Case Studies

The Kentucky General Assembly's 2026 session ran from January 6 through April 15 — a 10-week sprint of committee hearings, floor votes, and policy debates across dozens of standing committees. On a typical session day, the General Assembly runs six to ten committee meetings simultaneously. Our newsroom could staff two of them.

The result is predictable: stories get missed. Legislative action on education funding, healthcare access, and public safety advances with little to no coverage, because the newsroom was late or never knew it happened.

A fully automated pipeline built in MindStudio monitored the Kentucky Legislature's YouTube RSS feed continuously throughout the session. When a new committee meeting recording is posted, the system ingests it without human intervention — extracting audio, transcribing it via AssemblyAI, and analyzing the transcript with a large language model prompted to think like a beat reporter.

The output is a structured editorial report delivered by email to the Executive Producer. Story ideas are reviewed, filtered for newsworthiness and broadcast relevance, and forwarded to reporters for assignment — preserving human editorial judgment at every step.

Spectrum News Louisville has access to a statewide network of more than 200 Kentucky DOT traffic cameras — but was accessing them through VLC Media Player using XSPF playlist files. The workflow created three significant operational problems in live production.

• No visual preview. Cameras were listed as raw UUID stream URLs. Producers had no way to see what any camera showed before selecting one for air. As one producer described it: "playing Russian roulette."
• Slow load times. Opening a camera in VLC took 10–15 seconds — operationally significant during breaking news when real-time decisions matter.
• No multi-camera workflow. VLC allowed producers to view only one camera at a time. Each camera required a full stop-and-restart cycle.

DOT CAM was built by an Executive Producer with no formal software engineering background, during normal working hours, in between editorial responsibilities. The limiting factor was not technical knowledge — it was the ability to define problems precisely, evaluate outputs critically, and iterate with editorial judgment.

The build took 4.5 hours. The tool is live. It costs $18 a month. That ratio — problem identified to solution shipped — is what changes when domain experts engage seriously with AI as a development partner rather than a search engine.