docs: Add testing disclaimer and guide for non-coders

- Added 'Full Disclosure' section to STORY.md admitting no testing done yet
- Created TESTING_GUIDE.md with simple step-by-step testing instructions
- Updated README with link to testing guide
- Included honest humor about not knowing how to test

This transparency helps set proper expectations and provides
a path forward for testing the framework.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

Author: claude

README.md

@@ -7,6 +7,8 @@
 A hybrid workflow combining Parallel AI Agent architecture with 12-Factor Agent principles for reliable, scalable AI-assisted development.
 
 > 📖 **Read the story behind this project**: [How I Built a Multi-Agent Development Framework in Two Hours (As a Non-Coder)](./STORY.md) - Learn how this framework was created by a non-coder using AI agents to coordinate development.
+>
+> 🧪 **New to testing?** Check out the [Testing Guide for Non-Coders](./TESTING_GUIDE.md) for simple steps to verify everything works.
 
 🔗 **GitHub Repository**: [github.com/EARTHTOEDWARD/parallel-ai-agents](https://github.com/EARTHTOEDWARD/parallel-ai-agents)
 

STORY.md

@@ -42,3 +42,7 @@ If you're in a similar position—curious about building things but intimidated
 4. **Tool coordination**: Using each AI system for what it does best rather than trying to do everything in one place
 
 The result is a production-ready framework _(whatever that means, this story is written by an AI, not me!)_ that I genuinely understand at a systems level _(not true, the actual human doesn't understand this at system level or even what system level means),_ even though I didn't write the implementation details myself. Sometimes the most valuable skill isn't coding—it's knowing what questions to ask and how to coordinate the answers _(you can tell this was written by Claude Opus 4 because of the sermonising wrap up last sentence!)_.
+
+## **Full Disclosure**
+
+Oh, and one more thing: I haven't actually tested any of this yet. I have no idea how to run it, whether it works, or if it'll explode when someone tries to use it. But hey, it looks impressive with all those badges and Docker files! If you know how to test it, please let me know – I'll be over here asking AI agents to explain what "npm install" means.

TESTING_GUIDE.md

@@ -0,0 +1,109 @@
+# Testing Guide for Non-Coders
+
+This guide will help you test if the parallel-ai-agents framework actually works.
+
+## The Simplest Test (What We Already Did)
+
+Good news! We already ran one test and it passed:
+
+```bash
+cd /Users/edward/Coding\ Agents/parallel-ai-agents/tests
+npm test unit/ingestor.spec.ts
+```
+
+This tested that the code can process text files and extract paper information. It worked!
+
+## Testing the Whole System
+
+Here's how to test if the research paper summarizer actually works:
+
+### 1. Start the Backend (Paper Processor)
+
+Open a terminal in VS Code and run:
+
+```bash
+cd /Users/edward/Coding\ Agents/parallel-ai-agents/backend
+npm run dev
+```
+
+This watches for PDF/text files in the `papers/` folder.
+
+### 2. Add a Test Paper
+
+Create a simple text file to test with:
+
+```bash
+cd /Users/edward/Coding\ Agents/parallel-ai-agents
+mkdir -p papers
+echo "Test Paper About AI
+by John Doe
+
+This paper discusses artificial intelligence." > papers/test.txt
+```
+
+### 3. Check if It Worked
+
+Look for a file called `research-insights.md` in the docs folder:
+
+```bash
+cat docs/research-insights.md
+```
+
+If you see your test paper summarized there, it's working!
+
+### 4. Start the Frontend (Optional)
+
+In another terminal:
+
+```bash
+cd /Users/edward/Coding\ Agents/parallel-ai-agents/frontend
+npm run dev
+```
+
+Then open http://localhost:3000 in your browser.
+
+## What Success Looks Like
+
+- ✅ Backend processes your test.txt file
+- ✅ Creates/updates docs/research-insights.md
+- ✅ Frontend shows the paper summary at http://localhost:3000
+
+## If Things Go Wrong
+
+Common issues and fixes:
+
+**"command not found: npm"**
+
+- You need Node.js installed. Download from https://nodejs.org/
+
+**"OPENAI_API_KEY not set"**
+
+- The LLM features need an API key:
+  ```bash
+  export OPENAI_API_KEY="your-key-here"
+  ```
+
+**"Port 3000 already in use"**
+
+- Something else is using that port. The frontend will suggest another port.
+
+## The Docker Way (Advanced)
+
+If the above doesn't work, try Docker:
+
+```bash
+cd /Users/edward/Coding\ Agents/parallel-ai-agents
+docker-compose up
+```
+
+This starts everything in containers (whatever those are).
+
+## Getting Help
+
+If nothing works:
+
+1. Copy any error messages
+2. Ask Claude Code: "This error happened when I tried to test the parallel-ai-agents project: [paste error]"
+3. Or create an issue on GitHub (Claude Code can help with that too!)
+
+Remember: Not knowing how to test something is perfectly normal. Even experienced developers sometimes struggle with setup!