Intel / post

Software Factory Builder

Source: x.com
Author: Pierson Marks
Date: Indexed Jul 10, 2026

Context

Pierson Marks describes an automation setup that separates finding possible work from authorizing implementation. Scheduled agents examine operational signals and add issues to Linear, the team's issue tracker. A human normally adds an auto label before a coding session starts. Marks's account makes the tracker the handoff between discovery and execution.

Adding that label sends an event to a small routing service, which starts a remote Claude Code routine from Anthropic. The routine receives the issue and is instructed to implement it and open a pull request, a proposed code change for review. This lets the team automate investigation while retaining an explicit decision about which findings deserve engineering work.

Key takeaways · AI-distilled

The churn loop does real forensics: for each cancellation in the last 24 hours it pulls Stripe payment and user data, watches the PostHog session replay, and checks Supabase usage to classify wrong customer fit, no 'wow' moment, or bug.
Session replays are the highest-yield input in the whole system. Rage clicks and visible confusion show you where users struggle in a way that support tickets, which only capture people who bothered to write in, never will.
Cloud routines beat self-hosting for a non-obvious reason: connectors configured in the Claude desktop app are usable by both the local CLI and the cloud runs, so scheduled agents inherit integrations you already set up.
Sequencing advice: build only the work-discovery half first, so routines file high-quality issues into the tracker you already use, and keep implementing however you do today. The leverage arrives before the loop is closed.

Terms in this piece · Glossary

MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.

Key quotes

“Every software factory needs to have this centralized repository of work to be done, whether that's GitHub issues, Linear, or something else.”

“Session replays are a goldmine. You can see where rage clicks happen or where users are struggling and confused.”

“And to all the people saying "but what about vendor lock in!!" - it's literally just some text.”

“To actually run these agents consistently, I kept it simple and used Claude Code Cloud Routines.”

Read the source x.com