This essay foretells the future of coding with AI agents . It reminds me of Autopilot on an airplane or the Tesla Self driving AI where the humans job is to monitor and tweak the inputs to ensure a getting to the destination.

People coding with LLMs today use agents. Agents get to poke around your codebase on their own. They author files directly. They run tools. They compile code, run tests, and iterate on the results. They also:

  • pull in arbitrary code from the tree, or from other trees online, into their context windows,
  • run standard Unix tools to navigate the tree and extract information,
  • interact with Git,
  • run existing tooling, like linters, formatters, and model checkers, and
  • make essentially arbitrary tool calls (that you set up) through MCP.

Thomas Ptacek