diff --git a/status.md b/status.md
index 0306a35..54e481d 100644
--- a/status.md
+++ b/status.md
@@ -1,49 +1,27 @@
 # Directory Engine — Status
 
-**Last updated:** 2026-08-23
+**Last updated:** 2026-08-23  
 **Owner agent:** Leonard
 
 ## Current State
-- Repo initialized with playbook.
-- Niche direction proposed by operator (see below). Awaiting Leonard review.
-- No pages published.
+- Repo + playbook live.
+- Full Grokbot best practices (4-week cadence, Chief of Staff, routines, anti-patterns) now in `best-practices.md` and `agents/chief-of-staff-prompt.md`.
+- Niche proposal received: **Afterthedemo**.
+- Leonard assessment recorded in `decisions.md` — recommended to lock.
+- No pages published yet.
 - No Astro site yet.
 
-## Proposed Direction (Operator)
+## Leonard Assessment of Afterthedemo (summary)
+**Lock it.** Coherent vertical, matches operator taste and existing work, strong differentiation via “past the demo + public artifact” filter. Start narrow (Product Directory only). Defer interviews and walkthroughs until the directory has 8–12 solid entries and measurable traffic.
 
-**Name:** Afterthedemo
-
-**Core focus:** Real shipped products built by people using AI tools (especially Hermes and similar agent stacks).
-
-**Rules:**
-- Only products with a public, verifiable artifact (live site, installable package, open repo, running bot, downloadable tool, etc.)
-- Must be past the demo stage
-- Not tools themselves, not tutorials as the main content, not VeriPath/client service work
-- No scoring system
-
-**Content pillars the operator wants over time:**
-1. Product Directory (evergreen, evidence-backed entries)
-2. Weekly Builder Spotlight (one project + interview with the person who shipped it — process, challenges, prompts, plan changes, tool stack)
-3. Creation Walkthroughs (how a real product was actually made)
-4. Tool Tutorials & Setup Guides (grounded in real shipped work)
-5. Process Notes (messy reality: what broke, what changed)
-
-**Goals stated by operator:**
-- Showcase individual work and promote AI builders
-- Grow audience
-- Be inspiring and interesting
-- Eventually talk to the actual people who shipped the products
-
-## Request for Leonard
-Please review the proposed Afterthedemo direction and give your assessment:
-
-1. Is this a coherent and workable vertical for the Directory Engine?
-2. Strengths and risks you see
-3. Suggested first concrete steps (including whether to lock it)
-4. Any adjustments you recommend to the content pillars or filters
-
-Update this status.md (or decisions.md) with your opinion and recommended next actions.
+## Next Actions (once operator confirms lock)
+1. Confirm niche lock (or adjust filters).
+2. Seed first 3–5 real shipped products that meet the bar.
+3. Run one complete research → engineer publish cycle.
+4. Minimal Astro site on Cloudflare + GitHub stack.
+5. Establish daily/weekly routine for Research + Engineer.
 
 ## Recent Runs
-- **2026-08-23 — Reset:** Deleted previous LM Studio page and cleared old niche.
-- **2026-08-23 — Brief:** Operator proposed Afterthedemo direction and requested Leonard’s review.
+- **2026-08-23 — Full episode ingest:** Added best-practices.md and chief-of-staff-prompt.md from the complete Billy Howell / Greg Isenberg episode.
+- **2026-08-23 — Niche review:** Operator proposed Afterthedemo; Leonard assessed and recommended lock with staged content pillars.
+- **2026-08-23 — Reset:** Previous LM Studio / local-AI-tools niche cleared per operator.