Tag: AI

Get more from the chat drawer — structured filters, the context meter, and conversation history.

Where LLMs sharpen product discovery and where they quietly hollow it out — a stage-by-stage guide to the dos and don'ts.

AI feels like noise, not leverage — scattered usage, no compounding.

Building reusable AI setups (projects, custom instructions, examples) that improve with use, turning one-time prompt wins into durable productivity systems.

The practice of supplying AI systems with the right background information, in the right format, to produce useful outputs.

A hands-on workshop that moves professionals from casual AI usage to intentional workflow engineering, teaching prompt engineering, context engineering, and compounding setup design using real work.

Systematic methods for measuring AI output quality so you can tell whether your prompts, context, and setups actually work.

How to wire a library of example files into Claude Projects, Cowork, and Claude Code so the right exemplars are selected per task and your quality bar compounds instead of resetting every session.

Margaret-Anne Storey's article proposing a triple debt model of technical, cognitive, and intent debt for reasoning about software health in the age of AI.

Connect Claude or ChatGPT to the Nerd/Noir collection over Model Context Protocol for search, note retrieval, and resource browsing.

Using a model to build prompts as artifacts, either developing a reusable prompt on purpose or extracting one from a chat that already worked.

Thinking deliberately about how you work, surfacing habitual patterns and tacit knowledge so you can identify opportunities for improvement or automation.

Running many short-lived insight-to-experiment tracks alongside a durable delivery track. An AI-era update to Jeff Patton's dual-track model.

The practice of structuring instructions to AI systems for reliable, high-quality outputs through deliberate choices about structure, specificity, and iteration.

Six named structures for prompts — CO-STAR, RISEN, RACE, CREATE, APE, and STOKE — with the components each one forces you to specify and a decision matrix for picking one.

Using AI to analyze successful outputs and reverse-engineer the prompts that would produce them, accelerating prompt development.