# LLM Integration & Streaming AI Workflows

> Best practices for integrating Large Language Models into web apps, including streaming UI, prompt templating, token budgeting, and fallback providers.

Canonical: https://www.agentickit.co/skills/llm-integration
Last updated: 2026-11-18

## Key practices
- Stream AI responses using Vercel AI SDK to minimize perceived latency
- Enforce structured JSON output using OpenAI response_format or Anthropic tool use
- Implement token usage counters and rate limit throttling per user tier
- Add retry logic with exponential backoff for rate-limited API calls

## Related
- [ai-engineer](https://www.agentickit.co/agents/ai-engineer)
- [backend-architect](https://www.agentickit.co/agents/backend-architect)
- [/ai-feature](https://www.agentickit.co/commands/ai-feature)
- [/llm-chat](https://www.agentickit.co/commands/llm-chat)
