AI & RAG
Nightly: build a searchable config-rationale index from Git history and ADRs
On a schedule, this workflow walks every config key, links it to the commit that set it and the ADR that justified it.
How it runs
The automated pipeline, trigger to output.
- TriggerNightly schedule fires
- ActionEnumerate config files and blame keys to commits in GitLabGitLab
- ActionFetch and match ADRs from ConfluenceConfluence
- ActionSummarize and embed each key's rationaleOpenAI
- OutputUpsert rationale index into PostgresPostgres
What it does
Builds and refreshes a backing index that maps each config key to its current value, the commit SHA that introduced that value, the commit author and message, and any linked ADR. Storing this in Postgres means downstream "why" lookups are instant instead of re-walking Git every time.
When to use it
When ad-hoc rationale lookups are too slow or you want one canonical, auditable table of why every setting is what it is. Run it nightly so the index stays current as config and ADRs evolve.
How it works
- 1A scheduled trigger fires nightly.
- 2The workflow enumerates config files in GitLab and runs blame to attribute each key to its introducing commit.
- 3It fetches the ADR space from Confluence and matches ADRs to keys by reference and semantic similarity.
- 4An embedding/summarization step distills each key's rationale.
- 5It upserts key, value, SHA, author, ADR ID, and rationale into Postgres.
- 6It writes a run summary noting keys with no discoverable rationale (gaps to document).
Set it up
What you configure once, before turning it on.
- 1Connect GitLabRepos, MRs, pipelines, registry.
- 2Connect ConfluenceSpaces, pages, blueprints.
- 3Connect PostgresAny Postgres URL — query, write, migrate.
- 4Connect OpenAIModels, embeddings, files.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More AI & RAG workflows
Publish a Grounded API FAQ Page to Confluence Weekly
Each week, clusters the top unanswered or repeated API questions, generates spec-grounded answers with citations.
Detect Breaking API Changes from Spec Diffs and Alert Owners
Compares the new OpenAPI spec against the previous version on each GitLab merge, uses retrieval over the changelog to classify whether changes are breaking.
Pre-meeting prep brief grounded in Coda and CRM
Before each booked sales meeting, builds a one-page prep brief by combining the account's HubSpot context with grounded talking points and objection responses pulled from your…
Coda-grounded sales answer bot with citations in Slack
Reps ask product, pricing, or competitive questions in Slack and get an answer drawn only from your Coda knowledge hub, with links to the exact docs and rows it pulled from.
Weekly knowledge-gap digest from unanswered rep questions
Each week, scans rep questions the answer bot couldn't ground in Coda, clusters the recurring gaps.
RFP and security questionnaire drafter grounded in Coda
Drafts answers to inbound RFP and security questionnaire questions by retrieving approved language from your Coda hub, then files the cited draft for review before a rep sends 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.