Skip to main content
Use post-analysis when a run has completed or partially completed and you need analyzer output without rerunning the agent.

​
Command

agentcompass analysis \
  --input results/swebench_verified/your-model/20260703_120000 \
  --analysis-params '{
    "analyzers": ["ExceptionAnalyzer", "TruncationAnalyzer"]
  }'
By default, analysis copies the input run into a new timestamped sibling. Use --override only when you intentionally want to mutate the original run directory.

​
Qualitative Analysis

agentcompass analysis \
  --input results/terminal_bench_2/your-model/20260703_120000 \
  --analysis-params '{
    "analyzers": ["QualitativeAnalyzer"],
    "QualitativeAnalyzer": {"render_mode": "file"}
  }' \
  --task_concurrency 8

​
Outputs

ArtifactPurpose
analysis_result.<AnalyzerId>Per-task analyzer payload in detail files.
analysis_summary.jsonMachine-readable aggregate analyzer output.
analysis_summary.mdHuman-readable analyzer summary.