AI AGENTS
Document-Grounded Claim Audit
Takes a draft document from Google Drive, extracts every factual claim, researches each one against live sources, and writes back an annotated audit marking claims as Supported.
How it runs
The automated pipeline, trigger to output.
- TriggerDraft added or updated in watched Drive folderGoogle Drive
- ActionExtract factual claims from the documentOpenAI
- ActionResearch each claim against live sourcesExa
- LogicClassify claim: Supported, Unsupported, Outdated
- ActionWrite annotated audit tableNotion
- OutputEmail author the flagged claimsGmail
What it does
Fact-checks a finished draft. The agent pulls a document from Google Drive, breaks it into discrete factual claims, researches each claim against current web sources, and produces an audit table classifying every claim as Supported, Unsupported, or Outdated, each with its best source and a confidence flag.
When to use it
Use it before publishing a report, blog post, pitch deck narrative, or board memo, when you need assurance that the assertions hold up and nothing has gone stale. It turns a nervous final read-through into a structured, sourced audit.
How it works
- 1A new or updated file in a watched Google Drive folder triggers the run.
- 2The agent reads the document text and an LLM extracts each factual claim.
- 3For every claim it searches the live web for the strongest current source.
- 4A logic step classifies each claim as Supported, Unsupported, or Outdated based on what the sources show.
- 5Results are written to a Notion audit table with source links and confidence flags.
- 6A summary of any Unsupported or Outdated claims is emailed to the author.
Set it up
What you configure once, before turning it on.
- 1Connect Google DriveDocs, sheets, slides, files.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect ExaNeural search across the web.
- 4Connect NotionPages, databases, comments.
- 5Connect GmailRead, draft, send, label.
- 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 Agents workflows
Observability Cost Allocation Report
Monthly, an agent pulls Datadog and Honeycomb usage, allocates spend to teams and services by tags, writes the breakdown to Snowflake, and posts a chargeback summary to Slack.
Vendor Shortlist Matrix from a Buying Brief
An agent reads a buying brief, researches candidate vendors across the live web, and builds a scored comparison matrix in Coda ranking each vendor against your stated criteria.
Split oversized Linear epics into estimated child issues
An agent scans newly created Linear epics, breaks each one above a size threshold into discrete child issues with point estimates and acceptance criteria.
Datadog Bill Spike Attribution Agent
When a daily Datadog cost check detects a spend jump, an agent attributes the increase to the specific services and metric types driving it and posts a ranked breakdown to Slack.
Buying Brief Email to Shortlist Doc in Drive
When a buying brief arrives by email, an agent researches the market and produces a polished narrative shortlist document in Google Drive, then replies to the sender with the link.
Zoom Demo Low-Score Objection Escalation to Manager
Scores how well a rep handled objections in each Zoom demo, and only when the handling score falls below a threshold does it create a coaching task in ClickUp and alert the rep's…
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.