AI & RAG
Agentic incident investigator over the runbook wiki
When a PagerDuty incident fires, an agent reads the alert, retrieves and reasons across multiple runbook pages, correlates recent GitHub changes.
How it runs
The automated pipeline, trigger to output.
- TriggerPagerDuty incident triggers the investigatorPagerDuty
- ActionIteratively retrieve relevant runbook pages from pgvectorPostgres
- ActionPull recent deploys and merges from GitHubGitHub
- LogicReason over evidence and assemble cited plan with OpenAIOpenAI
- OutputPost grounded first-response plan to incident channelSlack
What it does
Spins up an autonomous first responder. Given a fresh incident, the agent searches the versioned runbook wiki, follows cross-references between pages, pulls in recent related code changes, and synthesizes a step-by-step mitigation plan grounded in cited sources rather than a single nearest-neighbor lookup.
When to use it
Use it for high-severity incidents where the right runbook is spread across several pages and the responder benefits from an agent that can chain retrieval, weigh freshness, and connect the alert to a likely recent deploy.
How it works
- 1A PagerDuty incident-triggered webhook delivers the alert payload.
- 2The agent issues iterative retrievals against the runbook vector store in Postgres, expanding from the alert symptoms.
- 3It queries GitHub for deploys and merges in the affected service over the last 24 hours.
- 4The agent reasons over the gathered evidence with OpenAI, citing each runbook page and commit it relied on.
- 5It posts a grounded first-response plan, with confidence and sources, to the incident's Slack channel.
Set it up
What you configure once, before turning it on.
- 1Connect PagerDutyIncidents, on-call, escalations.
- 2Connect PostgresAny Postgres URL — query, write, migrate.
- 3Connect GitHubRepos, issues, pull requests, actions.
- 4Connect OpenAIModels, embeddings, files.
- 5Connect SlackChannels, DMs, threads, mentions.
- 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 this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.