Help us improve
Share bugs, ideas, or general feedback.
Evaluate AI capability sourcing options across build, buy, fine-tune, and partner archetypes using a structured decision matrix. Use when deciding whether to build a custom model, use an LLM API, fine-tune a base model, or partner with an AI vendor.
npx claudepluginhub tarunccet/pm-skills --plugin pm-ai-product-managementHow this skill is triggered — by the user, by Claude, or both
Slash command
/pm-ai-product-management:ai-build-buy-partnerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Systematically evaluate AI capability sourcing options to find the right balance of speed, cost, control, and strategic differentiation.
Guides AI/ML system design, LLM architecture, MLOps pipelines, provider selection (OpenAI, Anthropic, Hugging Face), model serving, RAG, agents, evaluation. Use for AI systems, MLOps, provider choice.
Guides decisions on model sovereignty: prompting, RAG, fine-tuning (LoRA/QLoRA), distillation, local hosting for privacy, cost, and customization needs.
Guides adding AI-powered features to SaaS products including LLM API integration, RAG, AI assistants, prompt engineering, API selection, and cost management for scalable shipping.
Share bugs, ideas, or general feedback.
Systematically evaluate AI capability sourcing options to find the right balance of speed, cost, control, and strategic differentiation.
You are evaluating AI capability sourcing options for $ARGUMENTS.
Define the capability and requirements:
Evaluate the four sourcing archetypes:
Archetype 1 — Pure API (e.g., OpenAI, Anthropic, Google):
Archetype 2 — Fine-tuned base model (e.g., fine-tuned Llama, Mistral):
Archetype 3 — Hybrid (API + RAG / retrieval augmentation):
Archetype 4 — Fully custom model:
Score each archetype on the decision matrix:
| Dimension | Weight | Pure API | Fine-tuned | Hybrid | Custom |
|---|---|---|---|---|---|
| Strategic differentiation | 20% | /5 | /5 | /5 | /5 |
| Data advantage leverage | 15% | /5 | /5 | /5 | /5 |
| Cost at scale (10× volume) | 15% | /5 | /5 | /5 | /5 |
| Time-to-market | 15% | /5 | /5 | /5 | /5 |
| Compliance / data residency | 15% | /5 | /5 | /5 | /5 |
| Customisation / control | 10% | /5 | /5 | /5 | /5 |
| Team capability match | 10% | /5 | /5 | /5 | /5 |
| Weighted total | 100% |
Cost modelling — API vs. infrastructure:
monthly_requests × avg_tokens × price_per_1k_tokensMake-or-buy signals:
Vendor evaluation checklist:
Partnership vs. licensing:
Produce recommendation report:
Think step by step. Save as markdown.