# How to identify what to improve next in your AI software factory

DevFeed: [How to identify what to improve next in your AI software factory](<https://devfeed.tech/articles/how-to-identify-what-to-improve-next-in-your-ai-software-factory-111685.md>)

Original publisher: [Read original article](<https://www.port.io/blog/improving-your-software-factory>)

Author: John Crowley

Published: 2026-11-01T11:30:09Z

Content type: tutorial

Language: en

Sources: [Port](<https://devfeed.tech/sources/developer-experience-platform-engineering-blog-port.md>)

Topics: [developer-productivity](<https://devfeed.tech/topics/developer-productivity.md>), [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>), [Platform Engineering](<https://devfeed.tech/topics/platform-engineering.md>), [AI tools for developers](<https://devfeed.tech/topics/ai-tools-for-developers.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-software-factory](<https://devfeed.tech/tags/ai-software-factory.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [assessment](<https://devfeed.tech/tags/assessment.md>), [bottlenecks](<https://devfeed.tech/tags/bottlenecks.md>), [delivery](<https://devfeed.tech/tags/delivery.md>), [engineering-intelligence](<https://devfeed.tech/tags/engineering-intelligence.md>), [guide](<https://devfeed.tech/tags/guide.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [improvements](<https://devfeed.tech/tags/improvements.md>)

## AI overview

The Engineering Intelligence Pulse ranks improvement opportunities using engineering data, giving each one supporting evidence, affected service and team, a recommended action, and a success measure. In the example, it identifies limited reviewer coverage as the likely cause of 26-hour average PR review waits for the Payments service and recommends a backup reviewer, with a target below four hours. The process combines approved, customizable domain skills with the Engineering Intelligence Agent, which assesses data and ranks findings, and a customizable workflow that enriches Port's Context Lake and shares priorities in Slack. Setup requires engineering data in Port, service-to-team ownership, and a Slack bot that can publish the brief. Organizations can start with one use case, then use governed workflows to act on opportunities and measure results.

## Source excerpt

Learn how to prioritize improvements in your AI software factory, identify key gaps, and focus teams on changes that matter most.