AI & RAG
Slack 'have we seen this before?' incident lookup command
Lets any engineer paste an error or symptom into Slack and get back, in-thread, the most similar past incidents from the postmortem corpus with their causes, fixes, and links.
How it runs
The automated pipeline, trigger to output.
- TriggerEngineer asks the bot in SlackSlack
- ActionEmbed question and vector-search postmortem corpusPostgres
- LogicHandle no-strong-match case honestly
- ActionSummarize matches grounded on retrieved postmortemsOpenAI
- OutputReply in Slack thread with ranked similar incidentsSlack
What it does
This gives on-call engineers a self-serve way to ask the corpus directly. An engineer mentions the bot or runs a slash command in Slack with a pasted error, log line, or plain-English symptom. The workflow embeds the query, retrieves the closest postmortems from Postgres, and replies in-thread with a ranked list of similar incidents — each summarized with its root cause, the resolution, and a link — all grounded strictly on retrieved writeups.
When to use it
When engineers want an interactive 'have we seen this before?' during an active incident or while triaging, without leaving Slack to dig through a wiki. Complements the automatic Sentry and PagerDuty finders.
How it works
- 1An engineer triggers the bot in Slack with an error or symptom.
- 2The query is embedded and vector-searched against the postmortem corpus in Postgres.
- 3A gate handles the no-strong-match case with an honest 'nothing similar found' reply.
- 4An LLM summarizes the matches grounded only on retrieved postmortems, with citations.
- 5The ranked answer is posted back as a Slack thread reply.
Set it up
What you configure once, before turning it on.
- 1Connect SlackChannels, DMs, threads, mentions.
- 2Connect PostgresAny Postgres URL — query, write, migrate.
- 3Connect OpenAIModels, embeddings, files.
- 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 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.