Learn to work with AI, one clear guide at a time

Build a Classification Prompt That Beats Fine-Tuning

A production-ready classification prompt for your own labels, with self-consistency voting, structured output, and an eval harness, with 90%+ accuracy as the target and no fine-tuning.

Build a RAG Eval Harness That Catches Regressions

A repeatable test suite measuring faithfulness, answer relevance, and context precision across 50-200 Q&A pairs. Ship gates on it; your RAG quality stops being vibes-based and becomes observable.

Prompt Injection Test Suite for Production Agents

A regression-runnable suite of 40+ injection probes that catches the classes of attacks your agent will actually face. Run nightly, track pass rate per prompt/model version, catch regressions before users do.

Supervisor-Worker Agent Pattern for Cost Optimization

Cut agent costs by routing cheap sub-tasks to Haiku-class models and reserving the frontier for planning. Includes a full Python reference implementation, cost accounting, and the fallback logic.

Token Budget & Cost Estimator for Production LLM Apps

A pre-flight cost calculator that tells you, before you call, how many tokens a given prompt + expected response will burn, across multiple models, so your app can choose the cheapest model that fits the window.

Grounding Prompts With Retrieved Context: The RAG Prompt Patterns That Stop Invented Answers

Stop bolting retrieval onto bad prompts. Design prompts that actually use retrieved context correctly

Brian Gagne · July 27, 2026

Your Agent Skips Step 3 Every Time: Stop Describing Your Procedure and Verify Its Trace Instead

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.

Brian Gagne · July 23, 2026

GPT-5.6 Pays You to Delete Your System Prompt: State Every Rule Once and Stop Repeating Yourself

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.

Brian Gagne · July 20, 2026

Magentic Just Hit 1.0, and Your Whole Agent Team Lives or Dies by the Manager's Ledger Prompt

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.

Brian Gagne · July 16, 2026

Chain-of-Thought Is Sabotaging Your Model's Sense of Direction: Prompt Grids as Symbols, Not Sentences

Seventeen models, thirteen spatial benchmarks, one verdict: "think step by step" makes maps, mazes, and layouts worse. Here's what to send instead.

Brian Gagne · July 13, 2026

Your Agent's 'Done' Is a Lie: Gate Completion on Disk Evidence, Not Its Final Message

Steal the validation-gated completion pattern from July 2026's Paper-replication skill and make every agent attach a receipt before it stops.

Brian Gagne · July 9, 2026

Your Agent's Planner Is Fine. Its Aggregator Is What's Broken

ROMA hit state-of-the-art on SealQA by compressing every subtask tree before it bubbles up. Here are the four node prompts you can copy without adopting the framework.

Brian Gagne · July 2, 2026

Stop Trusting Free-Form Chain-of-Thought. Make Your Model Sign a Logical Certificate Instead

Meta's semi-formal reasoning template forces premises, traced paths, and a derived conclusion, so you can see exactly where the model is bluffing.

Brian Gagne · June 29, 2026