AI & RAG
Stale documentation detector for Confluence + GitLab wikis
Weekly, samples answer-bot queries that returned low-confidence or no results, traces them to gaps or outdated pages in Confluence and GitLab wikis.
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly schedule
- ActionPull low-confidence queries from PostgresPostgres
- ActionFind closest Confluence + GitLab wiki pagesConfluence
- LogicClassify gap: missing, outdated, or false miss
- ActionGroup and dedupe actionable gaps with OpenAIOpenAI
- OutputFile a Linear issue per documentation gapLinear
What it does
Closes the loop on your RAG system. Each week it reviews questions the answer bots couldn't confidently answer, uses OpenAI to classify whether the gap is a missing page or a contradicting/outdated one in Confluence or GitLab wikis, and files a Linear issue describing the gap with the failing queries attached.
When to use it
When you run grounded answer bots and want documentation to improve over time instead of decaying silently. Turns retrieval misses into a prioritized backlog for whoever owns the docs.
How it works
- 1A weekly schedule trigger starts the review.
- 2The flow pulls logged low-confidence and no-result queries from Postgres.
- 3For each, it retrieves the closest existing Confluence and GitLab wiki pages.
- 4A classifier decides: missing doc, outdated doc, or false miss (skip).
- 5Actionable gaps are deduped and grouped by topic.
- 6A Linear issue is created per gap with the failing queries and suggested owner.
Set it up
What you configure once, before turning it on.
- 1Connect PostgresAny Postgres URL — query, write, migrate.
- 2Connect ConfluenceSpaces, pages, blueprints.
- 3Connect GitLabRepos, MRs, pipelines, registry.
- 4Connect OpenAIModels, embeddings, files.
- 5Connect LinearIssues, projects, cycles, triage.
- 6Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 7Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 8Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More AI & RAG workflows
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.
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.
Grounded reply suggestions for inbound sales email
Reads inbound prospect emails, retrieves the matching answers from your Coda hub.
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.
On-Call Spec Answerer from Dropbox Engineering Corpus
Answers on-call questions posted in a Slack channel by retrieving the most relevant Dropbox engineering specs and replying with a grounded, source-cited answer in the thread.
Agentic Deep-Dive API Researcher for Hard Spec Questions
An agent fielded via webhook that answers multi-part API questions by iteratively searching OpenAPI specs, changelogs, and Confluence runbooks.
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.