a452cd95b8
- Every workflow prompt now shows a plan and asks the user to confirm before executing - /autoresearch asks for execution environment (local, branch, venv, cloud) and confirms before looping - Writer agent and key prompts now generate charts (pi-charts) and diagrams (Mermaid) when data calls for it - Cite alphaXiv and Agent Computer in README and website homepage - Clear terminal screen before launching Pi TUI - Remove Alpha Hub GitHub link in favor of alphaxiv.org Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2.1 KiB
2.1 KiB
description, args, section, topLevelCli
| description | args | section | topLevelCli |
|---|---|---|---|
| Autonomous experiment loop — try ideas, measure results, keep what works, discard what doesn't, repeat. | <idea> | Research Workflows | true |
Start an autoresearch optimization loop for: $@
This command uses pi-autoresearch.
Step 1: Gather
If autoresearch.md and autoresearch.jsonl already exist, ask the user if they want to resume or start fresh.
Otherwise, collect the following from the user before doing anything else:
- What to optimize (test speed, bundle size, training loss, build time, etc.)
- The benchmark command to run
- The metric name, unit, and direction (lower/higher is better)
- Files in scope for changes
- Maximum number of iterations (default: 20)
Step 2: Environment
Ask the user where to run:
- Local — run in the current working directory
- New git branch — create a branch so main stays clean
- Virtual environment — create an isolated venv/conda env first
- Cloud — delegate to a remote Agent Computer machine via
/delegate
Do not proceed without a clear answer.
Step 3: Confirm
Present the full plan to the user before starting:
Optimization target: [metric] ([direction])
Benchmark command: [command]
Files in scope: [files]
Environment: [chosen environment]
Max iterations: [N]
Ask the user to confirm. Do not start the loop without explicit approval.
Step 4: Run
Initialize the session: create autoresearch.md, autoresearch.sh, run the baseline, and start looping.
Each iteration: edit → commit → run_experiment → log_experiment → keep or revert → repeat. Do not stop unless interrupted or maxIterations is reached.
Key tools
init_experiment— one-time session config (name, metric, unit, direction)run_experiment— run the benchmark command, capture output and wall-clock timelog_experiment— record result, auto-commit, update dashboard
Subcommands
/autoresearch <text>— start or resume the loop/autoresearch off— stop the loop, keep data/autoresearch clear— delete all state and start fresh