Improve Decision Quality with AI: Why Slower Starts Speed Up Delivery
AI can slow the start yet speed the sprint. Learn how to improve decision quality with AI by front-loading context, stress-testing plans, and cutting rework.
Design resilient LLM workflows: from fragile chains to fault-tolerant systems
Stop duct-taping prompts and start engineering. Learn how to design resilient LLM workflows with modular steps, observability, quality gates, and safe recovery.
Scaling LLM Applications the Engineering Way: Budgets, Observability, and Architecture Over Prompt Hacks
Treat LLM apps like scalable systems, not prompt hacks. Budgets, observability, caching, model tiering, and token discipline deliver predictable cost and latency.
Manufactured Reps: How to practice high-stakes engineering
You rarely get to practice the moments that matter. This piece shows how to practice high-stakes engineering by shadowing, simulation, and rehearsal so you’re ready when pressure spikes.
Make AI Demos Production-Ready: Ship Process, Not Just Code
Demos wow, but launches fail without production-grade process and clear ownership. Here’s how to make AI demos production-ready and ship reliably without fire drills.
Offload coding to AI and Raise Your Altitude: Build Systems, Not Boilerplate
Treat AI as leverage: offload coding to AI so you can focus on architecture, integration, and business outcomes. Ship smarter by orchestrating systems, not grinding boilerplate.
From Simple Points to System Wins: Leverage Points in Complex Systems
Engineers can turn messy systems into assets by hunting leverage points in complex systems—using rules, timing, and exceptions to unlock asymmetric results. This post shows how to run a 30-day experiment for a real win.
Reasoning Beats Ratings: Make Decisions Beyond Ratings for Real Fit
Ratings compress nuance. Learn how to read mid-tier reasoning, map trade-offs to your priorities, and choose tools that truly fit—across coffee gear to LLMs.
Satisficing vs Optimizing: Fit-First Choices That Leave Room for Delight
Stop equating price and stars with better outcomes. This piece applies satisficing vs optimizing to tools, models, and trips so fit, slack, and lower stakes create more joy.
Build Technical Credibility with Engineers by Making the Scaffolding Visible
Engineers judge competence by your scaffolding, not your story. Learn how to build technical credibility with engineers by making assumptions, constraints, interfaces, and risks visible first.