Here's my take on what a software factory really is
This is my talk from @aiDotEngineer NYC, and I decided to record a version for everyone to watch on X.
tl;dr - software engineering is becoming factory engineering, and there's new work (especially factory benchmarking) that
Getting software factories working is going to be one of the more interesting software engineering challenges in the next few years.
Software engineering is becoming factory engineering. Organizations that can make their factories robust, dependable, and self-improving will be able to ship more at better cost and have a competitive advantage.
Software factories can be a real culture shift. The biggest change for us was moving from individual agents on everyone's machines to one central agent setup (a factory) that we can build as a team.
I wrote some learnings on how to navigate that. x.com/i/article/2110…
An interesting engineering challenge this next year will be closing the development loop we've started.
We have small loops already (code review, automatic CI fixes, computer use verification), but we need to close the larger loop: let agents suggest what to build next.
I've been thinking about what a true, closed-loop software factory will look like.
One where agents know what to fix, what costs to optimize, and the big one: what features to actually build.
We're not there yet. But maybe we're getting close... x.com/i/article/2110…
Software factories can be a real culture shift. The biggest change for us was moving from individual agents on everyone's machines to one central agent setup (a factory) that we can build as a team.
I wrote some learnings on how to navigate that. x.com/i/article/2110…
I've been thinking about what a true, closed-loop software factory will look like.
One where agents know what to fix, what costs to optimize, and the big one: what features to actually build.
We're not there yet. But maybe we're getting close... x.com/i/article/2110…
3. Have agents suggest roadmap items from customer feedback.
For example, you can use @GrainHQ to record transcripts on customer discovery calls, and have coding agents pull out insights.
Here, an agent goes through prior customer interviews with a scheduled automation and looks for commonalities in where customers get stuck. From there, you can fully close the loop by connecting your taskboard via MCP to drive the next agent task.
More on integrations: docs.warp.dev/factories/conn… 🔖
We've found a few key pieces to successful software factories, both from our internal testing and from helping companies deploy their own:
Factories-as-code: you should configure every part of the factory (agent orchestration, automations, permissions, sandbox configuration, etc) as code. This enables testing of different factory configurations to see which are most efficient, highest quality, etc.
Multi-model & multi-harness: you should make sure that your factories are able to use the latest models, both frontier and open-weight, and use different coding agent harnesses like Claude Code and Codex.
Data ownership: you should make sure you store and own all data coming out of your factory. This is the raw material for improving its operations.
I'll be joining @sergical at @sentry on October 22nd to talk about connecting error monitors to coding agents!
It's how we've closed the loop in our own software factory to have agents assign themselves work automatically. The flow we're using right now:
- Connect to an alert
Someone asked how I defined a software factory recently, and I think my definition is different from others.
To me, a software factory is centralizing your system of agents into one place to build software. That means going from custom coding setups on everyone's machines to a single definition.
In practice, it's one source of truth for agent automations, repository access, secret access, sandbox environments, model selections... every aspect of the stack.
I think loops and automations are a secondary aspect of this that gets unlocked once you unify everything into an "always-on" agent system. But the heart of it is having the whole team agree on the agent setup, the same way we agree on CI, lint rules, and all the automations we had pre-AI.
This also makes it clear what an engineer's job is now: to make the agents better at building software. Not to be prompt monkeys! We like to call it "factory engineering"
I chatted with @hudaman (Sr Engineering Manager, Uber) and @cmhandel (Director of Product, AI Platform, Faire) to compare notes on adopting software factories. We discussed:
- The best starting point for factories
- Code review and spec writing
- How to navigate team culture changes
And how everyone's handling software factory adoption at their companies. Many different approaches to this
youtu.be/0gDHnH89aQs
My @aiDotEngineer SF talk is on YouTube.
My take is that software engineering is becoming factory engineering: building the system of agents that builds the product.
We used the Warp open source repo (now at 65k GH Stars) as a testbed for this idea:
youtube.com/watch?v=tUPPVh… 🔖
I'll be joining @sergical at @sentry on October 22nd to talk about connecting error monitors to coding agents!
It's how we've closed the loop in our own software factory to have agents assign themselves work automatically. The flow we're using right now:
- Connect to an alert webhook like Sentry
- When errors happen, start a cloud agent run with the alert and the repo as context
- Have the agent ping humans for code review (or better: with an HTML summary of the problem and the solution)
- Merge and keep monitoring
This closes the loop on reducing software bugs. We'll show you how to deploy it in-code yourself!
BIG NEWS - Sign in with ChatGPT plan usage is now also available to all customers on the ChatGPT Go plan. That is - Customers on Go, Plus and Pro plans can now login to all commercial launch partner apps + open source applications and take their ChatGPT plan usage with them. So
72K Followers 1K FollowingBuilding @remix_run at @Shopify. God hath not given us the spirit of fear; but of power, and of love, and of a sound mind – 2 Tim 1:7
59K Followers 2K Following@Shopify design-engineer; prior @GoogleChrome, @GoogleCloud, CSSWG, and CSS Podcast. Host on @whiskeywebfm, maker of @OpenProps, https://t.co/lb3SDxC6EC and more
19K Followers 964 FollowingBuild smaller, faster, and secure cross-platform applications with a web frontend. Support our OSS project at Open Collective: https://t.co/JduvEOCrY2
455 Followers 364 FollowingApplied AI research & engineering. Co-founded BriteCore. Building tools for people and agents to work together. Bad at keeping experiments small.
61 Followers 2K FollowingLIVING TO BECOME BEST VERSION
(FIRST VERSION WAS V.1.0) 2000
(CURRENT VERSION V.25.1) 2026-27
UCOMMING VERSION V.26.0) 2027
RELEASE DATE 2 MAY 2027
@bitcoin
159 Followers 917 FollowingProduct Designer at https://t.co/motVRrQ2gJ
Tinkering w https://t.co/33zqdmUANR and https://t.co/qhmtMRTzkB and https://t.co/I9OuyUugOo
993 Followers 92 FollowingKI-gestützte Prozessoptimierung und -automatisierung im B2B-Mittelstand | Strategie, Umsetzung & Sparring für Unternehmer, Geschäftsführer und Führungsteams.