Skip to main content
AgentCompass writes each run under the configured results_dir, defaulting to results. 
results/
└── <benchmark>/
    └── <model>/
        └── <timestamp>/
            ├── details/
            ├── logs/
            ├── params.json
            ├── progress.json
            ├── progress.jsonl
            ├── summary.md
            ├── analysis_summary.json
            └── analysis_summary.md

​
Details

details/ contains per-task JSON files. Completed samples use the task id as the filename. Retryable failures may be written as _error_<task_id>.json so reuse mode can retry them later. If analysis is enabled, each attempt can include: 
analysis_result.<AnalyzerId>

​
Summary

summary.md contains aggregate benchmark metrics, run metadata, and high-level status. Regenerate it without running analyzers: 
agentcompass summary \
  results/<benchmark>/<model>/<run>
Use --dry-run to print the regenerated markdown without writing files.

​
Analysis Summary

analysis_summary.json and analysis_summary.md aggregate analyzer output across tasks. Recompute them with: 
agentcompass analysis \
  --input results/<benchmark>/<model>/<run> \
  --analysis-params '{"analyzers":["ExceptionAnalyzer"]}'

​
Resume and Reuse

When reuse is enabled, AgentCompass skips completed details with matching effective parameters. Execution-only knobs such as task concurrency do not need to force a new result directory.

​
Progress

progress.json records the latest structured state. progress.jsonl records the event stream and is the best source for external monitors.

​
Local Result Browser

For a local web view of summary.md, progress, and per-task details, start the result browser from the repository checkout: 
cd tools/result-browser
npm install
npm run dev
Open the Vite URL printed by the dev server and enter the absolute run directory path, such as /path/to/AgentCompass/results/<benchmark>/<model>/<run>. The path is resolved on the machine running npm run dev, including when the UI is reached through port forwarding.