# Software factories A pack of 8 talks from the AI Engineer YouTube channel, in the order to watch them. 3h 33m of video. Page: https://aietalks.com/packs/software-factories A software factory can build quickly and still fail if nobody decides what is worth building or retains enough understanding to support it after release. HumanLayer's lights-off experiment supplies the failure case: an outage forced the team back into code it had stopped reading. Repository preparation and Uber's shared context show what must exist before parallel agents can work safely. Continuous validation and a two-engineer case study then move review closer to intent and observable behavior. PostHog pushes the starting point further upstream, turning product errors and session replays into researched work rather than blind fixes. Stored lessons make the next feature cheaper, but one job stays human: judge the evidence, accept the risk and own what reaches production. ## This pack is for you if - Your agents create pull requests faster than the team can decide whether the underlying work was worth doing. - You want product evidence, planning, implementation and testing to form one system rather than four handoffs. - Your organization is removing old engineering ceremonies but has not decided where judgment and accountability now belong. ## The talks, in order ### 1. Harness Engineering is Not Enough: Why Software Factories Fail Dex Horthy, HumanLayer | 19:18 | AI Engineer World's Fair 2026 Video: https://www.youtube.com/watch?v=Ib5GBkD555M Summary: https://aietalks.com/talks/harness-engineering-is-not-enough-why-software-factories-fail.md Why first: Horthy starts with the failure case. His lights-off factory produced working code faster than the team could preserve its understanding of the system, and an outage sent them back into code they had stopped reading. Zakariasson's readiness checklist is an answer to that mistake. ### 2. Building your own software factory Eric Zakariasson, Cursor | 1:23:37 | AI Engineer Europe 2026 Video: https://www.youtube.com/watch?v=rnDm57Py54A Summary: https://aietalks.com/talks/building-your-own-software-factory.md Why second: Horthy shows what unchecked output does to a codebase. Zakariasson works through the prerequisites: local patterns, automated tests, isolated environments and shared rules, with people keeping the architectural and security decisions that carry the most risk. ### 3. Agentic SDLC at Uber Uday Kiran Medisetty & Adam Huda, Uber | 18:26 | AI Engineer World's Fair 2026 Video: https://www.youtube.com/watch?v=17-YSUHo6Lk Summary: https://aietalks.com/talks/agentic-sdlc-at-uber.md Why here: Zakariasson describes the pieces one team needs. Medisetty and Huda show them operating at company scale. Uber centralizes identity, privacy and tool access, then carries product research and designs through implementation, visual checks and a draft pull request. ### 4. CI/CD Is Dead, Agents Need Continuous Compute and Computers Hugo Santos, Namespace & Madison Faulkner, NEA | 18:37 | AI Engineer Europe 2026 Video: https://www.youtube.com/watch?v=VktrqzQgytY Summary: https://aietalks.com/talks/ci-cd-is-dead-agents-need-continuous-compute-and-computers.md Why here: Uber moves validation into the agent's inner loop but still stops at a draft pull request. Santos and Faulkner redesign the path for much higher throughput: begin with intent and a plan, validate in a stateful environment, reconcile competing changes, then ask a person to review the outcome. ### 5. Agents Don't Do Standups: Building the Post-Engineer Engineering Org Mike Spitz, PFF | 17:50 | AI Engineer Europe 2026 Video: https://www.youtube.com/watch?v=VMemhtlsoNk Summary: https://aietalks.com/talks/agents-dont-do-standups-building-the-post-engineer-engineering-org.md Why here: Santos and Faulkner change the delivery pipeline. Spitz changes the organization around it. Specs become design documents, tickets and pull requests; agents take deterministic implementation and style checks, while people keep product feel, system design and security. ### 6. Self Driving Products: Product Signals to Pull Requests Joshua Snyder, PostHog | 15:39 | AI Engineer Europe 2026 Video: https://www.youtube.com/watch?v=zMiSRliEzv4 Summary: https://aietalks.com/talks/self-driving-products-product-signals-to-pull-requests.md Why here: Spitz begins from an approved specification. Snyder starts earlier, with errors, messages and session replays coming out of the product. His system gathers evidence before it asks a coding agent to act, and sends an underspecified problem back to a person instead of inventing a fix. ### 7. The Era of Compound Engineering Kieran Klaassen, Every/Cora | 20:38 | AI Engineer World's Fair 2026 Video: https://www.youtube.com/watch?v=_ehJyfHg1Vk Summary: https://aietalks.com/talks/the-era-of-compound-engineering.md Why here: Snyder wants later pull requests to learn from rejected fixes and production outcomes. Klaassen makes that habit the operating model. He spends as much effort storing the lesson from a shipped feature as he spends shipping it, so the next job begins with more of the team's judgment. ### 8. The engineer of the future is the person who is able to choose what is worth doing. Addy Osmani | 18:26 | AI Engineer World's Fair 2026 Video: https://www.youtube.com/watch?v=n97BCfyFIvw Summary: https://aietalks.com/talks/the-engineer-of-the-future-is-the-person-who-is-able-to-choose-what-is-worth.md Why last: Klaassen describes a factory that remembers more after every feature. Osmani supplies its limit. More parallel agents create more routing, merging and verification decisions, while human attention stays finite. Someone must still judge the evidence, accept the risk and own what reaches production. ## Editor's note Horthy's factory lost track of what its own code meant. Snyder needs real production cases, and Klaassen improves his process by studying what each run got wrong. Kitaru records those runs so a team can replay selected cases after changing a model, tool or workflow and check the new behavior before the factory sends it back into production. Written by the AIE Talks editors (the Kitaru team), not by any of the speakers.