--- title: "Software Factories" category: "topics" sourceLabels: ["Official schedule", "Public YouTube livestream transcript", "Local slide OCR"] --- # Software Factories ## Overview Software factories are coordinated systems for turning ideas, issues, designs, tests, agents, and human review into shipped software. In an AI-native version, multiple agents may handle planning, coding, testing, review, documentation, and release support under explicit workflow rules. ## Conference Context The idea comes from assembly-line metaphors in software engineering, CI/CD, DevOps, internal developer platforms, and automated code generation. AI agents make the factory metaphor more literal because parts of the SDLC can be delegated to tool-using systems. ## How This Theme Evolved - **World's Fair 2024 (local comparison fixture):** Coding agents sat inside a broader code-generation and AI-engineering discipline. - **Miami 2026 (public comparison wiki):** The focus narrowed to developer workflow, agent-ready interfaces, runtimes, IDEs, context, and quality gates. - **World's Fair 2025 (local comparison fixture):** The comparison corpus emphasized shipping, evaluating, securing, and reviewing production coding agents. - **World's Fair 2026 (current event synthesis backed by linked local evidence):** The linked conference graph frames coding agents as software-factory components governed by eval gates, context systems, and execution boundaries. **Confidence:** medium-high. **Boundary:** Earlier event wikis are comparison context only. They are not primary evidence for World's Fair 2026 claims, and no local fixture is represented as a public live site. **Comparison source:** [[aie-wiki-generation-delta]]. ## Significance A single coding assistant is useful, but organizations need repeatability, governance, and quality gates. Software factories focus on the whole production system: intake, context, implementation, validation, review, deployment, and learning. ## Why This Matters Now The unit of engineering is shifting from an isolated assistant interaction to a repeatable production system that delegates, verifies, and records software work. **WF26 evidence gate:** this section was emitted only because the page links to configured local evidence. Relevant configured evidence: [[2026-06-29-nnenna-ndukwe-how-to-build-quality-gates-into-agentic-coding-workflows]], [[2026-06-29-uday-kiran-medisetty-agentic-sdlc-at-uber-building-blocks-for-uber-s-software-factory]], [[2026-06-30-suraj-gupta-warp-building-self-improving-agent-software-factories]]. **Confidence:** medium-high. Comparison history is context; linked WF26 pages remain the evidence for current-event claims. ## Applied Use Model the workflow as stages with inputs, outputs, owners, and acceptance checks. Give agents scoped roles, shared artifacts, test gates, traceability, and rollback paths. Measure cycle time, defect rate, review burden, and production outcomes. They fit engineering organizations, platform teams, internal tools groups, migration projects, and product teams with repeatable implementation patterns. Use a software-factory approach when many similar tasks flow through the same path or when agent work needs governance. Avoid overbuilding it for occasional one-off tasks. Model the workflow as stages with inputs, outputs, owners, and acceptance checks. Give agents scoped roles, shared artifacts, test gates, traceability, and rollback paths. Measure cycle time, defect rate, review burden, and production outcomes. They fit engineering organizations, platform teams, internal tools groups, migration projects, and product teams with repeatable implementation patterns. Use a software-factory approach when many similar tasks flow through the same path or when agent work needs governance. Avoid overbuilding it for occasional one-off tasks. Model the workflow as stages with inputs, outputs, owners, and acceptance checks. Give agents scoped roles, shared artifacts, test gates, traceability, and rollback paths. Measure cycle time, defect rate, review burden, and production outcomes. They fit engineering organizations, platform teams, internal tools groups, migration projects, and product teams with repeatable implementation patterns. Use a software-factory approach when many similar tasks flow through the same path or when agent work needs governance. Avoid overbuilding it for occasional one-off tasks. Model the workflow as stages with inputs, outputs, owners, and acceptance checks. Give agents scoped roles, shared artifacts, test gates, traceability, and rollback paths. Measure cycle time, defect rate, review burden, and production outcomes. They fit engineering organizations, platform teams, internal tools groups, migration projects, and product teams with repeatable implementation patterns. Use a software-factory approach when many similar tasks flow through the same path or when agent work needs governance. Avoid overbuilding it for occasional one-off tasks. Model the workflow as stages with inputs, outputs, owners, and acceptance checks. Give agents scoped roles, shared artifacts, test gates, traceability, and rollback paths. Measure cycle time, defect rate, review burden, and production outcomes. They fit engineering organizations, platform teams, internal tools groups, migration projects, and product teams with repeatable implementation patterns. Use a software-factory approach when many similar tasks flow through the same path or when agent work needs governance. Avoid overbuilding it for occasional one-off tasks. Model the workflow as stages with inputs, outputs, owners, and acceptance checks. Give agents scoped roles, shared artifacts, test gates, traceability, and rollback paths. Measure cycle time, defect rate, review burden, and production outcomes. They fit engineering organizations, platform teams, internal tools groups, migration projects, and product teams with repeatable implementation patterns. Use a software-factory approach when many similar tasks flow through the same path or when agent work needs governance. Avoid overbuilding it for occasional one-off tasks. ## Practical Lesson Evaluate the complete agent loop: task definition, context assembly, tool permissions, sandbox execution, verification, review, and provenance. Model capability alone is not the system boundary. **Confidence:** medium-high. Treat this as synthesis derived from the linked evidence graph, not as an official schedule claim. ## Connections - [[2026-07-01-session-the-software-factory]] — The Software Factory; speaker TBD (Day 4 — Session Day 3 · 2:50pm-3:10pm · Expo Stage 4 SE; official schedule) - [[2026-06-29-shane-wolf-the-best-sdlc-is-the-one-you-build-yourself-why-orchestration-changes-everything]] — The best SDLC is the one you build yourself: Why orchestration changes everything; [[shane-wolf|Shane Wolf]], [[andrei-bocan|Andrei Bocan]] (Day 1 — Workshop Day · 9:00am-11:00am · Workshops Day 1; official schedule) - [[2026-06-29-uday-kiran-medisetty-agentic-sdlc-at-uber-building-blocks-for-uber-s-software-factory]] — Agentic SDLC at Uber: Building Blocks for Uber's Software Factory; [[uday-kiran-medisetty|Uday Kiran Medisetty]], [[adam-huda|Adam Huda]] (Day 2 — Session Day 1 · 11:40am-12:00pm · AI-Native Enterprises; official schedule) - [[2026-07-01-ryan-cooke-no-that-s-not-a-software-factory]] — No, That's Not a Software Factory; [[ryan-cooke|Ryan Cooke]] (Day 4 — Session Day 3 · 10:45am-11:05am · Expo Stage 3; official schedule) - [[2026-06-29-tereza-t-kov-rise-of-the-software-factory]] — Rise of the Software Factory; [[tereza-t-kov|Tereza Tížková]] (Day 2 — Session Day 1 · 11:10am-11:30am · Software Factories; official schedule) - [[2026-06-29-eno-reyes-how-forward-deployed-engineering-is-done-at-factory]] — How Forward Deployed Engineering is done at Factory; [[eno-reyes|Eno Reyes]] (Day 2 — Session Day 1 · 10:45am-11:05am · Forward Deployed Engineering; official schedule) - [[2026-06-29-kyle-mistele-loop-engineering-from-first-principles]] — Loop Engineering from first principles; [[kyle-mistele|Kyle Mistele]] (Day 2 — Session Day 1 · 3:45pm-4:05pm · Software Factories; official schedule) - [[2026-06-30-christopher-manning-building-the-simulation-infrastructure-for-practical-world-model-use]] — Building the simulation infrastructure for practical world model use; [[christopher-manning|Christopher Manning]] (Day 3 — Session Day 2 · 10:45am-11:05am · Robotics & World Models; official schedule) - [[2026-06-30-christopher-manning-building-the-simulation-infrastructure-for-practical-world-model-use-part-2]] — Building the simulation infrastructure for practical world model use (Part 2); [[christopher-manning|Christopher Manning]] (Day 3 — Session Day 2 · 11:10am-11:30am · Robotics & World Models; official schedule) - [[2026-06-29-nnenna-ndukwe-how-to-build-quality-gates-into-agentic-coding-workflows]] — How to Build Quality Gates into Agentic Coding Workflows; [[nnenna-ndukwe|Nnenna Ndukwe]] (Day 1 — Workshop Day · 11:05am-12:05pm · Workshops Day 1; official schedule) - [[2026-06-29-joel-hooks-the-art-and-science-of-loopcraft-with-pi-and-friends]] — The Art and Science of Loopcraft with Pi (and friends); [[joel-hooks|Joel Hooks]] (Day 1 — Workshop Day · 4:30pm-5:30pm · Workshops Day 1; official schedule) - [[2026-06-30-suraj-gupta-warp-building-self-improving-agent-software-factories]] — Warp: Building Self-Improving Agent Software Factories; [[suraj-gupta|Suraj Gupta]] (Day 3 — Session Day 2 · 1:55pm-2:15pm · Expo Stage 3 SW; official schedule) - [[christopher-manning|Christopher Manning]] - [[shane-wolf|Shane Wolf]] - [[andrei-bocan|Andrei Bocan]] - [[uday-kiran-medisetty|Uday Kiran Medisetty]] - [[adam-huda|Adam Huda]] - [[ryan-cooke|Ryan Cooke]] - [[tereza-t-kov|Tereza Tížková]] - [[eno-reyes|Eno Reyes]] - [[kyle-mistele|Kyle Mistele]] - [[nnenna-ndukwe|Nnenna Ndukwe]] - [[joel-hooks|Joel Hooks]] - [[suraj-gupta|Suraj Gupta]] - [[atlassian|Atlassian]] - [[uber|Uber]] - [[factory|Factory]] - [[moonlake-ai|Moonlake AI]] - [[workos|WorkOS]] - [[humanlayer|HumanLayer]] - [[qodo-ai|Qodo AI]] - [[badass-dev-egghead-io|badass.dev / egghead.io]] - [[warp|Warp]] - [[2026-07-01-mike-chambers-harness-engineering-building-the-production-cage-for-powerful-domain-agents]] — Harness Engineering: Building the Production Cage for Powerful Domain Agents; [[mike-chambers|Mike Chambers]] (Day 4 — Session Day 3 · 12:05pm-12:25pm · Harness Engineering; related YouTube resource; via [[youtube-qdZzND79mcg]]) - [[2026-07-01-dru-knox-harness-engineering-the-new-core-skill-for-agentic-developers]] — Harness Engineering: The New Core Skill for Agentic Developers; [[dru-knox|Dru Knox]] (Day 4 — Session Day 3 · 2:50pm-3:10pm · Expo Stage 1 NE; related YouTube resource; via [[youtube-qdZzND79mcg]]) - [[mike-chambers|Mike Chambers]] - [[dru-knox|Dru Knox]] - [[amazon-web-services-aws|Amazon Web Services (AWS)]] - [[tessl|Tessl]] ## Evidence Graph ### Transcript-backed resources - [[youtube-qdZzND79mcg]] — Beyond the Harness: A Journey Towards Adaptative Engineering - Rajiv Chandegra, Annicha Labs - [[youtube-pmoDeA3RBZY]] — Dark Factory: OpenClaw Ships Faster Than You Can Read the Diff — Vincent Koc, OpenClaw - [[youtube-xUnRQ9vLXxo]] — What do we build now? — @t3dotgg ### Transcript-backed resources This evidence graph consolidates scheduled talks, linked videos, transcripts, and slide-derived material connected to this topic. ### Linked Sessions - [[2026-07-01-session-the-software-factory|The Software Factory]] - [[2026-06-29-shane-wolf-the-best-sdlc-is-the-one-you-build-yourself-why-orchestration-changes-everything|The best SDLC is the one you build yourself: Why orchestration changes everything]] - [[2026-06-29-uday-kiran-medisetty-agentic-sdlc-at-uber-building-blocks-for-uber-s-software-factory|Agentic SDLC at Uber: Building Blocks for Uber's Software Factory]] - [[2026-07-01-ryan-cooke-no-that-s-not-a-software-factory|No, That's Not a Software Factory]] - [[2026-06-29-tereza-t-kov-rise-of-the-software-factory|Rise of the Software Factory]] - [[2026-06-29-eno-reyes-how-forward-deployed-engineering-is-done-at-factory|How Forward Deployed Engineering is done at Factory]] - [[2026-07-01-mike-chambers-harness-engineering-building-the-production-cage-for-powerful-domain-agents|Harness Engineering: Building the Production Cage for Powerful Domain Agents]] - [[2026-07-01-dru-knox-harness-engineering-the-new-core-skill-for-agentic-developers|Harness Engineering: The New Core Skill for Agentic Developers]] - [[2026-06-29-kyle-mistele-loop-engineering-from-first-principles|Loop Engineering from first principles]] - [[2026-06-30-christopher-manning-building-the-simulation-infrastructure-for-practical-world-model-use|Building the simulation infrastructure for practical world model use]] ### Media Signals - `youtube-ShuJ_CN6zr4` — 2 slide-derived text signals - Slide-derived themes for `youtube-ShuJ_CN6zr4`: autonomous, engineering, systems, ready. - Evidence links for `youtube-ShuJ_CN6zr4`: [[youtube-ShuJ_CN6zr4]], [[youtube-ShuJ_CN6zr4-slides]], [[youtube-ShuJ_CN6zr4-dense-slides]], [[youtube-ShuJ_CN6zr4-reconstructed-slides]] - `youtube-HT4l0DeP69I` — 10 slide-derived text signals - Slide-derived themes for `youtube-HT4l0DeP69I`: mike, chambers, advocate, engineering, generative, real, world, applications. - Evidence links for `youtube-HT4l0DeP69I`: [[youtube-HT4l0DeP69I]], [[youtube-HT4l0DeP69I-slides]], [[youtube-HT4l0DeP69I-dense-slides]], [[youtube-HT4l0DeP69I-reconstructed-slides]] - `youtube-I2cbIws9j10` — 91,792 transcript words; 7 slide-derived text signals - Transcript signals for `youtube-I2cbIws9j10`: code, model, back, system, well, first, today, even. - Slide-derived themes for `youtube-I2cbIws9j10`: context, window, selects, response, facts, retry, coerce, rollback. - Evidence links for `youtube-I2cbIws9j10`: [[youtube-I2cbIws9j10]], [[youtube-I2cbIws9j10-transcript]], [[youtube-I2cbIws9j10-slides]], [[youtube-I2cbIws9j10-dense-slides]] ## Source Coverage This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed. | Evidence type | Count | Review note | | --- | ---: | --- | | other | 29 | Related pages outside the main evidence categories. | | resources | 7 | Video/resource pages; check source status before treating as primary event evidence. | | slides | 9 | OCR or reconstructed slide evidence; mark claims as OCR-derived unless image-reviewed. | | talks | 14 | Official schedule pages; use for titles, speakers, tracks, and stated talk framing. | | transcripts | 1 | Transcript markdown; check session matching and caption quality. | ### Talks - [[2026-07-01-session-the-software-factory]] - [[2026-06-29-shane-wolf-the-best-sdlc-is-the-one-you-build-yourself-why-orchestration-changes-everything]] - [[2026-06-29-uday-kiran-medisetty-agentic-sdlc-at-uber-building-blocks-for-uber-s-software-factory]] - [[2026-07-01-ryan-cooke-no-that-s-not-a-software-factory]] - [[2026-06-29-tereza-t-kov-rise-of-the-software-factory]] - [[2026-06-29-eno-reyes-how-forward-deployed-engineering-is-done-at-factory]] ### Resources - [[youtube-qdZzND79mcg]] - [[youtube-pmoDeA3RBZY]] - [[youtube-xUnRQ9vLXxo]] - [[youtube-htM02KMNZnk]] - [[youtube-ShuJ_CN6zr4]] - [[youtube-HT4l0DeP69I]] ### Slides - [[youtube-htM02KMNZnk-slides]] - [[youtube-ShuJ_CN6zr4-slides]] - [[youtube-ShuJ_CN6zr4-dense-slides]] - [[youtube-ShuJ_CN6zr4-reconstructed-slides]] - [[youtube-HT4l0DeP69I-slides]] - [[youtube-HT4l0DeP69I-dense-slides]] ### Transcripts - [[youtube-I2cbIws9j10-transcript]] This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed. ### Talks ### Resources - [[youtube-I2cbIws9j10]] ### Slides - [[youtube-HT4l0DeP69I-reconstructed-slides]] ### Transcripts This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed. ### Talks ### Resources ### Slides ### Transcripts This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed. | resources | 8 | Video/resource pages; check source status before treating as primary event evidence. | ### Talks - [[2026-06-29-nnenna-ndukwe-how-to-build-quality-gates-into-agentic-coding-workflows]] - [[2026-06-30-suraj-gupta-warp-building-self-improving-agent-software-factories]] ### Resources - [[aie-wiki-generation-delta]] ### Slides ### Transcripts This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed. ### Talks ### Resources ### Slides ### Transcripts This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed. ### Talks ### Resources ### Slides ### Transcripts This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed. ### Talks ### Resources ### Slides ### Transcripts This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed. ### Talks ### Resources ### Slides ### Transcripts This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed. ### Talks ### Resources ### Slides ### Transcripts ## Active Use Cases - Agent-assisted feature delivery pipelines. - Automated maintenance, migration, and dependency-update programs. - Multi-agent planning, coding, testing, and review workflows. - Internal developer platforms with AI-native task orchestration. ## Livestream Source - [[youtube-htM02KMNZnk]] — official WF2026 Software Factories and keynote livestream. - [[youtube-htM02KMNZnk-slides]] — extracted slide/OCR deck for the livestream. ## Neighboring Subjects - [[coding-agents]] - [[agent-security]] - [[agent-evaluations]] - [[ai-sandboxes]]