--- schema: 1 type: video title: 'Vibe Engineering Effect Apps — Michael Arnaldi, Effectful' description: >- What if the best way to get coding agents to use a library well is not better prompts, but giving them the library's actual code? In this workshop, Michael Arnaldi walks through a practical approach to building with Effect and LLMs by cloning the Effect repo into the project, extracting patterns directly from the source, and using those patterns to guide agent behavior. Starting from an empty repository, the session shows how to set up an Effect-based app with tests, strict TypeScript diagnostics, agent instructions, and a simple HTTP API, while also exploring the broader problem of how to make agents effective in unfamiliar codebases. If you're building with coding agents and care about reliability, structure, and real-world Effect workflows, this is a useful hands-on framing. Speaker info: - https://x.com/MichaelArnaldi - https://www.linkedin.com/in/michael-arnaldi-52858114a/ Timestamps 0:15 – Introduction and context setting for the workshop 0:47 – Interactive audience poll on experience with Effect and AI tooling 3:16 – Discussing the core philosophy: "Just clone the repo" for AI context 5:59 – Understanding LLMs vs. the human brain and context window limitations 13:13 – Project setup: Starting from an empty repository 14:20 – Initializing the project with Bun, Vitest, and TypeScript 19:18 – Adding Effect beta and configuring TSGo for the compiler 30:30 – Configuring strict diagnostics for AI-assisted development 35:20 – Adding the Effect repository as a git subtree for better agent access 37:07 – Creating agents.md to establish rules and available commands 41:40 – Researching Effect patterns for building an HTTP API 43:08 – Discussing "Spec-Driven Development" and avoiding plan-mode limitations 54:02 – Drafting the plan for the Todo HTTP API 1:05:07 – Implementing the SQL client and migration patterns 1:13:42 – Reviewing API schemas and handling identified code duplication 1:18:14 – Starting the API server and verifying OpenAPI documentation 1:20:56 – Cleaning up test suites and enforcing best practices for layers 1:38:08 – Concluding remarks on workflows, clustering, and future stability in Effect --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/Wmp2Tku2PrI-vibe-engineering-effect-apps 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/watch/Wmp2Tku2PrI' markdown: 'https://liquidgold.cc/watch/Wmp2Tku2PrI.md' llms: 'https://liquidgold.cc/watch/Wmp2Tku2PrI/llms.txt' parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T14:12:06.089Z' language: null children: [] videoId: Wmp2Tku2PrI durationSeconds: 6184 publishedAt: '2026-05-07T15:00:06.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 597 endSeconds: 714 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=597' heldReason: rights - ordinal: 1 text: null startSeconds: 725 endSeconds: 836 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=725' heldReason: rights - ordinal: 2 text: null startSeconds: 468 endSeconds: 587 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=468' heldReason: rights - ordinal: 3 text: null startSeconds: 341 endSeconds: 456 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=341' heldReason: rights - ordinal: 4 text: null startSeconds: 238 endSeconds: 328 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=238' heldReason: rights - ordinal: 5 text: null startSeconds: 2103 endSeconds: 2118 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=2103' heldReason: rights - ordinal: 6 text: null startSeconds: 2220 endSeconds: 2233 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=2220' heldReason: rights - ordinal: 7 text: null startSeconds: 2233 endSeconds: 2370 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=2233' heldReason: rights - ordinal: 8 text: null startSeconds: 2381 endSeconds: 2468 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=2381' heldReason: rights - ordinal: 9 text: null startSeconds: 2585 endSeconds: 2669 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=2585' heldReason: rights - ordinal: 10 text: null startSeconds: 2669 endSeconds: 2679 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=2669' heldReason: rights - ordinal: 11 text: null startSeconds: 2679 endSeconds: 2794 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=2679' heldReason: rights - ordinal: 12 text: null startSeconds: 2805 endSeconds: 2915 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=2805' heldReason: rights - ordinal: 13 text: null startSeconds: 2926 endSeconds: 3046 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=2926' heldReason: rights - ordinal: 14 text: null startSeconds: 1770 endSeconds: 1853 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=1770' heldReason: rights - ordinal: 15 text: null startSeconds: 3634 endSeconds: 3741 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=3634' heldReason: rights - ordinal: 16 text: null startSeconds: 3144 endSeconds: 3215 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=3144' heldReason: rights - ordinal: 17 text: null startSeconds: 3953 endSeconds: 4058 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=3953' heldReason: rights - ordinal: 18 text: null startSeconds: 4070 endSeconds: 4175 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=4070' heldReason: rights - ordinal: 19 text: null startSeconds: 5633 endSeconds: 5757 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=5633' heldReason: rights - ordinal: 20 text: null startSeconds: 5888 endSeconds: 5990 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=5888' heldReason: rights - ordinal: 21 text: null startSeconds: 6001 endSeconds: 6105 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=6001' heldReason: rights - ordinal: 22 text: null startSeconds: 1170 endSeconds: 1285 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=1170' heldReason: rights - ordinal: 23 text: null startSeconds: 5364 endSeconds: 5374 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=5364' heldReason: rights - ordinal: 24 text: null startSeconds: 932 endSeconds: 944 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=932' heldReason: rights - ordinal: 25 text: null startSeconds: 5114 endSeconds: 5253 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=5114' heldReason: rights - ordinal: 26 text: null startSeconds: 846 endSeconds: 932 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=846' heldReason: rights - ordinal: 27 text: null startSeconds: 6105 endSeconds: 6184 watch: 'https://liquidgold.cc/watch/Wmp2Tku2PrI?t=6105' heldReason: rights --- # Vibe Engineering Effect Apps — Michael Arnaldi, Effectful What if the best way to get coding agents to use a library well is not better prompts, but giving them the library's actual code? In this workshop, Michael Arnaldi walks through a practical approach to building with Effect and LLMs by cloning the Effect repo into the project, extracting patterns directly from the source, and using those patterns to guide agent behavior. Starting from an empty repository, the session shows how to set up an Effect-based app with tests, strict TypeScript diagnostics, agent instructions, and a simple HTTP API, while also exploring the broader problem of how to make agents effective in unfamiliar codebases. If you're building with coding agents and care about reliability, structure, and real-world Effect workflows, this is a useful hands-on framing. Speaker info: - https://x.com/MichaelArnaldi - https://www.linkedin.com/in/michael-arnaldi-52858114a/ Timestamps 0:15 – Introduction and context setting for the workshop 0:47 – Interactive audience poll on experience with Effect and AI tooling 3:16 – Discussing the core philosophy: "Just clone the repo" for AI context 5:59 – Understanding LLMs vs. the human brain and context window limitations 13:13 – Project setup: Starting from an empty repository 14:20 – Initializing the project with Bun, Vitest, and TypeScript 19:18 – Adding Effect beta and configuring TSGo for the compiler 30:30 – Configuring strict diagnostics for AI-assisted development 35:20 – Adding the Effect repository as a git subtree for better agent access 37:07 – Creating agents.md to establish rules and available commands 41:40 – Researching Effect patterns for building an HTTP API 43:08 – Discussing "Spec-Driven Development" and avoiding plan-mode limitations 54:02 – Drafting the plan for the Todo HTTP API 1:05:07 – Implementing the SQL client and migration patterns 1:13:42 – Reviewing API schemas and handling identified code duplication 1:18:14 – Starting the API server and verifying OpenAPI documentation 1:20:56 – Cleaning up test suites and enforcing best practices for layers 1:38:08 – Concluding remarks on workflows, clustering, and future stability in Effect --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/Wmp2Tku2PrI-vibe-engineering-effect-apps 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/watch/Wmp2Tku2PrI · 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.