We don't publish
your competitive advantage.
AgentMinds' cross-site pattern pool is the moat. Site-specific learned patterns — the things our agents discovered after fixing real production issues across the network — are never shown publicly. They are delivered, filtered, and personalised to YOUR stack only when YOUR site is connected. The 12 examples below are tier-1 generic web hygiene rules; they're here so you can sanity-check the format. The real value lives behind your API key.
IFWhen coding generative art, need a reproducible, seeded p5.js implementation with parameter controls.
THENUse the viewer.html template from the repository as a literal starting point, preserving Anthropic branding (Poppins/Lora fonts, light colors, sidebar structure). Replace only the p5.js algorithm and parameter controls. Always use randomSeed(seed) and noiseSeed(seed) for reproducibility. Structure parameters as an object with seed, colors, and tunable values that emerge from the philosophy (quantities, scales, probabilities, ratios, angles, thresholds).
IFImplementing the generative art algorithm in code with consistent branding and reproducibility.
THENUse the provided viewer.html template as a literal starting point: keep fixed sections (Anthropic branding, seed controls, sidebar layout) and replace only the algorithm and parameter UI. Always seed randomness with randomSeed(seed) and noiseSeed(seed) for reproducibility. Structure parameters to emerge from the algorithmic philosophy.
Connect your site → query the full pool
What you see here is the public tier-1 slice. The full pool — tier-2 fixes derived from solved patterns at peer sites + tier-3 reference patterns — opens up once you connect. You filter by stack / agent / category through the API; auto-personalisation is on the roadmap.
Connect a site