{"slug": "trying-the-software-factory-pattern", "title": "Trying the Software Factory pattern.", "summary": "Engineering leader Will Larson documented his first implementation of the \"software factory pattern\" — an agent skill called /linear-project-loop that reads a Linear project, audits its goal definition, reviews metrics and issues, and works through non-blocked tasks such as writing or updating pull requests. Larson, who attributes the term to Justin McCarthy's February 2026 piece \"Software Factories And The Agentic Moment,\" said the loop currently runs locally in a local harness but works well enough that he expects to move it to the same orchestrated harness used for one-off tasks. He said the pattern depends on Datadog MCP and Snowflake access for goal-tracking, Linear as the single source of state, and a harness that can work independently of his laptop, and that it caught post-release drift he would otherwise miss, such as changes in passkeys adoption or error rates.", "body_md": "One of the interesting challenges of the AI ecosystem in 2026 is that new, effective patterns emerge faster than I can adopt them. I’ll find a handful, get back to work, and realize a month later that I’d missed four or five more. The adoption cycle for Imprint this year has been something like:\n\nThe most recent question for me has been figuring out how to adopt the software factory pattern.\n(After some light research, the specific AI-context origin of this term is slightly messy to\nattribute, but I think it might be Justin McCarthy in February 2026’s\n[Software Factories And The Agentic Moment](https://factory.strongdm.ai/).)\n\nThe software factory pattern is looping on a broad goal, and then relying on the harness to drive progress towards that goal. Our first pass at implementation is fairly basic:\n\nAn agent skill `/linear-project-loop` which reads in a Linear project and starts by auditing\nthat project’s goal definition on these dimensions:\n\nIf those are missing, or the Linear project is missing in its entirety, it iterates with you on creating those missing tools.\n\nThen it reviews the state of the metrics and issues for the project. If new work is identified, it adds those issues to the project. It updates the state of issues that have moved.\n\nIt works on the non-blocked tasks based on the project’s current state. This is often writing a pull request, updating a pull request, pinging for review, asking a clarifying question, etc.\n\nWhen a task completes, if the project description is fresh, it takes on the next task. If the description hasn’t been updated in a while, it reruns the loop starting with the first step.\n\nRight now I am running this locally in a local harness, but it’s working well enough that I anticipate moving the behavior to be driven by the same orchestrated harness that we assign one-off tasks to.\n\nWhat I particularly like about the factory pattern is that it parallels very closely how I’ve been working locally, while forcing me to recognize the places where I was accidentally hoarding parts of the state for myself regarding the goals of the project. I was already asking agents to iterate on specific Linear projects, but they didn’t have the ability to evaluate if they were going in the right direction, or if it was missing necessary tasks. Now it does. The other place this has been extremely helpful for me is checking in on projects post-release. For example, I shipped our passkeys implementation earlier this year, but some months go by without my checking in on how it’s going. If we saw adoption spike, or error rates start to turn, I might miss it, but running the factory in a less frequent post-release mode would catch it immediately.\n\nThe final thought that’s been interesting to me is how much all of the pieces here compound only to the extent\nthat you have the other pieces. For example, this factory pattern depends on having Datadog MCP and Snowflake access available\nto manage goal-tracking, but it also depends on Linear being the single source of state for the company’s work,\nand an orchestrated harness that can perform work independently from your laptop. Keeping up with this\nmany [migrations](https://lethain.com/migrations/) is a fascinating industry moment.", "url": "https://wpnews.pro/news/trying-the-software-factory-pattern", "canonical_source": "https://lethain.com/software-factory-experiment/", "published_at": "2026-09-20 12:00:00+00:00", "updated_at": "2026-10-17 14:03:38.899326+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "artificial-intelligence"], "entities": ["Will Larson", "Linear", "Justin McCarthy", "Software Factories And The Agentic Moment", "Datadog", "Snowflake", "Imprint"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/trying-the-software-factory-pattern", "markdown": "https://wpnews.pro/news/trying-the-software-factory-pattern.md", "text": "https://wpnews.pro/news/trying-the-software-factory-pattern.txt", "jsonld": "https://wpnews.pro/news/trying-the-software-factory-pattern.jsonld"}}