Contract · Fully remote · £70–90/h

ROLE OVERVIEW

• Huzzle is seeking management consultants to test how well frontier AI systems handle real commercial analysis, and to document where they fall short.
• You will not be producing client work. You will be finding the point at which an AI system stops being reliable at it, and proving that point objectively.
• Each submission has three parts: a realistic commercial request, documented evidence of where the model failed it, and a scoring rubric that lets any reviewer grade a future attempt consistently.
• Full training and worked examples are provided. Prior AI or data-annotation experience is not required.

KEY RESPONSIBILITIES

• Design realistic commercial tasks of the kind a client actually commissions: market sizing, competitor and pricing benchmarking, commercial due diligence, operating model review, business cases, board-ready readouts.
• Ensure each task requires live research against primary sources — filings, published pricing, regulator and industry publications, company disclosures — plus multi-step analysis and an actual file deliverable. Typically a slide deck or Excel model, but also memos, PDFs and CSVs.
• Test each task against a frontier AI model and examine its output with the scrutiny you would apply to work going to a client.
• Document exactly where and how it failed: figures asserted without a traceable source, sources cited that do not contain the claim, synthesis that flattens a genuine trade-off, frameworks applied generically without adaptation, decks that are prose rather than a real file, requirements silently dropped.
• Author scoring rubrics with sourced, objective criteria that another consultant could apply without repeating your research.
• Escalate task difficulty where the model succeeds, until a genuine gap is exposed.