AI & RAG
Spike Triage Router with Runbook Answer or PagerDuty Escalation
On a Datadog alert, retrieves matching runbook guidance and decides whether the on-call can self-resolve in Slack or whether the spike warrants an immediate PagerDuty page…
How it runs
The automated pipeline, trigger to output.
- TriggerDatadog monitor crosses thresholdDatadog
- ActionFetch metric, severity tags, and breach durationDatadog
- ActionRetrieve best-matching runbook passagesPostgres
- LogicScore severity and coverage to choose route
- ActionOpen PagerDuty incident with cited context (severe path)PagerDuty
- OutputPost self-resolve answer to Slack (known-issue path)Slack
What it does
Adds a decision layer on top of runbook retrieval. When a monitor fires, it grades the spike's severity and how well the knowledge base covers it, then routes accordingly — a calm, cited fix suggestion in Slack for known issues, or a PagerDuty incident enriched with the runbook context for severe or unrecognized spikes.
When to use it
Use it when not every alert deserves a page, but the ones that do need full context immediately. Ideal for teams drowning in low-signal alerts who still want hard spikes escalated with the relevant runbook already attached.
How it works
- 1A Datadog monitor crosses threshold and triggers the flow.
- 2The flow fetches the metric, its severity tags, and recent breach duration from Datadog.
- 3It retrieves the best-matching runbook passages from the Postgres vector store.
- 4A logic step scores severity and retrieval confidence to choose a route.
- 5Known, low-severity spikes get a cited self-resolve message posted to Slack.
- 6Severe or low-coverage spikes open a PagerDuty incident with the runbook context and Slack link embedded.
Set it up
What you configure once, before turning it on.
- 1Connect DatadogMetrics, traces, log search.
- 2Connect PostgresAny Postgres URL — query, write, migrate.
- 3Connect OpenAIModels, embeddings, files.
- 4Connect PagerDutyIncidents, on-call, escalations.
- 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 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.