--- schema: 1 type: video title: >- Harness Engineering: Building the Production Cage for Powerful Domain Agents — Mike Chambers, AWS description: >- Mike Chambers puts a dictionary entry on screen: a harness is a set of straps and fastenings used to control an animal. Swap animal for model and the definition holds. His working version is subtraction. Take an agent, remove the model, and everything left over is the harness. Chambers is a senior AI specialist developer advocate at AWS, and he splits the field in two. There are agents we use, coding assistants and productivity tools, where the harness is memory, skills, tools, MCP servers, and the standards your team deploys to everyone. Then there are agents we build, and those need far more: loop management, scaling, payments, identity, runtime, context management, and the item he lists last while insisting it should come first, observability and evaluation. Writing all of that into one container and scaling it is the wrong answer at thousands of users, because each piece needs to scale on its own. That separation is what he means by harness engineering. The rest is live coding. He walks up from a bare SDK agent with a calculator tool, to one with a session manager that rehydrates conversation history between invocations, to a deployment where memory runs as its own managed infrastructure beside the agent rather than inside it. Along the way he argues against what he calls slop ops, the agent equivalent of clicking around a console, where an agent spins up cloud resources directly instead of writing infrastructure as code you still own. The reveal is saved for the end: one CLI option he skipped earlier turns the whole thing into a JSON file naming a model and a system prompt, with no agent code at all. Speaker info: - https://blog.mikegchambers.com Timestamps: 0:00 - Who he is and how he got here 2:45 - Two kinds of agents: the ones we use, the ones we build 4:24 - Defining a harness by subtraction 5:16 - The harness around a coding assistant 6:07 - No more slop ops 6:57 - What an agent you build needs instead 8:38 - Live coding: a bare agent with tools 10:16 - Adding a session manager and memory 12:50 - Deploying with the AgentCore CLI 15:18 - Scaling out without writing multi tenant code 16:59 - Talking to the running agent, local and deployed 18:40 - The harness option he skipped --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/gxVZ_1tuuq4-harness-engineering-building-production-cage 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/harness-engineering-building-the-production-cage-fo-f7f8b2854974 markdown: >- https://liquidgold.cc/channel/aidotengineer/video/harness-engineering-building-the-production-cage-fo-f7f8b2854974.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T03:43:04.483Z' language: null children: [] videoId: gxVZ_1tuuq4 durationSeconds: 1246 publishedAt: '2026-09-14T14:30:38.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 26 endSeconds: 172 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=26' heldReason: rights - ordinal: 1 text: null startSeconds: 182 endSeconds: 266 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=182' heldReason: rights - ordinal: 2 text: null startSeconds: 182 endSeconds: 266 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=182' heldReason: rights - ordinal: 3 text: null startSeconds: 276 endSeconds: 325 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=276' heldReason: rights - ordinal: 4 text: null startSeconds: 325 endSeconds: 336 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=325' heldReason: rights - ordinal: 5 text: null startSeconds: 380 endSeconds: 425 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=380' heldReason: rights - ordinal: 6 text: null startSeconds: 436 endSeconds: 525 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=436' heldReason: rights - ordinal: 7 text: null startSeconds: 537 endSeconds: 627 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=537' heldReason: rights - ordinal: 8 text: null startSeconds: 627 endSeconds: 637 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=627' heldReason: rights - ordinal: 9 text: null startSeconds: 637 endSeconds: 772 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=637' heldReason: rights - ordinal: 10 text: null startSeconds: 772 endSeconds: 782 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=772' heldReason: rights - ordinal: 11 text: null startSeconds: 782 endSeconds: 924 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=782' heldReason: rights - ordinal: 12 text: null startSeconds: 935 endSeconds: 1019 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=935' heldReason: rights - ordinal: 13 text: null startSeconds: 1019 endSeconds: 1029 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=1019' heldReason: rights - ordinal: 14 text: null startSeconds: 1129 endSeconds: 1140 watch: 'https://liquidgold.cc/watch/gxVZ_1tuuq4?t=1129' heldReason: rights --- # Harness Engineering: Building the Production Cage for Powerful Domain Agents — Mike Chambers, AWS Mike Chambers puts a dictionary entry on screen: a harness is a set of straps and fastenings used to control an animal. Swap animal for model and the definition holds. His working version is subtraction. Take an agent, remove the model, and everything left over is the harness. Chambers is a senior AI specialist developer advocate at AWS, and he splits the field in two. There are agents we use, coding assistants and productivity tools, where the harness is memory, skills, tools, MCP servers, and the standards your team deploys to everyone. Then there are agents we build, and those need far more: loop management, scaling, payments, identity, runtime, context management, and the item he lists last while insisting it should come first, observability and evaluation. Writing all of that into one container and scaling it is the wrong answer at thousands of users, because each piece needs to scale on its own. That separation is what he means by harness engineering. The rest is live coding. He walks up from a bare SDK agent with a calculator tool, to one with a session manager that rehydrates conversation history between invocations, to a deployment where memory runs as its own managed infrastructure beside the agent rather than inside it. Along the way he argues against what he calls slop ops, the agent equivalent of clicking around a console, where an agent spins up cloud resources directly instead of writing infrastructure as code you still own. The reveal is saved for the end: one CLI option he skipped earlier turns the whole thing into a JSON file naming a model and a system prompt, with no agent code at all. Speaker info: - https://blog.mikegchambers.com Timestamps: 0:00 - Who he is and how he got here 2:45 - Two kinds of agents: the ones we use, the ones we build 4:24 - Defining a harness by subtraction 5:16 - The harness around a coding assistant 6:07 - No more slop ops 6:57 - What an agent you build needs instead 8:38 - Live coding: a bare agent with tools 10:16 - Adding a session manager and memory 12:50 - Deploying with the AgentCore CLI 15:18 - Scaling out without writing multi tenant code 16:59 - Talking to the running agent, local and deployed 18:40 - The harness option he skipped --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/gxVZ_1tuuq4-harness-engineering-building-production-cage 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/harness-engineering-building-the-production-cage-fo-f7f8b2854974 · 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.