Automatically fact-check written content against your source facts

Splits any piece of text into sentences and flags any that don't match your verified facts.

How the work actually flows

A straight line. Runs once per one per sentence.

Pattern: Sequence (1) ยท Multiple Instances with a priori Run-Time Knowledge (14)

flowchart TD trig>"facts and text submitted"]:::trig s0["split text into sentences"]:::task s1[["check each sentence against facts"]]:::mi s2["filter out matching statements"]:::task s3["summarize inaccurate statements"]:::task trig --> s0 s0 -->|"one per one per sentence"| s1 s1 --> s2 s2 --> s3 out[/"report of inaccurate statements"/]:::out pay{{"confidence content is fact-checked"}}:::pay s3 --> out out --> pay classDef task fill:#e7f6fe,stroke:#34b8f0,color:#2c2a29 classDef svc fill:#f6f8fa,stroke:#7c8795,color:#2c2a29 classDef mi fill:#e7f6fe,stroke:#0079a8,color:#2c2a29,stroke-width:2px classDef human fill:#fff,stroke:#0079a8,color:#0079a8 classDef store fill:#f6f8fa,stroke:#0079a8,color:#2c2a29 classDef trig fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigtime fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigdata fill:#8ad4f5,stroke:#0079a8,color:#06314c,font-weight:bold classDef gate fill:#fff,stroke:#e8a23d,color:#6b4708,font-weight:bold classDef out fill:#1f9d6b,stroke:#167a53,color:#fff,font-weight:bold classDef pay fill:#06314c,stroke:#021f33,color:#fff
Starts itA stepRuns once per itemResultPayoff
Build size
Advanced

A larger build with multiple systems, AI reasoning, and custom rules.

Business functions
General Automation
Connects
Ollama

The problem it solves

When you publish AI-generated or draft content, you can't always be sure every claim in it is actually true. Manually checking each sentence against your source material takes time you don't have, especially under deadline.

Who it fits

Editorial teams, marketers, or anyone reviewing AI-generated content for accuracy.

How it works

  1. A list of facts and a piece of text are submitted
  2. Splits the text into individual sentences
  3. Checks each sentence against your facts
  4. Filters out anything that doesn't match
  5. Summarizes the incorrect statements found
What you get

Sentences flagged for you to double-check

You get every sentence in a piece of writing checked against your verified facts, with any mismatches flagged for you to review.

What you get

A summary report listing any inaccurate or unsupported statements in the text.

What you need

A server running Ollama with a fact-checking model installed.

We can build this. But should you?

The hard question is not how to build it. It is whether this is the right thing to build first.

That is what a Fractional Chief AI Officer figures out with you, before anyone writes a line of code.

Let's Talk Strategy

Related automations

Read invoices from Gmail and log them to Google Sheets automatically

Pulls invoice attachments out of your inbox, reads the details with AI, and records them in a spreadsheet.

Advanced

A private AI chatbot that remembers your conversation

A self-hosted AI chatbot that responds to messages and remembers recent context, without sending data to outside AI providers.

Standard

Automatically research, write and illustrate news articles with AI

Finds trending topics, researches them, and writes a publish-ready article with suggested photo ideas.

Advanced

Identify what's in a photo using a private, local AI model

Sends a photo to a locally-run AI vision model so it can describe what's in the image without using outside services.

Standard
Back to the AI Playbook