The Video Signal

AI Engineer

Lifestyles of the AI-Native — Nick Nisi & Zack Proser, WorkOS

Published 2026-10-05 · Duration 1:01:28

Summary

This workshop details advanced workflows for operating 'AI-Native' engineering teams, moving beyond single-session agent interaction to managing 'fleets' of autonomous agents. Key concepts include defining measurable completion criteria using 'Goals,' setting up repeatable tasks with 'Loops,' enforcing mandatory steps via 'Hooks,' and parallelizing development using 'Git worktrees.' The focus is on building robust, autonomous systems that minimize human babysitting while preserving human judgment for final review.

Download summary

Key takeaways

  1. Shift from Single Session to Agent Fleet 2:00

    Engineers should operate a 'fleet of agents' rather than babysitting a single session, allowing for concurrent work across multiple tasks and projects.

  2. Goals vs. Loops 16:50

    A 'Goal' has a clear, measurable stopping condition (e.g., 'refactor this until all tests pass'). A 'Loop' repeats a task until manually canceled or a timer expires.

  3. Autonomous Workflow Primitives 19:10

    The system uses 'Hooks' (mandatory steps), 'Goals' (measurable termination), and 'Loops' (repetition) to ensure tasks complete fully, preventing agents from 'punching out' early.

  4. Concurrent Development with Worktrees 29:50

    Using 'Git worktrees' allows agents to run in parallel on isolated, safe copies of the repository, compressing large development blocks into shorter timeframes.

Technical details

  • Voice Coding 340s

    Using local dictation tools like Handy (which runs on-device) allows engineers to operate at the 'speed of thought,' significantly accelerating the process of generating code, file names, and technical commands.

  • Agent Orchestration (Fleet) 1850s

    Tools like 'Fleet' help manage and track multiple concurrent cloud sessions (e.g., 12 agents running simultaneously) by providing a centralized summary and status indicator.

  • Verification Gates and Hooks 1450s

    Hooks enforce mandatory steps (e.g., running linting, type checks, and tests) before an agent can proceed, preventing the system from lying about completion. Adversarial review (using a second model like Codeex) is recommended to find issues locally.

  • Scheduled Tasks 1300s

    The 'schedule' command allows automating tedious, recurring tasks (e.g., weekly reports, dependency updates) on a durable, repeatable basis, acting like a cron job for AI workflows.

  • Model Context Management 1550s

    To prevent context loss in long sessions, advanced techniques involve breaking work into small, atomic pieces and using state machines (e.g., in TypeScript) to force the agent through defined steps.

Mentioned resources

Channel & topics

Watch on YouTube · Back to latest

This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.