Blog
Practical prompt engineering -- every post includes real prompts you can copy and adapt.
88 articles • Page 1 of 10
The orchestration patterns behind Cursor's parallel agents and Claude Code's background tasks
The delimiter strategy that Claude, GPT, and Gemini all respond to better than plain English sections
Model Context Protocol is the new API layer for AI agents -- here's how to design tools that don't confuse them
Stop bolting retrieval onto bad prompts -- design prompts that actually use retrieved context correctly
Turn your workflow's "always do X before Y" rules into machine-checkable invariants that catch out-of-order tool calls before they cause damage.
OpenAI's own tests show trimming duplicated instructions raises scores 10-15% while cutting tokens up to 66%. Your old scaffolding is now a tax.
Microsoft Agent Framework's magentic pattern lets a manager invent the workflow at runtime. Here's the ledger prompt that makes it converge instead of loop forever.
Seventeen models, thirteen spatial benchmarks, one verdict: "think step by step" makes maps, mazes, and layouts worse. Here's what to send instead.
Steal the validation-gated completion pattern from this week's Paper-replication skill and make every agent attach a receipt before it stops.
