small blog tweaks

Author: motdotla

blog/_posts/2026-03-02-wizard-of-drift-oz-and-dotenvx.md

@@ -3,14 +3,14 @@ layout: blog
 author: "Scott Motte – Mot"
 title: "Stop .env Drift Before Merge with Wizard of Drift"
 image: "/assets/img/blog/blog-13.png"
-excerpt: "Catch .env key drift on pull requests automatically with Warp Oz + Dotenvx."
+excerpt: "Catch .env key drift on pull requests automatically with Warp's Oz + Dotenvx."
 ---
 
 I shipped a small GitHub Action this week: [wizard-of-drift](https://github.com/dotenvx/wizard-of-drift).
 
 It catches `.env*` key drift in pull requests and leaves a review comment with concrete fixes.
 
-It uses [Warp Oz](https://warp.dev/oz) under the hood to do the review, and it works great.
+It uses [Warp's Oz](https://warp.dev/oz) under the hood to do the review, and it works great.
 
 <img src="https://github.com/user-attachments/assets/b77d8c0f-a96e-4e31-905d-6c76c42882a9" />
 
@@ -72,7 +72,7 @@ jobs:
           warp_agent_profile: "" # optional
 ```
 
-## Why Oz Works Well Here
+## Why A Coding Agent Works Well Here
 
 This is a great use case for an agent because the input is high-context but bounded:
 
@@ -81,11 +81,11 @@ This is a great use case for an agent because the input is high-context but boun
 - the `.env*` diff in the PR
 - explicit rules about `DOTENV_PUBLIC_KEY` naming
 
-Wizard of Drift builds that context first, then gives Oz a tight prompt and asks for one output: a concise review summary with exact keys to add.
+Wizard of Drift builds that context first, then gives the agent (in this case Oz) a tight prompt and asks for one output: a concise review summary with exact keys to add.
 
 That pattern matters.
 
-Oz is not guessing from vague code context. It is reviewing a purpose-built context document generated by CI, then returning actionable output directly into the PR conversation.
+The agent is not guessing from vague code context. It is reviewing a purpose-built context document generated by CI, then returning actionable output directly into the PR conversation.
 
 So the reviewer sees concrete fixes, not generic AI advice.
 
@@ -97,8 +97,8 @@ This is the kind of workflow I want more of:
 - AI agent review
 - deterministic output in PR comments
 
-Oz helps amplify what Dotenvx is already good at: making `.env` workflows safer and easier to operate at scale.
+And Oz was a great choice here because I wanted to easily trigger a coding agent from a GitHub action. Plus it supports any model and can be monitored from [its dashboard](https://oz.warp.dev).
 
-Dotenvx gives you the secure env model. Oz gives you a practical enforcement loop at review time.
+The combination makkes my `.env` workflows safer and easier to operate at scale. Dotenvx gives you the secure env model and the agent gives you a practical enforcement loop at review time.
 
 Together, they remove a class of annoying config breakages before they merge.