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.
Candidate
Baseline
Control
replay timeline
ci verdict
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.
Interpret results
Bring your first workload into the loop
Read the interpret-results guide, then wire scorecard thresholds into CI gates and release policy.
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.