ml-llm-prd

name	ml-llm-prd
description	Use when the user wants a service PRD or PRD-lite for an ML or LLM feature, agent, retriever, evaluation service, or internal ML capability. Focus on business problem, scope, users, KPI, and release acceptance.

ML / LLM PRD

Read:

• ../../../ML LLM Delivery Pipeline/01 PRD Template.md
• ../../../ML LLM Delivery Pipeline/ML LLM Delivery Pipeline and Required Documents.md

Use this skill for business-facing scoping of a single ML/LLM service or capability, not for full architecture.

Cover

• goal and business context
• problem statement
• users and use cases
• scope and non-goals
• KPI and success criteria
• assumptions, constraints, dependencies
• pilot and release acceptance

Avoid

Do not drift into:

• API schemas
• low-level architecture
• detailed evaluation datasets
• runbook and operational procedures