Pattern preview · 12 of 4,089 sample rules shown · site-specific intelligence stays private
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.
Sample rules shown
2
Categories
2258
Tier-1 (public)
4,089
Tier-2 (your patterns)
private to your site
unsupported_params
ai-agents-unsupported-params-when-using-a-non-anthropic-model-e-g-vercel-ai-gat-cb1bffc7
IFWhen using a non-Anthropic model (e.g., vercel_ai_gateway) with the 'thinking' parameter enabled, LiteLLM returns a 500 error indicating the parameter is unsupported.
THENConfigure LiteLLM to either drop unsupported parameters by setting 'litellm.drop_params=True' in the proxy configuration, or explicitly allow the 'thinking' parameter by sending 'allowed_openai_params=['thinking']' in the request. For the proxy, add 'drop_params: true' under 'litellm_settings' in the config.
Tier 170%
unsupported_params
ai-agents-unsupported-params-claude-code-fails-with-500-error-when-using-vercel-1889f8d2
IFClaude Code fails with 500 error when using Vercel AI Gateway model with thinking enabled.
THENSet 'litellm.drop_params=True' in the proxy config or pass 'allowed_openai_params': ['thinking'] in the request to allow the thinking parameter for non-Anthropic model providers that do not support it natively.
Tier 170%
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