AgentClash

Feature

Agent scorecards that justify a release decision

Scorecards turn long agent runs into a reviewable verdict. AgentClash aggregates correctness, cost, latency, tool strategy, and validator evidence so baselines and candidates are easy to compare.

live race
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 scorecards include

Built for reviewable agent decisions

A scorecard should be more than a single number — it should explain why a run passed or failed.

Sandboxed real-tool execution

Head-to-head runs with fair constraints

Scorecards for correctness, cost, latency, and tool strategy

Replay trails for every important action

Challenge packs that turn failures into reusable tests

CI gates for baseline versus candidate decisions

Workflow

From run to scorecard

Package the task

Describe the workload as a challenge pack with inputs, tools, scoring rules, and artifacts.

Race the agents

Run every candidate against the same task with the same constraints.

Replay the evidence

Inspect tool calls, outputs, artifacts, latency, cost, and judge evidence after the run.

Gate the release

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

FAQ

Agent scorecard FAQ

What appears on an AgentClash scorecard?

Correctness signals, validator evidence, cost, latency, tool usage summaries, and dimension scores your challenge pack defines.

Can scorecards compare two runs?

Yes. Baseline versus candidate comparisons are first-class for regression testing and CI gates.

Can scorecards be exported or shared?

Yes. Runs keep scorecard views in the product and support shareable evidence for reviewers.