
LLM Structured Outputs Handbook: Marcus's Take
Getting your fancy Large Language Model to return data in a usable format. We're talking JSON, dictionaries, predictable formats - the kind of thing you can actually pipe into your backend.


Senior AI Tool Analyst
Marcus Webb spent 8 years building backend systems before realizing he was more interested in evaluating tools than using them. Now at UsedBy.ai, he puts every AI tool through rigorous testing.
His approach is simple: show me the numbers. Marketing claims mean nothing without reproducible benchmarks. He's seen too many "revolutionary" tools turn out to be wrappers around existing APIs.
At 31, Marcus has the patience to dig deep and the experience to spot red flags. When he recommends something, it's because he's actually used it in production.

Getting your fancy Large Language Model to return data in a usable format. We're talking JSON, dictionaries, predictable formats - the kind of thing you can actually pipe into your backend.


Anthropic's thrown its hat into the all-purpose AI assistant ring with Claude Cowork. Think Claude, but for spreadsheets and emails rather than just Python scripts.
