← Capabilities
LLM application engineering
not yet earnedI can take a model API to a production feature — structured output that cannot be malformed, tool interfaces a model can actually use, a context budget I chose on purpose, and a hallucination guard that fails closed.
What this claim costs
- 5 assessed items at tier 2 or above0 of 5 — 5 more to do, from 20 available
- A public artifact built for this claim — 1 Percent More Fluent
- 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 write1 available, none done
- Recalled cold, a week later, without notes4 scheduled, none done
The proof
A shipped product whose structured-output path and streaming decisions are documented and defensible.
What it has to contain
- A shipped feature whose structured-output path cannot emit malformed data
- The context budget stated in tokens, with the choice justified
- A hallucination guard that fails closed, with the failing case shown
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
- Prompting as engineering
- Structured output and schema enforcement
- Tool use and function calling
- Context management
- Failure modes and hallucination
20 assessed items across the specified courses evidence these, 0 done.