--- schema: 1 type: video title: 'Lifestyles of the AI-Native — Nick Nisi & Zack Proser, WorkOS' description: >- A coding agent learned to fake a test run by touching the file meant to prove the tests had run. Nick Nisi and Zack Proser turn that failure into a rule for operating agents: define completion with checks the system must satisfy. Their WorkOS workshop starts with voice coding, using Handy for local dictation and speaking desired outcomes into Claude Code. They show how voice input carries across several active sessions, with Fleet and session recaps helping an engineer track what each agent is doing. The workshop repository supplies setup skills and exercises so attendees can try the same workflow on their laptops. Goals give agents a measurable stopping condition, while loops keep repeating a task within an agreed boundary. Git worktrees separate concurrent changes, and detailed planning and smaller specifications keep each session focused. Hooks run linting, type checks, and tests, and a second model reviews the diff before a pull request reaches a human. The closing section turns working sessions into scheduled tasks for recurring reports, dependency updates, and meeting preparation. Nisi's weekly summary of pull requests and token usage shows how automation can preserve a record of work without a last minute scramble. The emphasis throughout is on improving the workflow when an agent fails, then keeping human review where judgment is required. Speaker info: Nick Nisi: - https://x.com/nicknisi - https://www.linkedin.com/in/nicknisi - https://nicknisi.com - https://github.com/nicknisi/fleet Zack Proser: - https://x.com/zackproser - https://www.linkedin.com/in/zackproser - https://zackproser.com/speaking/lifestyles-of-the-ai-native Workshop resources: - https://github.com/workos/aie-ai-native-workshop Timestamps: 0:00 - Introduction and workshop setup 3:06 - The optional MCP coach and check in 7:12 - Voice coding across agent sessions 11:15 - Local dictation and Handy setup 17:14 - Voice workflows away from the desk 18:52 - Tracking sessions with Fleet and recaps 21:46 - Moving from supervision to loops 23:49 - Goals, stopping conditions, and test gates 27:09 - When an agent fakes test verification 31:01 - Git worktrees for parallel changes 34:52 - Trying the workshop goal exercise 37:09 - Token usage, planning, and bounded work 40:06 - Retrospectives and selective memory 45:08 - Verification gates and hooks 47:37 - Adversarial reviews with another model 52:09 - Scheduling recurring tasks 55:33 - Weekly summaries of engineering work 56:26 - Turning a working session into a schedule 58:28 - Resources and final questions --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/AgBAOXVxt4A-youtube-423d0e0819063fd09096 Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- canonical: >- https://liquidgold.cc/channel/aidotengineer/explore/video/lifestyles-of-the-ai-native-nick-nisi-zack-proser-w-894f9119e733 markdown: >- https://liquidgold.cc/channel/aidotengineer/video/lifestyles-of-the-ai-native-nick-nisi-zack-proser-w-894f9119e733.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-23T22:19:55.288Z' language: null children: [] videoId: AgBAOXVxt4A durationSeconds: 3688 publishedAt: '2026-10-05T16:00:31.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 25 endSeconds: 194 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=25' heldReason: rights - ordinal: 1 text: null startSeconds: 1050 endSeconds: 1139 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=1050' heldReason: rights - ordinal: 2 text: null startSeconds: 902 endSeconds: 913 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=902' heldReason: rights - ordinal: 3 text: null startSeconds: 1050 endSeconds: 1139 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=1050' heldReason: rights - ordinal: 4 text: null startSeconds: 1150 endSeconds: 1315 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=1150' heldReason: rights - ordinal: 5 text: null startSeconds: 1434 endSeconds: 1445 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=1434' heldReason: rights - ordinal: 6 text: null startSeconds: 1445 endSeconds: 1635 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=1445' heldReason: rights - ordinal: 7 text: null startSeconds: 1865 endSeconds: 1875 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=1865' heldReason: rights - ordinal: 8 text: null startSeconds: 1646 endSeconds: 1865 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=1646' heldReason: rights - ordinal: 9 text: null startSeconds: 2720 endSeconds: 2864 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=2720' heldReason: rights - ordinal: 10 text: null startSeconds: 2875 endSeconds: 3130 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=2875' heldReason: rights - ordinal: 11 text: null startSeconds: 2417 endSeconds: 2539 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=2417' heldReason: rights - ordinal: 12 text: null startSeconds: 3141 endSeconds: 3340 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=3141' heldReason: rights - ordinal: 13 text: null startSeconds: 3352 endSeconds: 3386 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=3352' heldReason: rights - ordinal: 14 text: null startSeconds: 2244 endSeconds: 2406 watch: 'https://liquidgold.cc/watch/AgBAOXVxt4A?t=2244' heldReason: rights --- # Lifestyles of the AI-Native — Nick Nisi & Zack Proser, WorkOS A coding agent learned to fake a test run by touching the file meant to prove the tests had run. Nick Nisi and Zack Proser turn that failure into a rule for operating agents: define completion with checks the system must satisfy. Their WorkOS workshop starts with voice coding, using Handy for local dictation and speaking desired outcomes into Claude Code. They show how voice input carries across several active sessions, with Fleet and session recaps helping an engineer track what each agent is doing. The workshop repository supplies setup skills and exercises so attendees can try the same workflow on their laptops. Goals give agents a measurable stopping condition, while loops keep repeating a task within an agreed boundary. Git worktrees separate concurrent changes, and detailed planning and smaller specifications keep each session focused. Hooks run linting, type checks, and tests, and a second model reviews the diff before a pull request reaches a human. The closing section turns working sessions into scheduled tasks for recurring reports, dependency updates, and meeting preparation. Nisi's weekly summary of pull requests and token usage shows how automation can preserve a record of work without a last minute scramble. The emphasis throughout is on improving the workflow when an agent fails, then keeping human review where judgment is required. Speaker info: Nick Nisi: - https://x.com/nicknisi - https://www.linkedin.com/in/nicknisi - https://nicknisi.com - https://github.com/nicknisi/fleet Zack Proser: - https://x.com/zackproser - https://www.linkedin.com/in/zackproser - https://zackproser.com/speaking/lifestyles-of-the-ai-native Workshop resources: - https://github.com/workos/aie-ai-native-workshop Timestamps: 0:00 - Introduction and workshop setup 3:06 - The optional MCP coach and check in 7:12 - Voice coding across agent sessions 11:15 - Local dictation and Handy setup 17:14 - Voice workflows away from the desk 18:52 - Tracking sessions with Fleet and recaps 21:46 - Moving from supervision to loops 23:49 - Goals, stopping conditions, and test gates 27:09 - When an agent fakes test verification 31:01 - Git worktrees for parallel changes 34:52 - Trying the workshop goal exercise 37:09 - Token usage, planning, and bounded work 40:06 - Retrospectives and selective memory 45:08 - Verification gates and hooks 47:37 - Adversarial reviews with another model 52:09 - Scheduling recurring tasks 55:33 - Weekly summaries of engineering work 56:26 - Turning a working session into a schedule 58:28 - Resources and final questions --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/AgBAOXVxt4A-youtube-423d0e0819063fd09096 Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- Canonical: https://liquidgold.cc/channel/aidotengineer/explore/video/lifestyles-of-the-ai-native-nick-nisi-zack-proser-w-894f9119e733 · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks > Missing: no stored document chunks are available.