Logs

See every tool call
your agents make.
‍And who they made it for.

Which agent, which user, which tool, what came back. On every call, searchable, and streamable to your SIEM.

Every connector's health,
‍on one screen.

Success rate, errors and volume for every connector, or just one. See the week's shape before you hunt for a single call.
See which connector is failing
An overall 96% success rate can hide one connector failing half its calls. Filter by connector to find it.
Nothing to set up
Logging starts with your first tool call. There's no SDK to add or setting to turn on.
Spot agents stuck in a loop
A sudden jump in call volume usually means an agent is repeating itself, not doing more work.

Did your agent fail,
‍or did the connector?

Every failure is marked as a connector error or an API error, so you know whether to fix your setup or wait on the app.
Connector error means wait, or back off
The upstream is throttling, down, or refusing the scope. Retrying may work; changing your code usually won't.
API error means look at your own setup
A tool schema that needs tightening, a grant that lapsed, a config pointing somewhere it shouldn't. These are yours to fix.

Every call,
down to the payload.

Each tool call is captured as a structured event — when it ran, which agent ran it, which tool it hit, whose account it touched, how long it took and what came back.
Tell your agents apart
Three agents on one connector show up as three separate rows, so you can see which one is misbehaving.
Every call tied to a real user
Filter to one customer and you can answer "what did your agent do in my account?"
Reads are logged too
A security review asks what an agent looked at, not only what it changed. Both are recorded.

Send it to your telemetry.
‍No instrumentation.

Events stream as they happen, so security watches agent activity next to everything else.

Know what your agents did. Before someone asks.

Free to start, no credit card.
Logging is on from the first tool call — there's nothing to enable.