Is it really one trail across everything?

Yes. Every agent action against every connected tool lands in the same record — one schema for all users and agents, no per-app log stitching.

Can we export to our own tooling?

Yes — events live in warehouse-grade storage and export cleanly for your SIEM, warehouse, or audit workflow.

Does the agent write its own log?

No. Logging happens at the policy layer where each call is checked — outside the agent’s reach entirely.

How do we investigate an incident?

Filter the trail by service, event type, or time window in the dashboard — every event carries both identities and the verdict, so the sequence reconstructs in minutes.

Are refused calls in the trail too?

Verdicts are part of the record — events show whether a call was allowed, held for approval, or refused, right next to who asked and which agent acted.

Use case · Audit Trail

One audit trail. Every agent, every user, every tool.

All agent activity across all your applications lands in one centralized record — both identities, the action, and the verdict.

Get a demo

The problem

When an agent misbehaves — or an auditor asks — you need a record you can trust. The agent shouldn’t write its own.

Agents keeping their own logs is self-review

App logs are incomplete and mutable

No verdicts — did the call even go through?

“Who did this?” shouldn’t answer “the agent”

How a call becomes a record

Request

A user asks an agent

Every call starts with a real person and a registered agent — two identities, not one.

Check

Policy decides

Allowed, held for approval, or denied — per user, per action, before anything runs.

Act

The tool call runs

Through Fabriq, with credentials injected server-side — the agent never holds a key.

Record

The trail gets the event

Who asked, which agent, what it touched, and the verdict — one schema, one place.

See it

14:02:11maya@ · ap-bot-01create_billallowed

14:02:38raj@ · support-botissue_refund $84allowed

14:03:05raj@ · support-botissue_refund $612needs_approval

14:03:41dana@ · qa-bot-03export_docsdenied

14:04:19maya@ · ap-bot-01notify_channellogged

EVERY CALL IS AN EVENT — WHO ASKED, WHICH AGENT, WHAT, AND THE VERDICT

Capabilities

What you get

One trail across everything.

Every agent, every user, every connected tool — a single centralized record, one schema.

Both identities on every event.

The person who asked and the agent that acted — with tool, action, and timestamp.

The verdict is part of the record.

Allowed, held for approval, or refused — outcomes land in the trail.

Query and filter in the dashboard.

Slice by service, event type, and time window.

Warehouse-grade storage, exportable.

Events land in BigQuery-backed storage and export to your own tooling.

Usage metering alongside.

Calls per user and per tool, over time — right beside the audit trail.

The payoff

When someone asks what an agent did, the answer is a query — not an investigation.

Get a demo

Questions

One audit trail. Every agent, every user, every tool.

When an agent misbehaves — or an auditor asks — you need a record you can trust. The agent shouldn’t write its own.

What you get

Common questions