AgentClash

Agent evals

Agent evals that catch production regressions

Agent evals should answer whether a change made your agent worse. AgentClash imports traces or curated examples, compares candidates to baselines, and turns failures into release gates.

live eval
gate: pass

Candidate

92correct patch, low cost

Baseline

88stable reference run

Control

73missed edge case

replay timeline

1loaded task inputs and tool policy
2ran sandbox actions and captured artifacts
3scored trajectory and validator evidence
4attached scorecard and release verdict

ci verdict

Candidate clears release gate

Correctness improved, latency within budget, and required artifacts were preserved for review.

agentclash run create --follow

What useful agent evals capture

Built for reviewable agent decisions

If your agent eval only checks the final string, you miss the tool misuse, RAG drift, latency spikes, and artifact gaps that show up in production.

OpenTelemetry-compatible trace import

Pinned datasets and golden test cases

Baseline versus candidate regression checks

Replay trails for tool calls, outputs, and artifacts

Scorecards for correctness, cost, latency, and evidence

CI gates for prompt, model, RAG, and tool changes

Workflow

From one eval to a reusable gate

Import the evidence

Start from OpenTelemetry traces, curated datasets, support transcripts, or a real failure your team already saw.

Pin the baseline

Record the current accepted behavior so every prompt, model, RAG, or tool change has a fair comparison point.

Replay the evidence

Inspect tool calls, outputs, artifacts, latency, cost, and judge evidence when a candidate gets worse.

Gate the release

Compare candidate and baseline runs, then fail CI before a regression reaches users.

FAQ

Agent eval FAQ

What is an agent eval?

An agent eval is a repeatable test that runs an agent on a task, scores the full trajectory, and compares the result to a baseline, dataset, or competitor.

How is AgentClash different from prompt evals?

Prompt evals score one model response. AgentClash evals multi-turn agents that use tools in a sandbox and scores correctness, cost, latency, and evidence quality across the run.

Can agent evals run in CI?

Yes. AgentClash can compare candidate and baseline scorecards, including dataset baselines, and fail a pull request when the configured release gate regresses.