--- schema: 1 type: video title: >- From AI-Assisted to AI-Native: Building a Frontier Development Team — Clare Liguori, AWS description: >- Amazon watched 50 ordinary teams for the better part of a year, teams with normal seniority mixes working in existing codebases. Ninety percent of them used the same coding assistant. Half saw under 3x improvement in deployment velocity to production. The other half saw a median of 4.5x and sometimes past 10x. The tool was not the variable. The teams that pulled ahead had deliberately changed how they worked, and the rest had sprinkled agents on top of the way they already worked. Clare Liguori calls the result frontier development, and defines it by behavior: engineers writing one to two percent of their own code, agents running for hours without interruption, several running at once. Her five habits are mostly unglamorous. Write down what lives in your head, then keep pruning it as models improve so old workarounds stop bloating context. Expect to get slower first, because brownfield codebases need real work before agents succeed in them, which for some teams meant better error messages, new tools, or restructuring outright. Feed agents rather than babysitting them, since a running conversation keeps you in the loop and makes parallelism impossible. Fix the intent in a document before arguing with generated code. Shift testing left, with local deterministic mocks, so the feedback loop is fast enough for an agent to self correct. The new bottleneck is decision speed. Speaker info: - https://x.com/clare_liguori - https://www.linkedin.com/in/clareliguori/ - https://clare.dev/ Timestamps: 0:00 - Four phases, and only 10% to 20% felt 1:22 - What the pilots actually measured 2:34 - Thirty people for 18 months, or six people for 76 days 3:43 - Why that team was not reproducible 4:51 - A ten day sprint, and its asterisks 5:57 - Fifty ordinary teams, and the real split 7:04 - Same tools, different ways of working 8:14 - Habit one: invest in agent context 9:21 - Pruning context as models improve 10:31 - Habit two: slow down to speed up 12:50 - Feeding agents instead of babysitting them 13:58 - Making intent explicit before writing code 15:09 - Shifting testing left with local mocks 16:15 - Burnout, FOMO and cognitive load 17:23 - What organizations have to change 19:41 - When decision speed becomes the bottleneck --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/pqlWNihgdjI-youtube-ca313d4e0a12a2daf850 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/pqlWNihgdjI' markdown: 'https://liquidgold.cc/watch/pqlWNihgdjI.md' llms: 'https://liquidgold.cc/watch/pqlWNihgdjI/llms.txt' parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T04:28:40.101Z' language: null children: [] videoId: pqlWNihgdjI durationSeconds: 1257 publishedAt: '2026-08-28T16:30:19.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 100 endSeconds: 156 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=100' heldReason: rights - ordinal: 1 text: null startSeconds: 170 endSeconds: 228 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=170' heldReason: rights - ordinal: 2 text: null startSeconds: 239 endSeconds: 293 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=239' heldReason: rights - ordinal: 3 text: null startSeconds: 373 endSeconds: 429 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=373' heldReason: rights - ordinal: 4 text: null startSeconds: 429 endSeconds: 441 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=429' heldReason: rights - ordinal: 5 text: null startSeconds: 505 endSeconds: 562 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=505' heldReason: rights - ordinal: 6 text: null startSeconds: 573 endSeconds: 638 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=573' heldReason: rights - ordinal: 7 text: null startSeconds: 648 endSeconds: 776 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=648' heldReason: rights - ordinal: 8 text: null startSeconds: 776 endSeconds: 787 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=776' heldReason: rights - ordinal: 9 text: null startSeconds: 787 endSeconds: 844 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=787' heldReason: rights - ordinal: 10 text: null startSeconds: 856 endSeconds: 910 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=856' heldReason: rights - ordinal: 11 text: null startSeconds: 921 endSeconds: 975 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=921' heldReason: rights - ordinal: 12 text: null startSeconds: 986 endSeconds: 1053 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=986' heldReason: rights - ordinal: 13 text: null startSeconds: 1065 endSeconds: 1189 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=1065' heldReason: rights - ordinal: 14 text: null startSeconds: 1189 endSeconds: 1200 watch: 'https://liquidgold.cc/watch/pqlWNihgdjI?t=1189' heldReason: rights --- # From AI-Assisted to AI-Native: Building a Frontier Development Team — Clare Liguori, AWS Amazon watched 50 ordinary teams for the better part of a year, teams with normal seniority mixes working in existing codebases. Ninety percent of them used the same coding assistant. Half saw under 3x improvement in deployment velocity to production. The other half saw a median of 4.5x and sometimes past 10x. The tool was not the variable. The teams that pulled ahead had deliberately changed how they worked, and the rest had sprinkled agents on top of the way they already worked. Clare Liguori calls the result frontier development, and defines it by behavior: engineers writing one to two percent of their own code, agents running for hours without interruption, several running at once. Her five habits are mostly unglamorous. Write down what lives in your head, then keep pruning it as models improve so old workarounds stop bloating context. Expect to get slower first, because brownfield codebases need real work before agents succeed in them, which for some teams meant better error messages, new tools, or restructuring outright. Feed agents rather than babysitting them, since a running conversation keeps you in the loop and makes parallelism impossible. Fix the intent in a document before arguing with generated code. Shift testing left, with local deterministic mocks, so the feedback loop is fast enough for an agent to self correct. The new bottleneck is decision speed. Speaker info: - https://x.com/clare_liguori - https://www.linkedin.com/in/clareliguori/ - https://clare.dev/ Timestamps: 0:00 - Four phases, and only 10% to 20% felt 1:22 - What the pilots actually measured 2:34 - Thirty people for 18 months, or six people for 76 days 3:43 - Why that team was not reproducible 4:51 - A ten day sprint, and its asterisks 5:57 - Fifty ordinary teams, and the real split 7:04 - Same tools, different ways of working 8:14 - Habit one: invest in agent context 9:21 - Pruning context as models improve 10:31 - Habit two: slow down to speed up 12:50 - Feeding agents instead of babysitting them 13:58 - Making intent explicit before writing code 15:09 - Shifting testing left with local mocks 16:15 - Burnout, FOMO and cognitive load 17:23 - What organizations have to change 19:41 - When decision speed becomes the bottleneck --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/pqlWNihgdjI-youtube-ca313d4e0a12a2daf850 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/pqlWNihgdjI · 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.