What practice do you recommend for customizing AI coding agents to your workflow?

The answers all emphasize tailoring AI agents to your needs, whether by defining clear goals, building accessible systems, or iteratively refining and training the models for your workflow.

5 answers

Answers

  • Hahnbee Lee

    Co-Founder · Mintlify

    Create APIs

    Hahnbee Lee recommends creating APIs so everything is accessible to agents, saying agents speak the language of developers and are really good at bash and CLI commands.

    AI Engineer · Watch on YouTube
  • 🦄 Peter Steinberger

    Founder · Amantus Machina

    Design a pipeline

    Peter Steinberger recommends designing a pipeline from “this is what I want” to “this is the outcome,” saying the better you do that, the better your outcome will be.

    A16Z GAMES · A16Z GAMES · Read
  • Nan Yu

    Head of Product · Linear

    Define clear goal

    Nan Yu recommends giving the agent a really good defined goal, saying they're smart enough to get what they need if you do.

    Peter Yang · Watch on YouTube
  • Jacob Shumway

    Product Engineer · Linear

    Start With the Biggest Model

    Jacob Shumway recommends throwing the biggest model at a task until it’s working well, then optimizing down once you have evals and success criteria to check it.

    Peter Yang · Watch on YouTube
  • Mark Papermaster

    CTO and EVP · AMD

    Invest time to train

    Mark Papermaster recommends investing time to tailor and train the model of your choice to you, telling it who you are, what you like and your style, because he says that makes it most productive for you.

    The Deep View: Conversations · The Deep View: Conversations · Listen at 18:34

More Software Engineering questions

View all →