About Signal Lens

Signal Lens is an AI knowledge hub and interactive learning space — a personal reference and a shareable resource for making sense of the fast-moving AI landscape.

What you'll find here

The site is organised around five sections, each covering a different layer of working with AI:

• Tools — Reviews of AI tools across categories: coding assistants, chat interfaces, image and video generators, audio tools, local models, and APIs. Each review includes personal ratings, pricing notes, and practical observations from real use.
• Models — Structured profiles of major AI models covering capabilities, context windows, pricing, API access, and what each model is actually good for.
• Prompts — Tested prompt templates for development, analysis, and creative work — with variable slots, usage notes, and example output.
• Concepts — Interactive explainers of how AI works under the hood. Attention mechanisms, tokenization, embeddings, transformers, RAG, and more — each with live visualizations you can explore directly in the browser.
• Use Cases — Real-world AI workflow patterns documented from practice: architecture decisions, database migrations, backend performance, and other applied patterns.

How it's built

Signal Lens is itself an AI-collaborative project — designed, built, and maintained with Claude Code. The site is static (Astro + React islands), deployed to Cloudflare Pages, and every piece of content is a Markdown file in a Git repository. No CMS, no database — just files and code.

The interactive concept visualizations are built with Three.js and React. The content schemas are type-safe with Zod. Every push to the main branch triggers an automatic deployment.

A living project

The AI landscape moves fast. Models change, tools appear and disappear, and understanding deepens. This site is updated continuously to reflect what's actually current — not as a publication, but as a working reference.