Skip to content

Blog

Insights on AI, software development, and building better digital products

Filtered by:best-practices
How We Review Code When Agents Write Most of It
ai+5

How We Review Code When Agents Write Most of It

In June we merged 16 pull requests into our own website. In the first 18 days of October we merged 167. Nobody reads that many diffs line by line. Here is how we review code now, and where a person still decides.

13 min readTerrance MacGregorTerrance MacGregor
the_fidelity_flow.jpg
ai+3

Fidelity is up and obedience is down!

As a developer, you will be silently fired if you execute on user stories exactly as written. It won't be on purpose and it will happen slowly over time. This is called "ticket obedience" and it is no longer rewarded in the age of AI.

5 min read

USB cables look the same. They are not.

Most of what matters on a USB cable is invisible. We organized the mess into a simple reference at usb.periscoped.io.

2 min readTerrance MacGregorTerrance MacGregor
Stop Building on Shifting Sand: Lock Your Object Model Before AI Touches It -- card image
ai+3

Stop Building on Shifting Sand: Lock Your Object Model Before AI Touches It

AI-assisted projects turn to slop when there's no foundation. Lock two files — a plain-English object definition and a derived data model — and AI has to build on rock instead of shifting sand.

6 min read

We Gave Every AI Agent a Job Title: It Changed Everything

We broke AI agents into domain-specific subagents with explicit ownership of routes, types, and business rules. The codebase got better overnight.

6 min read

The API Agent That Enforces What Developers Forget Under Pressure

Under deadline pressure, API routes accumulate bad habits. Here's how a dedicated agent enforces REST standards, Zod validation, and permission checks on every route, every time.

2 min readTerrance MacGregorTerrance MacGregor