docs: update README and examples/README for v3.3.5 -- demo source now live

Author: jovanSAPFIONEER

README.md

@@ -68,7 +68,7 @@ That's it. No config files, no setup wizards. Add more agents, swap frameworks,
 
 > The demo shows a code review swarm, but Network-AI is not a code review tool. The same orchestration pattern works for research pipelines, data processing, content moderation, customer support routing, document analysis, financial workflows — any task where multiple agents need to coordinate without stepping on each other.
 
-> **Live demo source coming soon:** The full source for `04-live-swarm.ts` and `05-code-review-swarm.ts` will be added to the repo with a `.env.example` so you can run them against your own API keys. In the meantime, examples `01`–`03` cover all core framework features — atomic blackboard, FSM governance, parallel dispatch — with no API key or external dependency required.
+> **Run the demo yourself:** `05-code-review-swarm.ts` is in the repo. Copy `.env.example` to `.env`, add your `OPENAI_API_KEY`, then run `npx ts-node examples/05-code-review-swarm.ts`. Supports 4 modes: built-in code review, paste your own code, system design document, or custom role for any content type (proposals, policies, job descriptions, emails). Examples `01`–`03` cover all core framework features with no API key required. `04-live-swarm.ts` (live AI research swarm) is coming soon.
 
 ## Why This Exists -- The Multi-Agent Race Condition Problem
 

examples/README.md

@@ -1,15 +1,17 @@
 # network-ai · Examples
 
-Runnable demos that show the core features in under five minutes.  
-All three examples work without an API key.
+Runnable demos that show the core features in under five minutes.
 
 ```
 examples/
-  01-hello-swarm.ts      ← three agents passing work through a blackboard
-  02-fsm-pipeline.ts     ← FSM governance (state-based access control)
-  03-parallel-agents.ts  ← parallel agents + four synthesis strategies
+  01-hello-swarm.ts        ← three agents passing work through a blackboard  (no API key)
+  02-fsm-pipeline.ts       ← FSM governance (state-based access control)     (no API key)
+  03-parallel-agents.ts    ← parallel agents + four synthesis strategies      (no API key)
+  05-code-review-swarm.ts  ← 5-agent AI code review swarm, 4 modes            (OPENAI_API_KEY required)
 ```
 
+Examples `01`–`03` run without any API key. `05` calls the OpenAI API — copy `.env.example` to `.env` and add your key before running it.
+
 ## Prerequisites
 
 ```bash
@@ -79,10 +81,38 @@ npx ts-node examples/03-parallel-agents.ts
 npx ts-node examples/01-hello-swarm.ts
 npx ts-node examples/02-fsm-pipeline.ts
 npx ts-node examples/03-parallel-agents.ts
+
+# 05 requires OPENAI_API_KEY in .env
+npx ts-node examples/05-code-review-swarm.ts
 ```
 
 ---
 
+## 05 · Code Review Swarm
+
+A 5-agent swarm (Security, Performance, Reliability, Testing, Architecture) reviews code or documents in parallel, then a coordinator synthesizes the findings and a fixer agent applies them. Requires `OPENAI_API_KEY`.
+
+```bash
+# Setup (one time)
+cp .env.example .env        # then add your key inside .env
+
+# Run
+npx ts-node examples/05-code-review-swarm.ts
+```
+
+**4 modes at launch:**
+
+| Mode | Prompt | Output |
+|------|--------|--------|
+| `[1]` Built-in | Reviews the bundled `auth-service.ts` | Fixed `.ts` file |
+| `[2]` Paste code | Paste your own source (ends with `end`) | Fixed `.ts` file |
+| `[3]` System design | Paste a design/architecture doc | Revised `.md` file |
+| `[4]` Custom role | Define your own reviewers for any content | Revised `.md` file |
+
+Output files are saved to `examples/output/`. See the [YouTube demo](https://youtu.be/UyMsNhaw9lU) for a walkthrough.
+
+---
+
 ## Next steps
 
 | Goal | Starting point |