Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Architecture docs die the moment code ships. Code-to-Blueprint sync now catches the drift. Every merged PR triggers an agent in Software Factory to compare the code to the architecture and leaves comments where they disagree. Learn more about Software Factory:

8090

10,246 subscribers

122,982 views • 4 months ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

2 Comments

Faisal Feroz | Fractional CTO (AI + Modernization)4 months ago

Doc-code drift is the silent killer of modernization. Living ADRs + AI diff-review is the right pattern.

sam4 months ago

Architecture drift is the symptom. The root cause is that specs and code live in different systems with no feedback loop. When implementation deviates from the spec, the deviation feeds back into the context files. The spec does not drift because it learns from the code.

Related Videos

This is what your SDLC looks like today: requirements in one doc, architecture in someone's head, code in Cursor, docs gone stale. Watch Software Factory connect the chain so the spec and the shipped code stop drifting apart.

This is what your SDLC looks like today: requirements in one doc, architecture in someone's head, code in Cursor, docs gone stale. Watch Software Factory connect the chain so the spec and the shipped code stop drifting apart.

8090

108,977 views • 3 months ago

Factory for Slack Code is now in beta for select users. Bring a software task into the channel, collaborate with your team, and Factory gets to work. The result comes back where the conversation started.

Factory for Slack Code is now in beta for select users. Bring a software task into the channel, collaborate with your team, and Factory gets to work. The result comes back where the conversation started.

Factory

17,407 views • 2 days ago

I asked Simon Willison what the next leap in AI software engineering is likely to be. He explained the "dark factory" pattern where teams don't write any code or even look at their code.

I asked Simon Willison what the next leap in AI software engineering is likely to be. He explained the "dark factory" pattern where teams don't write any code or even look at their code.

Lenny Rachitsky

70,196 views • 5 months ago

Common Linear workflow we have internally: from Slack message to merged code in minutes. User asked about MCP team docs support, Linear agent checked the code to verify if it's true then started coding session to add it. Code was then reviewed, improve and merged through Diffs.

Common Linear workflow we have internally: from Slack message to merged code in minutes. User asked about MCP team docs support, Linear agent checked the code to verify if it's true then started coding session to add it. Code was then reviewed, improve and merged through Diffs.

Karri Saarinen

31,732 views • 3 months ago

Enterprises today are running single-player AI in a multiplayer business. One engineer plus one IDE plus one agent ships lines of code faster. It does not ship coordinated software. Two desks over, another engineer's agent is shipping a change that contradicts last quarter's architecture decision. Neither agent knows. Compliance assembles the audit trail from screenshots after the fact. We built Software Factory to turn that into a team. Requirements captures the business intent in plain English. Blueprints maps the architecture as it actually exists. Work Orders translates that into structured tasks agents execute through MCP in Cursor, VS Code, or Claude Code. Tests validates the deployed code against the Requirement that started it. The Knowledge Graph wires it all together. Your engineers conduct the agents. The agents share state. The audit trail is part of the build, not a quarterly forensics exercise. EY's deployment: +70% productivity, 95%+ automated test coverage, months of roadmap compressed to days.

Enterprises today are running single-player AI in a multiplayer business. One engineer plus one IDE plus one agent ships lines of code faster. It does not ship coordinated software. Two desks over, another engineer's agent is shipping a change that contradicts last quarter's architecture decision. Neither agent knows. Compliance assembles the audit trail from screenshots after the fact. We built Software Factory to turn that into a team. Requirements captures the business intent in plain English. Blueprints maps the architecture as it actually exists. Work Orders translates that into structured tasks agents execute through MCP in Cursor, VS Code, or Claude Code. Tests validates the deployed code against the Requirement that started it. The Knowledge Graph wires it all together. Your engineers conduct the agents. The agents share state. The audit trail is part of the build, not a quarterly forensics exercise. EY's deployment: +70% productivity, 95%+ automated test coverage, months of roadmap compressed to days.

8090

75,406 views • 3 months ago

The software factory is already here. We're seeing bots write code, bots review it, and humans reduced to dispatching the next tool in the chain. Using 500k+ PRs from Code Review Bench, we looked at one question: can the human leave the loop yet?

The software factory is already here. We're seeing bots write code, bots review it, and humans reduced to dispatching the next tool in the chain. Using 500k+ PRs from Code Review Bench, we looked at one question: can the human leave the loop yet?

Martian

50,744 views • 5 months ago

everyone wants to sell you a software factory, but as David Crawshaw (founder tailscale, would probably say, these things need to be open systems I went deep with Vaibhav Gupta on the future of software factory architecture, and the tradeoffs between turnkey stacks and owning+composing the system full video here:

everyone wants to sell you a software factory, but as David Crawshaw (founder tailscale, would probably say, these things need to be open systems I went deep with Vaibhav Gupta on the future of software factory architecture, and the tradeoffs between turnkey stacks and owning+composing the system full video here:

dex

39,976 views • 21 days ago

🌐 The integrated browser in Visual Studio Code now has pinch-to-zoom and zoom shortcuts on macOS, better agent tool descriptions, and more updates. Learn more →

🌐 The integrated browser in Visual Studio Code now has pinch-to-zoom and zoom shortcuts on macOS, better agent tool descriptions, and more updates. Learn more →

Visual Studio Code

56,203 views • 5 months ago

What is the “dark factory” that there’s so much talk about, in relation to software factories? dex, founder of HumanLayer explains: “You can imagine a car factory where it’s all robots building the cars, and they don’t have lights. There’s no humans. You walk in there, there’s no lights, there’s not even light switches. And in software, you can have mini loops that are dark in your thing: hey, if the code review agent comes back with a problem, you loop that back to the builder agent, it fixes it and comes back, and that’s a dark factory. You don’t need a human loop for that. But the full dark factory where you don’t read any code: yeah, it’s a good way to maximize your token utilization. If your belief is that ‘my job is to extract as much intelligence out of the machine as I can’, then you go token harder. And my take is token smarter: how do I get as much value out of AI as I can without having to turn the lights off, while still maintaining control and taste and judgment and understanding the system architecture?”

What is the “dark factory” that there’s so much talk about, in relation to software factories? dex, founder of HumanLayer explains: “You can imagine a car factory where it’s all robots building the cars, and they don’t have lights. There’s no humans. You walk in there, there’s no lights, there’s not even light switches. And in software, you can have mini loops that are dark in your thing: hey, if the code review agent comes back with a problem, you loop that back to the builder agent, it fixes it and comes back, and that’s a dark factory. You don’t need a human loop for that. But the full dark factory where you don’t read any code: yeah, it’s a good way to maximize your token utilization. If your belief is that ‘my job is to extract as much intelligence out of the machine as I can’, then you go token harder. And my take is token smarter: how do I get as much value out of AI as I can without having to turn the lights off, while still maintaining control and taste and judgment and understanding the system architecture?”

The Pragmatic Engineer

37,636 views • 2 months ago

$VANTIS is now available on Robinhood Crypto via Virtuals Protocol. Official CA: 0xB6d695d5fbcEbD837f6b9f214c9BeeE8bA90762B Vantis is an on-chain AI software factory—one pipeline from our own GPU compute to shipped software. We build consumer and enterprise products across perception, generative, agentic, and robotics AI. Stake $VANTIS to unlock the software factory: Pro access to every product: Pabrik, Vault, Kreofi, Trillion, and many more with unlimited inference. Own the factory.

$VANTIS is now available on Robinhood Crypto via Virtuals Protocol. Official CA: 0xB6d695d5fbcEbD837f6b9f214c9BeeE8bA90762B Vantis is an on-chain AI software factory—one pipeline from our own GPU compute to shipped software. We build consumer and enterprise products across perception, generative, agentic, and robotics AI. Stake $VANTIS to unlock the software factory: Pro access to every product: Pabrik, Vault, Kreofi, Trillion, and many more with unlimited inference. Own the factory.

Vantis

72,342 views • 2 months ago

Most documentation rots because it’s expensive to maintain and easy to ignore. Software Factory is documentation-first so teams can describe systems in English and let agents compile that intent into code. It detects drift on every code push and keeps documentation synchronized with reality. Context stays alive. Agents keep building. Try it here:

Most documentation rots because it’s expensive to maintain and easy to ignore. Software Factory is documentation-first so teams can describe systems in English and let agents compile that intent into code. It detects drift on every code push and keeps documentation synchronized with reality. Context stays alive. Agents keep building. Try it here:

Chamath Palihapitiya

197,716 views • 7 months ago

Using LLaMA 3 70B on Groq Inc to instantly refactor and document code. The implications for software engineering are wild. Gone are the days of waiting on an LLM for suggestions or code changes. Now, it's an instant feedback loop. Demo link in the comments:

Using LLaMA 3 70B on Groq Inc to instantly refactor and document code. The implications for software engineering are wild. Gone are the days of waiting on an LLM for suggestions or code changes. Now, it's an instant feedback loop. Demo link in the comments:

Matt Shumer

442,737 views • 2 years ago

Want to stand out in the job market with top-rated tech skills? Join AltSchool Africa to learn in-demand code and no-code tech skills in our Software, Product and Data Programs Start now and get certified in 12 months!

Want to stand out in the job market with top-rated tech skills? Join AltSchool Africa to learn in-demand code and no-code tech skills in our Software, Product and Data Programs Start now and get certified in 12 months!

AltSchool Africa

5,912,143 views • 2 years ago

The new Factory software AI agents just combined OpenAI’s Codex, Devin, and Cursor into one product. They are fully autonomous agents called Droids that perform deep code research, technical docs, and do autonomous end-to-end coding. Here’s how it works (with real examples)👇:

The new Factory software AI agents just combined OpenAI’s Codex, Devin, and Cursor into one product. They are fully autonomous agents called Droids that perform deep code research, technical docs, and do autonomous end-to-end coding. Here’s how it works (with real examples)👇:

Alvaro Cintas

94,884 views • 1 year ago

Within software architecture, few people shaped the industry as much as Grady Booch. Safe to say he's a true legend. In today's The Pragmatic Engineer Podcast episode, he shares fascinating stories, insights, observations. Listen or watch the full episode: - YouTube: - Spotify, Apple, or web: Thank you to our wonderful sponsors: 🌟 WorkOS — The modern identity platform for B2B SaaS. Learn more at 🌟Sevalla — Deploy anything from preview environments to Docker images. Check it out at 🌟Chronosphere — The observability platform built for control. Get details at --- 3 of my takeaways from this fascinating conversation: 1. Surprising: The US Department of Defense and the military built some of the most complicated software systems in the 70s and 80s. In the 70s, these organizations probably had the most code to deal with - globally! - and things like distributed computing were pioneered thanks to these use cases. 2. The three axes of software architecture Grady argues that when talking about software architecture, we should look at these three dimensions: ceremony, risk and complexity. 3. The economics of software and software architecture are always connected Machine time was very expensive in the 1960s and 1970s, and software had to be written from scratch. Good architecture meant writing highly performant code to utilize these rather limited machines. However, these days, machine time has gotten very cheap, and there are also plenty of “building blocks” at our disposal: from frameworks to cloud services. Software architecture is frequently still connected with cost: to decide on what services and technologies to use, taking the cost aspect into account! I hope you enjoy this conversation - together with a history overview of the last 50 years in software - as much as I did! Thanks a lot Grady Booch

Within software architecture, few people shaped the industry as much as Grady Booch. Safe to say he's a true legend. In today's The Pragmatic Engineer Podcast episode, he shares fascinating stories, insights, observations. Listen or watch the full episode: - YouTube: - Spotify, Apple, or web: Thank you to our wonderful sponsors: 🌟 WorkOS — The modern identity platform for B2B SaaS. Learn more at 🌟Sevalla — Deploy anything from preview environments to Docker images. Check it out at 🌟Chronosphere — The observability platform built for control. Get details at --- 3 of my takeaways from this fascinating conversation: 1. Surprising: The US Department of Defense and the military built some of the most complicated software systems in the 70s and 80s. In the 70s, these organizations probably had the most code to deal with - globally! - and things like distributed computing were pioneered thanks to these use cases. 2. The three axes of software architecture Grady argues that when talking about software architecture, we should look at these three dimensions: ceremony, risk and complexity. 3. The economics of software and software architecture are always connected Machine time was very expensive in the 1960s and 1970s, and software had to be written from scratch. Good architecture meant writing highly performant code to utilize these rather limited machines. However, these days, machine time has gotten very cheap, and there are also plenty of “building blocks” at our disposal: from frameworks to cloud services. Software architecture is frequently still connected with cost: to decide on what services and technologies to use, taking the cost aspect into account! I hope you enjoy this conversation - together with a history overview of the last 50 years in software - as much as I did! Thanks a lot Grady Booch

Gergely Orosz

55,813 views • 1 year ago

Antigravity + Claude Code: Automate ANYTHING! Build software in minutes with zero code. No more manual debugging. No more slow development cycles. Here's the new play 👇 → AI plans project architecture. → Claude Code writes all code. → Controls terminal and browser automatically. → Verify progress via visual artifacts. → Instant API and CRM integrations. Launch your first app today. Public preview is free right now. Want the full guide? DM me.

Antigravity + Claude Code: Automate ANYTHING! Build software in minutes with zero code. No more manual debugging. No more slow development cycles. Here's the new play 👇 → AI plans project architecture. → Claude Code writes all code. → Controls terminal and browser automatically. → Verify progress via visual artifacts. → Instant API and CRM integrations. Launch your first app today. Public preview is free right now. Want the full guide? DM me.

Julian Goldie SEO

12,598 views • 7 months ago

Antigravity + Claude Code: Automate ANYTHING! Build software in minutes with zero code. No more manual debugging. No more slow development cycles. Here’s the new play 👇 → AI plans project architecture. → Claude Code writes all code. → Controls terminal and browser automatically. → Verify progress via visual artifacts. → Instant API and CRM integrations. Launch your first app today. Public preview is free right now. Want the full guide? DM me.

Antigravity + Claude Code: Automate ANYTHING! Build software in minutes with zero code. No more manual debugging. No more slow development cycles. Here’s the new play 👇 → AI plans project architecture. → Claude Code writes all code. → Controls terminal and browser automatically. → Verify progress via visual artifacts. → Instant API and CRM integrations. Launch your first app today. Public preview is free right now. Want the full guide? DM me.

Julian Goldie SEO

37,857 views • 8 months ago

Introducing Mesa, the world’s first multi-agent code review system that truly understands your system and architecture to deliver senior-level reviews.

Introducing Mesa, the world’s first multi-agent code review system that truly understands your system and architecture to deliver senior-level reviews.

Oliver

65,440 views • 10 months ago