AI AGENTS
Fact-check marketing copy against primary sources before publish
An agent extracts every factual claim from a draft, finds primary sources for each, and blocks publish until each claim is backed by a citation or flagged for human review.
How it runs
The automated pipeline, trigger to output.
- TriggerNotion page status set to Ready for reviewNotion
- ActionExtract discrete factual claims from draftOpenAI
- ActionFind and read primary sources per claimExa
- ActionScore each claim Supported / Unverified / ContradictedOpenAI
- LogicAny claim contradicted or unverified?
- OutputWrite report and set publish-ready or flag for editorNotion
What it does
When a marketing draft is moved to a "Ready for review" status in Notion, an agent pulls the body, decomposes it into discrete factual claims (stats, comparisons, dates, superlatives), and verifies each one against primary sources it finds on the open web. It writes a verdict per claim — Supported, Unverified, or Contradicted — with a source URL and a one-line rationale, then appends a fact-check report to the page and sets a publish-ready flag only if nothing is contradicted.
When to use it
For content and brand teams who need a defensible paper trail before claims go live, especially in regulated or claims-heavy categories where an unsourced "3x faster" can become a legal problem.
How it works
- 1A Notion page status change to "Ready for review" triggers the run.
- 2The agent reads the page body and extracts an itemized list of factual claims.
- 3For each claim it searches Exa for primary sources and reads the top results.
- 4It writes a per-claim verdict with citation and rationale via OpenAI.
- 5A branch checks whether any claim is Contradicted or Unverified.
- 6The report is written back to the Notion page; publish-ready is set only when clean, otherwise the page is flagged for an editor.
Set it up
What you configure once, before turning it on.
- 1Connect NotionPages, databases, comments.
- 2Connect ExaNeural search across the web.
- 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 Agents workflows
Custom Metrics Cardinality Spike Pager
A webhook from a Datadog monitor fires when custom-metric cardinality jumps; an agent pinpoints the offending metric and tag, estimates the added cost.
Sentry-to-Confluence Runbook Updater
When a Sentry issue is resolved, the agent finds the matching Confluence runbook page and proposes an inline update with the verified fix.
Stale Doc-PR Chaser for Runbook Gaps
On a daily schedule the agent finds runbook doc PRs that were opened from resolved incidents but never reviewed, summarizes what each one fixes.
Resolved Incident to Public Troubleshooting Doc
For customer-facing errors resolved in Sentry, the agent drafts a sanitized troubleshooting entry and opens a PR to your ReadMe documentation.
On-Call Runbook Gap Closer: Resolved Sentry Issues to Doc PRs
An agent reads each newly resolved Sentry issue, compares the actual fix against your existing runbook, and opens a GitHub PR adding the missing remediation steps.
Weekly On-Call Doc-Gap Digest
Each week the agent reviews every Sentry issue resolved in the last 7 days, ranks the ones whose runbook coverage is missing or thin.
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.