Building with LLMs
Docs, patterns and tools for agents and coding assistants
Last edited .
Prompting and patterns
- Anthropic: prompt engineering
- OpenAI: prompt engineering
- Prompt Engineering Guide
- Building effective agents - read before picking a framework
Tools and protocols
- Model Context Protocol - see also the Dataverse MCP server
- Claude Code and best practices
- gstack - Garry Tan’s opinionated Claude Code setup
- OpenCode - open source, any model
- Hermes Agent - open source, from Nous Research
- CrewAI - multi-agent framework in Python
- Groq - fast inference API, with a playground
- Agent shell commands failing on Windows with
fork ... 0xC0000142? Fix Git Bash under Mandatory ASLR - Anthropic skills
- ElevenLabs - voice, and D-ID - avatar video
Running models locally
- Ollama
- LM Studio - with a GUI
- AI Dev Gallery - Microsoft’s Windows app of on-device samples; works nicely with Phi and Intel silicon
- Foundry Local - Microsoft’s on-device runtime
Microsoft
- GitHub Copilot docs and Copilot in VS Code
- Copilot Studio - agents on the Power Platform
- Microsoft 365 Copilot documentation
Still stuck? Work with me or get in touch.