ENGINEERING
Loom Bug Dedupe Against Existing GitHub Issues
Before filing, it transcribes a Loom bug video, searches existing GitHub issues for a likely duplicate, and either comments the new video on the match or opens a fresh issue.
How it runs
The automated pipeline, trigger to output.
- TriggerNew Loom bug video sharedLoom
- ActionFetch transcript and metadataLoom
- ActionSummarize symptom + repro via LLMOpenAI
- ActionSearch open GitHub issues for matchesGitHub
- LogicDecide duplicate vs new issue
- OutputComment on match or open new issueGitHub
What it does
Stops duplicate bug reports before they clutter the tracker. When a Loom bug video arrives, it extracts the symptom and repro, semantically searches open GitHub issues for a match, and decides: if it's a likely duplicate it comments the new Loom and any extra detail onto the existing issue; if not, it opens a new structured issue.
When to use it
Use it on high-traffic bug intakes where the same defect gets reported many times. It keeps signal consolidated on one canonical issue and saves engineers from triaging the same bug repeatedly.
How it works
- 1A new Loom bug video triggers the flow.
- 2Loom returns the transcript and metadata.
- 3An OpenAI step produces a normalized symptom summary and repro steps.
- 4A GitHub action searches open issues using the summary as the query.
- 5An OpenAI step compares candidates and decides duplicate or new.
- 6A logic branch routes the decision.
- 7A GitHub action either comments on the matched issue or creates a new one.
Set it up
What you configure once, before turning it on.
- 1Connect LoomVideo transcripts, libraries.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect GitHubRepos, issues, pull requests, actions.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Engineering workflows
Gate breaking API PRs behind downstream consumer acknowledgement
When a PR introduces a breaking contract change, comments the impact summary back on the PR, applies a blocking label.
Publish a versioned API changelog to Confluence on each release tag
On a new semver release tag, gathers the contract changes since the last release and writes a clean.
Agent reviews model-license fit and suggests compliant swaps on the PR
When a PR adds a Hugging Face model, an agent reads the model card and license, judges fit against your commercial-use policy.
Upgrade Impact Router to Module Code Owners
Maps a dependency-bump PR's affected modules to their CODEOWNERS, then DMs each owner on Slack with only the changelog slice that touches code they own.
Re-Voice IVR Prompts on Phone-Tree Config Merge
When a phone-tree config change merges in GitHub, regenerates the ElevenLabs audio for any prompt whose script changed in the diff and opens a follow-up PR adding the new audio…
Upstream Release to Notion Upgrade Brief
When a watched package publishes a new release, fetches the release notes, maps them to the internal modules that depend on it.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.