Automation & AI · Vandebron

Fixing an AI agent that cost $26 a run and found nothing

per run, down from $26
$0.87
per run, down from 15
2 min
automated tests guarding every release
340

The situation

Vandebron's AI incubator was building a multi-agent system to suggest new product ideas: market, customer and compliance research, then a summary. I led delivery.

The problem

  • For weeks the agent reported that it had found nothing.
  • One run cost $26 and took 15 minutes, with no output.

What I did

  • Found two bugs hiding each other: a source list the search code silently read as empty, and a loop where the agent re-read its own conversation nine times per request.
  • Enforced the rules in code rather than asking nicely in prompts: no number the data didn't produce, every claim linked and dated, disagreements between researchers kept visible, and legal risk routed to a person.
  • Set the scope with a clear must-have versus nice-to-have list, and gated releases with 340 automated tests.
Getting an AI to find things is easy. Getting it to tell you what it doesn't know is the real job.

Contact

Got a problem like this?

Thirty minutes to talk through what you’re trying to fix. If I’m not the right fit, I’ll say so, and point you to someone who is.