Luma Goods
The Builder's Stack

Prompt → Agent → Eval.

The three primitives every AI builder ships. Engineered, evaluable, drop-in. One-time purchase, commercial license, lifetime updates.

01 · Prompts as code.

Prompt Foundry

$49

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

Explore
02 · Drop-in agents.

Agent Blueprints

$79

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

Explore
03 · Ship with data, not vibes.

Eval Kit

$39

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

Explore
Bundle

Get all three. Ship the whole pipeline.

Buy The Builder's Stack bundle and get Prompt Foundry, Agent Blueprints, and Eval Kit — plus a 45-minute onboarding walkthrough that wires them together end-to-end.

  • All 3 products, fully integrated
  • Stack Onboarding walkthrough (45 min)
  • Commercial license + lifetime updates
Bundle price
$129
$167save $38
Day 1

Engineer your prompts

XML-tagged templates that play with Claude Opus 4.7, GPT-5, and Gemini 2.5. Each prompt ships with golden-example eval files.

Day 2

Compose into agents

Drop-in agent definitions for the Claude Agent SDK, Vercel AI SDK, or the OpenAI Assistants API. Tool schemas, few-shots, ADRs included.

Day 3

Measure everything

Run evals locally or in CI. A 47-item pre-launch checklist tells you when the thing is actually ready to ship.

One-time purchase · Commercial license · Lifetime updates · 14-day refund