← Capabilities
AI architecture and build-versus-buy
not yet earnedI can decide whether a problem needs an LLM at all, price the alternative, and show a case where the cheaper approach won.
What this claim costs
- 3 assessed items at tier 2 or above0 of 3 — 3 more to do, from 29 available
- A public artifact built for this claim — llm-or-notNot built yet
- A documented negative result — where this stops workingNothing recorded. A capability with no known failure boundary has not been explored.
- Defended aloud, against questions you did not write2 available, none done
- Recalled cold, a week later, without notes5 scheduled, none done
The proof
llm-or-not
A classification problem currently served by an LLM, reimplemented with a baseline that is measured against it on cost, latency and accuracy.
What it has to contain
- A problem currently served by an LLM, reimplemented with a cheaper baseline
- Cost, latency and accuracy compared at a stated volume
- A case where the cheaper approach won, stated plainly
Where it stops working. Not established yet. Anyone can ship a demo; the boundary is the part that is worth reading, so this claim is not earned until it is written down.
Skills underneath
- Choosing an AI approach
- Human-in-the-loop design
- AI economics and build-versus-buy
29 assessed items across the specified courses evidence these, 0 done.