Track III · The playbook

Working with
AI agents.

How to read, review, and prompt agents that already write Rust well. Agents already know Rust well; the gap is on your side. When an agent emits 600 lines against your prompt, you do not need to write them from scratch. You need to read them critically, gate them with Cargo, and push back specifically.

The loop

  1. i
    Prompt clearly

    Name the contract: signature, error type, ownership boundary, tests.

  2. ii
    Read the diff

    Five minutes, five questions. Diff shape, public API, errors, allocations, tests.

  3. iii
    Run the gates

    cargo fmt --check && cargo clippy -- -D warnings && cargo test --workspace.

  4. iv
    Push back specifically

    Justify each .clone(). Show the error type. Why Arc and not Rc?

  5. v
    Iterate small

    Tiny diffs that pass the gates. Compound the discipline.

Chapters

Six pieces · 45 min total
  1. 01
    Review lens
    Per-concept review notes you scan during every diff.
    The cheat sheet
  2. 02
    12 failure modes
    What agents get wrong in Rust, with diffs.
    12 patterns
  3. 03
    Cargo gates
    Make agents prove correctness with Cargo.
    CI + pre-commit
  4. 04
    Prompting Rust
    Rust-specific prompts that actually work.
    Templates
  5. 05
    5-minute PR review
    Five questions, in order, for every Rust diff.
    5 minutes
  6. 06
    Error decoder
    Common errors, the lazy fix, and the real fix.
    rustc decoded