Self-improving loops, grounded in real traces.

Start with one trace GitHub
Self-hostable MIT license
/

Dashboard preview

Traces
1,248
+12.8% this week
Open Findings
12
-4 this week
Knowledge
86
+9 this week
Dataset Examples
324
+28 this week
Evidence volume
Improvement outputs
tr_8f9a2b captured
Request
Model
Tool
Response
Spans 12
Latency 1.42s
Cost $0.031

How it works

From trace to the next version.

Repair the agent or improve the model.

Findings

Find failures worth fixing.

Recurring failures, grouped with their evidence.

Explore Findings

Silent payment failure reported as success

Request Charge $49.00 and confirm subscription
stripe.charges HTTP 502 · gateway timeout after 5s
Response Subscription activated — $49.00 charged.

Knowledge

Keep what the agent learns.

Verified knowledge, linked to its source.

Explore Knowledge

Refunds over $500 require manager approval.

Sources

Conversation conv_92a1

“Enterprise refunds over $500 need manager approval.”

Account lookup sp_73a1

“Plan: enterprise · Refund amount: $740”

Datasets

Build audit-ready data.

Review trace-backed examples.

Explore Datasets

corrections-v3

128 examples

TaskStatus
Rejected refund Reviewed
Failed tool result Pending
Approval policy Pending

Get started

Start with one trace.

Connect once. Your first trace flows in automatically.

What happens next

Agent Trace received tr_8f9a2b Open Workbench

Run any agent task — traces are captured automatically.