The Supervisor-Worker Agent Pattern: One Smart Model Plans, Cheap Models Execute
How to architect multi-agent systems that cost 90% less than running Opus on everything
Blog
Practical prompt engineering -- every post includes real prompts you can copy and adapt.
90 articles • Page 6 of 10
How to architect multi-agent systems that cost 90% less than running Opus on everything
The 2026 skill that replaced prompt engineering as the bottleneck for agentic systems
The cost and quality math behind splitting monolithic prompts into chains
Why 'You are a senior engineer who also reviews for security' beats single-role prompts
Use frontier models to improve their own instructions with measurable improvement loops
Why exclusion constraints are more effective than inclusion instructions for complex tasks
The counterintuitive cases where removing examples improves output quality
The prompts that turn raw financials into client-ready advisory letters, and the judgment calls AI can't make for you
The PM prompt toolkit that replaces 6 hours of synthesis work with 20 minutes