X postJustin DukeOpinion
Organisations adopting AI coding agents frequently struggle when relying on generic vendor platforms. Because success depends on encoding internal hierarchies, context, and review workflows, self-hosted and open-source infrastructure tailored by platform engineers often provides better alignment and lower costs.
Murray highlights why commercial software factory platforms struggle to provide defensible value: vendors do not own the models or the sandboxes, leaving them with generic control planes that fail to fit distinct enterprise operating models. Effective agent deployment requires deep contextual integration—such as managing thousands of bespoke tools and routing prompts according to domain authority. Duke's commentary reinforces this shift, noting that the hardest part of operationalising AI agents is not generating code, but restructuring organisational incentives and collaborative processes.
Justin Duke
@jmduke · 14 September 2026
I think this is the best piece of writing I've seen on "software factory" as a concept, in no small part because it correctly identifies the barriers to building such a thing as technological (process, incentive, culture) and not technological (code) t.co/Ka6ehj2owu
358 likes9 replies1k bookmarks124.8k views
View on XSummary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
X post:cole murray
Cole Murray argues that building a 'software factory' is not merely an engineering or tooling exercise, but fundamentally about shaping how teams within a company collaborate.
2.3kbookmarks77.2kviews
X post:Zach Lloyd
Zach Lloyd shares insights on adopting software factories, noting that the biggest cultural change was transitioning from individual agents running on local machines to a centralised agent setup built collaboratively by the team.
266bookmarks7.3kviews
X post:Gergely Orosz
In an in-depth report, Gergely Orosz explores internal operations at OpenAI, where Codex and ChatGPT Work have evolved into the operational foundation across technical and non-technical teams. Powered by deep integrations with systems like Slack and Kubernetes, automated feedback loops like 'Perf Factory' are reshaping engineering workflows and organisational structures.
6.5kbookmarks456.2kviews
Article:Gergely Orosz
Gergely Orosz provides an inside look at OpenAI, where Codex and ChatGPT Work have transformed internal operations, shifting workflows away from IDEs to autonomous coding agents while a tenfold increase in PR volume forces a rethink of CI/CD.
VideoVideo:CURT
In his talk at the AI Engineer World's Fair, Tessl's Dru Knox introduces the concept of a software factory, where coding agents produce all user-facing code whilst engineers build and maintain the factory infrastructure. He outlines harness engineering (also referred to as loop engineering) as the guiding discipline, dividing engineering work into inner, outer, and meta loops to improve autonomy, automation, and overall code quality.
VideoVideo:IndyDevDan
IndyDevDan introduces his open-source 'Super Simple Software Factory' framework. The approach pairs specialised coding agents with deterministic Python code to make automated software engineering workflows repeatable, observable, and cost-effective.
Parts of this content were created with the assistance of AI.
