From 8c9ef48fa02a1ec18053b759f8f274c597ed2fd3 Mon Sep 17 00:00:00 2001 From: dfberry Date: Sat, 20 Jun 2026 15:50:52 -0700 Subject: [PATCH] fix: update image reference in squad first impressions blog post --- website/blog/2026-06-20-squad-first-impressions.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/blog/2026-06-20-squad-first-impressions.md b/website/blog/2026-06-20-squad-first-impressions.md index 386bed0..73cac57 100644 --- a/website/blog/2026-06-20-squad-first-impressions.md +++ b/website/blog/2026-06-20-squad-first-impressions.md @@ -66,7 +66,7 @@ I do not want eight approvals. I want eight different objections. I also want those objections resolved through agent collaboration, not by pulling me into every pass. Just like a real PR review, reviewers should send issues back to build, build should improve the work, and the review should run again until everyone agrees the bar is met. -![Watercolor illustration of a team examining the same cabinet from different angles](./media/2026-06-20-squad-first-impressions/2026-06-20-squad-first-impressions-watercolor-2-build-review.png) +![Watercolor illustration of a team examining the same cabinet from different angles](./media/2026-06-20-squad-first-impressions/2026-06-19-carpenter-watercolor-table-leg.png) A single generalist reviewing its own output gives me consistency with itself. That is not the same as complete and correct.