Jeremy Neely Text Jeremy

AI & Agents · Production

Secure AI Hatz Tips

Fact-checked how-to answers inside the AI chat customers already use.

Built for: Business customers of an AI onboarding program, about 600 end users

Scrolling the approved tip sheet that the tips service generates (public help content).
Tips as customers see them: short steps, why it helps, and the source.
Tips as customers see them: short steps, why it helps, and the source.

The problem

Customers learning Hatz AI kept asking the same how-to questions, and the answers were scattered across decks, help articles, release notes and dozens of vendor videos. Hand-written tips do not scale, and AI-written tips are often wrong: about 38% of the first batch pulled from videos contained a claim the video never made.

What I built

I built a tips service that customers call as an MCP tool from inside their own Hatz chats, and get short answers that link to the exact article or video moment. Behind it is a .NET platform on a Linux server that turns vendor videos and docs into fact-checked, de-duplicated draft tips for review, plus a supervisor that watches and heals the system.

How it works

  1. Pull new vendor videos and help pages on a schedule.
  2. Have AI draft short tips with timestamped links.
  3. Fact-check every tip against its source and drop duplicates.
  4. A person approves tips in a web console.
  5. Customers ask in their Hatz chat and get cited answers.
How Secure AI Hatz Tips is wiredNothing the pipeline produces goes live until a person approves it. A supervisor watches and heals the stack.
Comes inInside Secure AI Hatz TipsGoes out Vendor videos captions, on a schedule Vendor help pages changelog, help center Customer question from inside a Hatz chat Extract tips AI, timestamped links Fact-check every tip vs its source Dedupe & tag drafts only, never live Human approval in a web console Cited answer as an MCP tool in chat Tips library MariaDB on a Linux server Source changed flag when a page changes

Built with

  • C# / .NET 10
  • ASP.NET Core
  • MariaDB
  • Claude Code CLI
  • Hatz AI
  • Ubuntu Linux
Text Jeremy about this Next: Hatz User Watch All 38 tools Texting opens your Messages app with a note already written. He replies himself.

More screens

A Hatz chat answering a how-to question from the tips library, recreated.
A Hatz chat answering a how-to question from the tips library, recreated.
Scrolling the approved tip sheet that the tips service generates (public help content), a frame from the demo clip (sample data).
Scrolling the approved tip sheet that the tips service generates (public help content), a frame from the demo clip (sample data).

More of Jeremy's work

All 38 tools, by category