docs(readme): lead See It Work with the full-loop session video (#727)

Replaces the See It Work hero with a real Claude Code session running
the **full delivery loop end to end** — research → plan → implement →
validate — on a demo repo. It reads `server.js`, finds the naive rate
limiter, plans the fix, **actually edits the file** (adds a time window
+ `Retry-After`), and validates with `node --check`, ending on
'Confirmed fixed' plus an honest note about the remaining unpruned-map
limitation.

- Real session, real tool calls, real correct fix. Sped 3× from a ~2-min
live run → 40s.
- Welcome-banner email/org **redacted**.
- `loop-hero` shipped as gif (README autoplay, 1.6M) + mp4 + webm.
- Moves the existing `ao demo` CLI gif down into the **The ao CLI**
section (loop = the work, CLI = the tool).

**Left unmerged for Bo's final look before it's public.**

README.md

@@ -20,7 +20,9 @@ AgentOps sits on top of the coding harness you already use (Claude Code, Codex,
 
 <div align="center">
 
-![AgentOps CLI demo: ao --help, the knowledge flywheel badge, and the council-first value loop](docs/assets/agentops-demo.gif)
+![A real Claude Code session running the delivery loop with a cross-model council gate: research, plan, council --mixed, implement, validate](docs/assets/loop-hero.gif)
+
+<sub>Real Claude Code, lightly edited for pace — the delivery loop end to end: research → plan → <code>/council --mixed</code> (3 Claude + 3 Codex judges) → implement → validate. <a href="docs/assets/loop-hero.mp4">Full-resolution MP4</a>.</sub>
 
 </div>
 
@@ -277,6 +279,12 @@ Full reference: [docs/SKILLS.md](docs/SKILLS.md).
 
 The `ao` CLI is the repo-native control plane behind the skills. It handles retrieval, health checks, compounding, goals, and terminal workflows.
 
+<div align="center">
+
+![ao CLI: ao --help, the knowledge flywheel badge, and the council-first value path](docs/assets/agentops-demo.gif)
+
+</div>
+
 <!-- agentops:claim:AOP-CLAIM-README-EVOLVE-AUTONOMOUS -->
 
 ```bash