AI & RAG
Flag config values changed without an ADR and draft the missing rationale
On a schedule, this workflow finds config values that were changed in Git but have no linked ADR, drafts a rationale from the commit context.
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled gap scan fires
- ActionBlame recent config changes and pull commits from GitLabGitLab
- LogicKeep only changes with no linked or matching ADR
- ActionDraft rationale from commit contextOpenAI
- ActionCreate a draft ADR stub in ConfluenceConfluence
- OutputAlert the owning team in Slack to finalizeSlack
What it does
Hunts for accountability gaps: config values whose introducing commit cites no architecture decision record. For each gap, it drafts a candidate rationale from the commit message and diff context, creates a draft ADR stub in Confluence, and pings the owning team in Slack to confirm or correct it.
When to use it
When your ADR discipline has slipped and load-bearing settings exist with no recorded reasoning. Use it to backfill documentation debt steadily rather than in a painful one-time audit.
How it works
- 1A scheduled trigger runs the gap scan.
- 2The workflow blames recent config changes in GitLab and pulls each introducing commit.
- 3A logic step keeps only commits with no ADR reference and no matching ADR in Confluence.
- 4The agent drafts a rationale from the commit message, diff, and author.
- 5It creates a clearly-marked draft ADR stub in Confluence.
- 6It posts a Slack alert tagging the owner to review and finalize the stub.
Set it up
What you configure once, before turning it on.
- 1Connect GitLabRepos, MRs, pipelines, registry.
- 2Connect ConfluenceSpaces, pages, blueprints.
- 3Connect SlackChannels, DMs, threads, mentions.
- 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.