Automation & AI · European energy supplier

An AI research system that found a product opportunity nobody had suggested

per opportunity researched and vetted
~$7
sources behind the first real proposition it produced, each linked and dated
5
automated tests guarding every release
340

The situation

An energy supplier's AI incubator wanted a system that could find and assess new product opportunities on its own: market research proposing candidates, customer research sizing them, compliance research checking them, and a final step merging the three verdicts into a one-page brief. I led delivery, from written requirements to runs on production infrastructure. (The client is unnamed here: the engagement terms restrict it.)

The problem

  • AI research systems are easy to demo and hard to trust: left alone, they invent numbers, cite pages they never opened, and smooth over disagreement.
  • Mid-build, the system reported finding nothing for weeks, with each run costing $26 and taking 15 minutes.

What I did

  • Wrote the requirements first: 89 prioritised requirements, each mapped one-to-one into the delivery backlog before the build began.
  • Enforced the rules in code rather than asking nicely in prompts: no number the data didn't produce, every claim linked and dated, and a citation must name a page the run actually opened.
  • Kept judgement human where it matters: a severe compliance finding interrupts a person, and disagreement between the research streams stays visible instead of being averaged away.
  • Diagnosed the two bugs hiding each other: a source list the search code silently read as empty, and a loop where the system re-read its own conversation nine times per request. Fixing them took a run from $26 and 15 minutes to $0.87 and two.
  • The first run after the fix produced a real, dated, five-source product proposition nobody had suggested, with a compliance finding attached that would otherwise have been discovered expensively later.
  • Gated every release with 340 automated tests, and ran the system on a schedule on company infrastructure, with every step traceable.
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?

A few lines is enough. Every enquiry comes straight to me, and you’ll get a considered reply: a straight answer, a question or two, or an honest “I’m not the right fit”.

Prefer email? hello@firstniyyah.com