Writing
Verified, Not Trusted: Expense Analysis, Part Three
Evals are acceptance tests for prompts and skills: repeated isolated runs, a pass rate for each check, and a minimum pass rate as the gate. Code grades extracted facts and traces failures.
Topic
Prompting
Writing instructions that define a language model's task, constraints, evidence requirements, and expected output. Prompt comparisons examine which decisions are specified and which remain open.
3 pages
Writing
Verified, Not Trusted: Expense Analysis, Part One
Expense totals need verifiable source coverage and reproducible calculations. Two prompts show how parsing, category rules, refunds, and code shape the evidence.
Writing
Skills versus Controlled Workflows
Stakes and human verification determine where workflow control belongs. Explicit prompts guide a model; imperative code enforces steps, checks, and use of results.