Skip to content

Roll Out Self-Improvement Tracks

Self-improvement tracks periodically seed an issue that asks Colony to inspect a repository and propose a slate of useful improvements. A person selects a candidate before development begins. Tracks use the same pipeline and Worker capacity as ordinary issues.

Choose a repository where one additional open issue will be easy to observe. Use one track, a seven-day cooldown, and a prompt focused on a single concern such as missing tests or stale documentation.

Important field semantics:

  • Name is the stable track key.
  • Label is the actual code-host label applied to seeded issues, not a display title.
  • Cooldown starts after the latest linked SI issue completes. A track can also have only one open linked issue at a time.
  • Cron schedules use UTC.
  • Weight can influence strategic ranking; it does not make the scheduler run a track more often or move its work ahead in the shared task queue.

Open SI Tracks (/dashboard/si-tracks), filter to the repository, and add a track with:

  • name test-coverage;
  • label colony:si-test-coverage;
  • cooldown 10,080 minutes;
  • enabled off.

Owners and administrators can create and edit tracks. The repository-specific view uses the same underlying track records.

A prompt version has three operational fields:

  • seed_title: the title of the SI seed issue;
  • seed_body: stable context placed in that issue;
  • instructions: how the analyzer should search the repository and construct candidates.

The seed issue exists before candidate analysis, so prompt instructions cannot prevent the scheduler from creating it. Instead, make the instructions demand evidence, bounded candidates, and honest reporting when no worthwhile candidate is found.

Use Manage Prompts on the track, add a prompt version, and confirm that it is active.

In Cloud, enable the track’s toggle. In a self-hosted deployment, return to the monitor dashboard’s Tracks table and click the track’s Off button so it changes to On.

A newly eligible track can seed on the next scheduler loop. Colony then analyzes repository signals and presents a candidate slate for human selection. Review the candidates for evidence, scope, expected value, and overlap with existing work; select one only when it is worth developing.

Do not evaluate the track from the seed title alone. The useful artifact is the analyzed candidate slate and, after selection, the completed implementation outcome.

After a full completion:

  • refine instructions if candidates were vague or repetitive;
  • keep the long cooldown until candidate quality is consistent;
  • add a second track only when it covers a genuinely different concern;
  • shorten cooldown based on repository need and Worker capacity, remembering that eligibility begins after completion;
  • disable a track before editing a risky prompt or investigating unwanted output.

Monitor open SI issues, latest completion, next eligibility, candidate selection latency, completion quality, and cost. A track that has an open issue is correctly ineligible even if its nominal interval has elapsed.