Replay Validation
Prove it on the failure that triggered it.
When replay is available, the candidate rule is tested against recent failures and protected wins, then promoted only when outcomes improve without regression.
Why Harness[—/—]
Finding failures is not the same as fixing them.
Tracing and evaluation identify failures. The Harness turns that evidence into scoped, validated rules agents can use to recover from them.
Evidence becomes action
The Harness turns trace evidence and evaluation failures into structured repair work, connecting detection to improvement.
Learning survives the run
Learned rules live in a persistent workspace, scoped by task, workflow, or domain instead of disappearing with one session.
Fixes prove themselves
Every candidate is tested through developer-controlled task replay. Only rules that improve evaluated outcomes become trusted.
Next runs improve
Validated rules stay available to relevant agents so known failures can be avoided instead of diagnosed and repaired again.
Repair stays governed
Scoped rules, restricted tools, validation gates, and human policy keep self-repair bounded and auditable.
Learning compounds across the fleet
Reuse scoped rules across the fleet to reduce manual repair on low-cost models and achieve higher success rates.
How It Works[—/—]
From failure to trusted rule
The Repair Harness evaluates traces, posts failure notices, writes scoped rules for the next turn, and validates what becomes trusted.
Trace evaluation
Each new trace is scored for task completion and coherence, while the trajectory is watched for stalls or regressions. Suspected failures trigger deeper tool and argument checks, with optional planning and efficiency diagnostics.
Trace evaluation
Each new trace is scored for task completion and coherence, while the trajectory is watched for stalls or regressions. Suspected failures trigger deeper tool and argument checks, with optional planning and efficiency diagnostics.
Evidence-Gated Learning[—/—]
No rule earns trust without evidence.
Candidate rules are tested against replay or live evidence before promotion, then re-checked as the rule set evolves.
Forward-Trial Validation
Prove it live when replay is unavailable.
The candidate is trialed across matching live sessions and promoted only after its breach rate reaches zero or clears its baseline by a meaningful margin.
Regression & Calibration
Keep the gate honest as rules accumulate.
Captured failures and protected wins are replayed against the current rule set, while labeled outcomes keep breach thresholds measured rather than guessed.
Let evidence decide what your agents learn.
Start buildingIntegrations[—/—]
Drop it around what you already run.
First-class adapters for six agent frameworks, a lightweight path for custom loops, and four optional read-only tools for consulting learned rules.
Framework Adapters
Read-Only Rule Tools
Your agents can list, search, and read learned rules or check a rule's validation status. Repair and administration stay outside their tool surface.
Keep your loop. Add the Repair Harness.
View integrationsQuick Start[—/—]
Add the Harness in three steps.
Install the package, connect your project, and wrap one turn boundary—no framework migration required.
- 01
Install the Harness
Add the Python package to your agent environment.
pip install pandaprobe-harness - 02
Get your API key
Connect the Harness to the PandaProbe project receiving your traces.
- 03
Wrap your agent
Use a framework adapter or wrap one turn boundary in your existing loop.
Wire up your first repair loop.
Read the quickstartQ&A[—/—]
Frequently asked questions
Everything you need to know about building self-repairing agents with the PandaProbe Harness.
Every failure should improve the next turn.
Wire the Repair Harness into your agent loop and turn failures into validated rules the next turn can use.
Peak task-success uplift
+20%
Build your repair loop in the open.
Start building