docs: integrate 2025 benchmark insights and standard MCP Web Component examples

[jgoldfoot]

🎯 What
This PR introduces a strategic update proposal synthesizing 2025 AI Agent industry benchmarks (e.g. the 20-40% benchmark-to-production gap) and the widespread adoption of the Model Context Protocol (MCP). It adds a concrete code example demonstrating a unified, standards-based Web Component using the ElementInternals API for the Accessibility Object Model (AOM) alongside native <link> tag discovery for MCP. The core methodology in whitepaper.md and README.md have also been updated to incorporate these insights.

💡 Why
As AI Agent ecosystems evolve rapidly, the BiModal Design framework must reflect the latest benchmark realities and standards. Public benchmarks (like WebArena) do not fully predict production success, creating a 20-40% performance gap that requires stronger Layer 2 defense-in-depth strategies. Additionally, the proliferation of MCP makes Layer 5 standard discovery critical. By using ElementInternals and native <link> tags, we ensure robust agent accessibility without relying on brittle custom attributes.

✅ Verification

• Validated via npm run format, npm run lint, and npm test successfully.
• Code Review confirmed the solution correctly targets the guidelines and adheres to standard-based patterns without custom attributes.
• Read contents of modified README.md and docs/whitepaper.md via diff to ensure accurate patching.

---

PR created automatically by Jules for task 4345801612010651327 started by @g0ldf7

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.