The problem
What was broken before AI
Engineering teams lose time in the gaps between planning, context, execution, and review. A person may need to prepare for standup, understand the latest customer context, read through specs, check metrics, catch up on Slack, and turn a comment into an actual code change. None of those steps is the whole job, but together they create friction before work can move forward.
What changed
What the use case made possible
Ryan’s workflows put AI closer to the team’s operating system. Notion AI helps prepare standups and summarize the work happening across projects. Spec-first development gives AI a clear written plan before implementation starts. Codex can turn certain Notion comments or specs into pull requests. Observability and Slack context help engineers understand what changed and why before they write code or review a fix.
Why this matters
Why this use case is worth studying
Ryan’s use case is valuable because it does not treat AI coding as a standalone trick. The better pattern is connecting AI to the team’s existing rhythm: specs, project pages, comments, pull requests, telemetry, and reviews. That makes the work easier to start and easier to evaluate. The model is not only producing code; it is helping the team move from scattered context to a smaller, clearer next step.
Use this when
When this pattern applies
Use this pattern when engineering work is slowed down by context switching: specs live in one place, comments in another, metrics somewhere else, and code changes somewhere else again. It works best when the team already writes things down, but needs help turning that written context into action.
