local definitions with imported canon, label conflicts, record an adjudication, and capture corrections. The Console makes the trust loop inspectable without turning it into approval ceremony.
For HubSpot, an exact zero in a complete distribution means the value is absent from observed records; it does not mean the option is missing from HubSpot configuration.
Analytics specialist path
For Analytics, a hand-typed file of claimed definitions has the same trust problem as the original numbers — it's just asserted text. ClariLayer can reconcile a saved definition through two shipped evidence paths. For warehouse context, your agent reports a result shape from SQL it ran. For HubSpot property contracts, it reports bounded property metadata and row-free distributions. ClariLayer compares the declared contract with that evidence and flags a mismatch as a caveat.
In this personal MCP path, your agent remains the connector. Source support is separate from qualifying the extraction provider used for selected-history import. ClariLayer never holds warehouse or CRM credentials, executes SQL server-side, or calls HubSpot. Warehouse evidence may contain preview rows if the agent chooses to send them; HubSpot evidence never contains CRM rows. Public reconcile uses two honest statuses: a mismatch becomes caveat, otherwise the entry remains asserted. Verified is not a live status.
assertedSaved and not contradicted — the default for anything you remember. After reconcile, applicable checks may pass or be inconclusive and the entry still remains asserted; a mismatch becomes a caveat.
caveatReconcile caught a declared-vs-actual mismatch. The valuable signal: you and your agent now know exactly what to treat with care.
provenanceEvery entry shows where it came from — you, SQL, a dictionary, dbt, a semantic model, or an agent proposal — next to its status so trust stays legible.
in-flowThe working loop rides inside the agent you already use, over MCP. The Console is there when you want to inspect it, not as a required destination.
In-flow, via MCP
Connect a compatible remote Streamable HTTP MCP client. The Claude CLI is the qualified extraction provider; Cursor history import has limited support. Connection alone does not import history or authorize provider processing. Once connected, your agent can recall relevant context mid-task, remember confirmed corrections, and reconcile warehouse or HubSpot definitions without leaving the flow. The AI agent context guide walks through the managed recall-first loop for supported local agents, including the completion checkpoint.
Recall stays inside the selected authorized space. Optional capture has separate setup, limits and exclusions. Already run a metrics stack? See how ClariLayer sits above your semantic layer.
Connect a compatible client through the guided setup. OAuth is preferred where available; secure client-side key configuration is the fallback.
Choose a supported local history source and qualified extraction provider only if you want to import past work.
Review the exact initial proposal before accepting it into the selected space.
Configure later bounded capture separately when it helps, with its own authorization and exclusions.
A session, before and after
In the specialist Analytics path, say you're chasing a familiar gap: the revenue dashboard says one number, the ad-hoc query you just ran says another, and the board deck is due this afternoon. Here is the same task without ClariLayer, then with it — using only the shipped loop, nothing roadmap.
Without a context layer
orders — but your canonical revenue lives in fct_orders, and it's counting gross, refunds included.With ClariLayer, in-flow
bootstrap — on day one you point it at ./analytics/sql and your dbt models, so the canonical revenue definition is already in your context store, structured into tables, joins, and time grain.recall — the agent pulls that definition mid-task and reaches for fct_orders from the start, with provenance and status attached so you can see where it came from.reconcile — you ask it to check the saved definition against the warehouse. It runs the SQL with its own access and reports the result shape back; reconcile compares that against the definition's declared signals — columns, grouping, aggregates — and the shapes don't match, so it records a caveat. That caveat is the flag to investigate, and it sends the agent back to the numbers, where it finds refunds are still in the total.remember — you save the correction once: net revenue must net refunds. Next Tuesday it's already there; the agent doesn't re-litigate refunds, and the context you built quietly remains available when it applies.context_checkpoint — before completion, the agent declares context_updated and references the active ClariLayer entry. If a review finds that nothing durable changed, it declares no_update_required instead. The checkpoint persists that declaration and validates eligible references; it does not independently prove an entry changed.That caveat is the working output of the loop: reconcile records a caveat on a declared-vs-actual mismatch, or leaves the entry asserted when nothing conflicts. Throughout this personal MCP flow, ClariLayer never holds your warehouse credentials or executes SQL server-side: your agent is the connector, sending result metadata and any preview rows it chooses to include. The completion receipt persists the agent's bounded declaration; it does not independently prove a context entry changed or certify the SQL, code, deployment, or external system.
For teams · the Governed Context Edge · private pilot
ClariLayer starts with personal context. The Governed Context Edge — the shared, governed team canon your personal layers connect into — is built and in a private pilot with a few design-partner teams.
Teams choose what to propose into a governed, shared canon. Personal context does not silently become team context. Early access requests are open; the pilot has no public price.
As a team adopts ClariLayer, the personal context analysts build can be proposed up to shared, owned, governed context — tier-based approvals, immutable release bundles, and audit trails for high-stakes metrics.
Explore team governance, ownership, and release evidenceYour reconciled definition can be proposed up to the team's shared layer, and the team's canon can flow back down to you — always with agency: adopt it, override it, or fork it, never a silent overwrite.
Explore how personal context becomes team canonWhat flows across an edge carries its owner, version, and validation evidence, so whoever adopts it — a teammate, or their AI data agent reading the governed contract — knows whether to trust it.
Explore the evidence a definition carriesAs teams adopt it, agents, dashboards, and internal apps can fetch the governed definition, owner, version, and trust state through a read-only contract instead of scraping stale warehouse artifacts.
Explore the read-only contract for team agents and BI toolsStart free with no credit card. Connect your AI, choose the space, and keep the first durable rule you want available later.
The personal offer starts free. No credit card required.
We use privacy-friendly analytics
With your consent we use PostHog and Vercel Analytics to understand how ClariLayer is used so we can improve it. We never sell your data. Errors are always monitored (without analytics) so we can keep the app reliable. You can change your mind anytime.