A series exploring the development of AI-powered assistants. Covering prompt engineering, tool-use frameworks, local LLM deployment, and integration with realtime communication platforms.
Episodes
No posts yet in this series. Subscribe to the blog or follow on Twitch for updates.
Topics Covered
- Local LLM setup (Ollama, llama.cpp)
- Function calling & tool-use patterns
- Twitch chat integration
- Discord bot assistants
- RAG pipelines for personal knowledge bases