# /ai-feature - AI Integration & Vector Pipeline Builder

> OpenAI/Anthropic integration, streaming chat, embeddings, and vector search.

Canonical: https://www.agentickit.co/commands/ai-feature
Last updated: 2026-11-18

Integrates LLMs into your product: streaming completions, prompt templates, pgvector embeddings, and token cost budgeting.

**Usage:** `Use when adding AI features like document summarization, semantic search, or smart assistants.`

## Pipeline
1. Configure AI provider SDK with streaming response handler
2. Generate embeddings for incoming text records and save to pgvector
3. Implement cosine similarity search endpoint with relevance filtering
4. Build streaming frontend UI with markdown rendering and token counters

## Output files
- `src/app/api/ai/.../route.ts`
- `src/lib/ai.ts`
- `src/components/ai/...`

**Claude Code frontmatter:** `argument-hint: [AI feature description]` · `model: inherit`

## Related
- [ai-engineer](https://www.agentickit.co/agents/ai-engineer)
- [backend-architect](https://www.agentickit.co/agents/backend-architect)
- [llm-integration](https://www.agentickit.co/skills/llm-integration)
- [vector-database](https://www.agentickit.co/skills/vector-database)
- [prompt-engineering](https://www.agentickit.co/skills/prompt-engineering)
