diff --git a/site/README.md b/site/README.md
index 20b6107..0d6ce36 100644
--- a/site/README.md
+++ b/site/README.md
@@ -1,6 +1,6 @@
# devloop site
-Minimal static marketing site for the `devloop` CLI. Single page, monochrome
+Minimal static landing site for the `devloop` CLI. Single page, monochrome
teletype aesthetic, violet accent matching the CLI brand. No runtime
dependencies: Tailwind compiled to static CSS, JetBrains Mono self-hosted from
`public/fonts/` (OFL, weights 400 + 700), used across the whole page. Built with
diff --git a/site/index.html b/site/index.html
index 3b0ce99..de513fd 100644
--- a/site/index.html
+++ b/site/index.html
@@ -11,7 +11,7 @@
-
Spec-driven code/review loop that runs until all
- acceptance criteria are met and bugs fixed.
+ acceptance criteria are met and bugs fixed by agents.
-
+
Requires Codex and Claude Code. Runs on macOS.
-
+
-
+
+
+
+
@@ -119,15 +137,19 @@
## WHY
-
+
Developers now spend most of their time in code
review, assisted by coding agents. But the same
- model family can't both code and review. It favors
- its own outputs. Devloop makes Codex implement and
+ model family can't both code and review. It
+ favors its own outputs. Devloop makes Codex implement and
Claude Code review adversarially (or vice versa),
until all criteria are met and reviews addressed, so
- humans only come in where judgment pays off: the
- spec and PR sign-off.
+ humans only come in where judgment pays off: at the
+ spec and PR sign-off stages.
@@ -139,7 +161,7 @@
>HOW IT WORKS
-
+
[
>WHEN (NOT) TO USE
-
-
-
When to use
-
+
+
When to use
+
[When to use
unattended and only pull you in for the
spec and PR sign-off.
-
-
-
-
When not to use
-
+
+
When not to use
+
[When not to use
You want hands-on control of every edit
rather than a loop running on its own.