When chat is the wrong UI

Burke Holland of GitHub argues that once a person knows a repeated job, having an AI agent build a small app for it costs fewer tokens than asking in chat.

Chat is still the main way people work with AI models, three years after it took off. Burke Holland, who works on AI-powered development at GitHub, argues that chat suits a first attempt but becomes wasteful once the job is known. In the GitHub Copilot app, which runs GitHub's AI coding agent, he has the agent build small apps called canvases that run inside the app and talk to the agent.

• Holland's reason is cost. Tokens are the units of text an AI model is billed by. An agent asked to do a routine job spends tokens every time, while a tool it builds once costs nothing to use.
• His examples include a manager for software packages that contains no AI at all, a browser for a SQLite database and an editor for blog posts.
• He also built a canvas that runs his whole working process, from research to finished code, so the agent can work alone and call him in for review. It took most of a day to get right.
• The piece appears on GitHub's own blog and promotes GitHub's own app.

Once a team knows a job it keeps asking an agent to do, it can have the agent build a small tool for that job instead. This is the author's advice, and he is promoting his employer's product.

Derived by Working Surface from the article. Source line: The goal with agents is always to take yourself out of the loop as much as you can.

26 September 2026: when agents can finish whole tasks, teams redesign the work, the checks and the roles around them.