The library

Prompt → Agent → Eval. All three products, fully integrated. Save $38 vs. buying separately.

• All 3 products — Prompt Foundry + Agent Blueprints + Eval Kit
• Save $38 vs. buying individually
• Built to integrate — evals auto-discover prompts & agents

Ship with data, not vibes. A TS framework, 60 production test cases, CI workflow, and a 47-item pre-launch QA checklist.

• Real TypeScript framework — clone-and-run, ~500 LOC
• 60 production-tested seed cases across 10 categories
• GitHub Actions: block PRs on >5pp regression

12 production agents. Drop them in. Ship by Friday. Three SDK formats. Tool schemas, ADRs, evals included.

• 6 production agent blueprints, named & opinionated
• Drop-in TypeScript & Python — no pseudocode
• Each agent: tool schemas, few-shots, evals, ADR

Stop writing prompts. Engineer them. 32 XML-tagged templates, eval files, a TS loader, and a 28-page methodology PDF.

• 32 XML-tagged production prompts across 8 categories
• Each prompt ships with 5–7 golden eval cases (.jsonl)
• Zero-dependency TypeScript loader with hot reload