--- schema: 1 type: video title: 'Feedback Loops are All You Need — Mehedi Hassan, Granola' description: >- One-shotting is seductive. One line of code for web search. One prompt to serve every user. One deploy and you're done. Granola shipped a chat feature into their meeting notes app and found out what comes after that. This talk is a product engineer's honest account of why the gap between "it works in the playground" and "it works in production" is so hard to close. Web search looks like a single tool call — until it blows up your context, bills you 10p per chat, and your provider ships an overnight update that silently degrades your results. Prompt personalization looks straightforward — until you realize that one prompt genuinely cannot serve the salesperson expecting a deal summary, the engineer expecting blockers and linear tickets, and the HR manager expecting something else entirely. The response at Granola wasn't to prompt better. It was to build the machinery for iteration: custom internal tracing that exposes tool calls, search trails, reasoning traces, and cost in a UI built for everyone — not just engineers with CloudWatch access. And a move to run their Electron frontend as a web app, so every PR gets a preview link and Cursor can go test changes automatically. The point isn't any single technique. It's the feedback loop — and what happens to an AI feature when it actually has one. Speaker info: - https://x.com/mehedih_ - https://github.com/MehediH timestamps: 0:15 Introduction to Granola and product engineering 1:08 Demonstration of meeting transcription and note-taking features 1:52 The challenges of shipping generic AI features 2:48 The difficulties of integrating web search tools 4:02 Why a single prompt cannot serve diverse user roles 4:40 Building custom internal tracing and observability tools 6:22 Enhancing developer experience for desktop applications 7:16 Refactoring Electron for web-based testing and CI/CD preview links 8:33 Automating feature verification with Cursor 8:46 Concluding thoughts on building iterative feedback loops for AI products --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/ON5LIT0M4do-feedback-loops-are-all-you-need 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/feedback-loops-are-all-you-need-mehedi-hassan-grano-2fe10c2971e4 markdown: >- https://liquidgold.cc/channel/aidotengineer/video/feedback-loops-are-all-you-need-mehedi-hassan-grano-2fe10c2971e4.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T14:11:42.828Z' language: null children: [] videoId: ON5LIT0M4do durationSeconds: 611 publishedAt: '2026-05-10T18:00:06.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 26 endSeconds: 115 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=26' heldReason: rights - ordinal: 1 text: null startSeconds: 26 endSeconds: 115 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=26' heldReason: rights - ordinal: 2 text: null startSeconds: 126 endSeconds: 211 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=126' heldReason: rights - ordinal: 3 text: null startSeconds: 126 endSeconds: 211 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=126' heldReason: rights - ordinal: 4 text: null startSeconds: 211 endSeconds: 223 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=211' heldReason: rights - ordinal: 5 text: null startSeconds: 223 endSeconds: 313 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=223' heldReason: rights - ordinal: 6 text: null startSeconds: 223 endSeconds: 313 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=223' heldReason: rights - ordinal: 7 text: null startSeconds: 313 endSeconds: 323 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=313' heldReason: rights - ordinal: 8 text: null startSeconds: 323 endSeconds: 446 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=323' heldReason: rights - ordinal: 9 text: null startSeconds: 323 endSeconds: 446 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=323' heldReason: rights - ordinal: 10 text: null startSeconds: 323 endSeconds: 446 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=323' heldReason: rights - ordinal: 11 text: null startSeconds: 457 endSeconds: 611 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=457' heldReason: rights - ordinal: 12 text: null startSeconds: 457 endSeconds: 611 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=457' heldReason: rights - ordinal: 13 text: null startSeconds: 457 endSeconds: 611 watch: 'https://liquidgold.cc/watch/ON5LIT0M4do?t=457' heldReason: rights --- # Feedback Loops are All You Need — Mehedi Hassan, Granola One-shotting is seductive. One line of code for web search. One prompt to serve every user. One deploy and you're done. Granola shipped a chat feature into their meeting notes app and found out what comes after that. This talk is a product engineer's honest account of why the gap between "it works in the playground" and "it works in production" is so hard to close. Web search looks like a single tool call — until it blows up your context, bills you 10p per chat, and your provider ships an overnight update that silently degrades your results. Prompt personalization looks straightforward — until you realize that one prompt genuinely cannot serve the salesperson expecting a deal summary, the engineer expecting blockers and linear tickets, and the HR manager expecting something else entirely. The response at Granola wasn't to prompt better. It was to build the machinery for iteration: custom internal tracing that exposes tool calls, search trails, reasoning traces, and cost in a UI built for everyone — not just engineers with CloudWatch access. And a move to run their Electron frontend as a web app, so every PR gets a preview link and Cursor can go test changes automatically. The point isn't any single technique. It's the feedback loop — and what happens to an AI feature when it actually has one. Speaker info: - https://x.com/mehedih\_ - https://github.com/MehediH timestamps: 0:15 Introduction to Granola and product engineering 1:08 Demonstration of meeting transcription and note-taking features 1:52 The challenges of shipping generic AI features 2:48 The difficulties of integrating web search tools 4:02 Why a single prompt cannot serve diverse user roles 4:40 Building custom internal tracing and observability tools 6:22 Enhancing developer experience for desktop applications 7:16 Refactoring Electron for web-based testing and CI/CD preview links 8:33 Automating feature verification with Cursor 8:46 Concluding thoughts on building iterative feedback loops for AI products --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/ON5LIT0M4do-feedback-loops-are-all-you-need 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/feedback-loops-are-all-you-need-mehedi-hassan-grano-2fe10c2971e4 · 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.