← All topics
Topic 11 articles

Building With AI

How to actually use AI: skills, harnesses, and turning capability into results.

A guided path

Start here, then go deeper

Three selected reads, ordered from foundation to practical application.

01 Start here
A projector shines through a row of hanging sheets of checklists and diagrams onto one finished page, beside crumpled drafts and a neat stack of printed pages.
Article Building 9 min read

Where the Harness Pays Off, and Where It Does Not

Most AI budgets fund the wrong remedy because the workflow type was never diagnosed. Capability-bound vs friction-bound is the missing one-page policy.

Read article →
  1. 02 Go deeper Building 8 min read

    AI Is a Mirror: Stanford's Lesson From 51 Deployments

    Stanford studied 51 successful enterprise AI deployments. The difference was never the AI model. It was the organization. Here is what that means.

    Read article →
  2. 03 Go deeper Building 9 min read

    Don't Build What You Can't Keep

    McKinsey's 2026 survey found 32% of respondents saying their organization decided against buying at least one software product or feature because it could be built with coding agents. The companion post argued that the buy rule grew a second half. This article does the three things the post could not: reads the survey's size gap honestly, sorts builds into the three kinds that need different rules, and shows how to price what keeping a built tool costs every month.

    Read article →
Continue browsing

Latest in this topic

The newest decisions beyond the guided path.

A railway junction. On a side track ending at a buffer stop, a row of eight freight wagons stands parked. On the main line, a small locomotive pulls just two open wagons away, with a long stretch of empty track between them and the row.
Article Building 10 min read

Token Economics Starts With What a Session Carries

Claude Code resends the whole conversation with every request. A five-step routine to cut what sessions carry without cutting what the work needs.

Read article →
A desk dial labelled 'Model Selector' with a large knob and three settings around it: 'Fast & Simple', 'Balanced' and 'Deep Thinking'.
Article Building 6 min read

Ask the Phase, Not the Model

Anthropic and OpenAI both say to match reasoning effort to the task: explore an approach, or execute one you already trust.

Read article →
Four identical upright metal posts with round knobs are mounted in a row on a shelf. Only the first one has a blank tag tied to it.
Article Building 6 min read

Four Levers, Not One Dial

AI autonomy isn't one dial. Anthropic's own team breaks it into four separate handoffs, and only one of them decides whether the rest are safe to hand off.

Read article →
A tall metal filing cabinet is covered in dozens of sticky notes pinned over its drawers and sides, some half hiding the drawer handles and labels.
Article Building 7 min read

Cheap to Write, Expensive to Keep

A system that remembers across more than one layer has a stratum you can delete with no consequence and a stratum that takes everything with it. Cost asymmetry moves important knowledge into the cheap one without anyone deciding it. This is the evidence for why that happens, and why better writing tools do not fix it.

Read article →
A filing cabinet with one drawer pulled half open, the drawer densely packed with file folders.
Article Building 5 min read

Skills Beat Agents: The AI Layer CEOs Keep Missing

Agent count is the visible metric. Skill depth is the layer that actually produces returns, survives vendor changes, and becomes IP the company owns.

Read article →
What Zuckerberg's AI Deputy Reveals About Your Information Gap
Article Building 4 min read

What Zuckerberg's AI Deputy Reveals About Your Information Gap

Zuckerberg is building an AI agent to bypass the layers between him and his data. The real story is the information gap every CEO shares.

Read article →
You're Not Using AI Wrong. You're Building Wrong.
Article Building 5 min read

You're Not Using AI Wrong. You're Building Wrong.

McKinsey tested 25 factors. The single biggest predictor of AI profitability was workflow redesign. Not better models, not bigger budgets.

Read article →
The Case for Using AI Less
Article Building 3 min read

The Case for Using AI Less

More AI is not always better AI. When cognitive dependency replaces cognitive effort, the advantage reverses.

Read article →
Other topics
GovernanceStrategy & ROIWorkforceStack & EconomicsReal World