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
1
Categories
2258
Tier-1 (public)
4,089
Tier-2 (your patterns)
private to your site
thinking_with_tools
ai-agents-thinking-with-tools-when-using-claude-reasoning-models-with-thinking-e-8351ffe5
IFWhen using Claude reasoning models with thinking enabled and tools defined, the API returns an error because an assistant message after a tool_use result does not start with a thinking block.
THENDisable thinking mode when using tools, or ensure that your application (or proxy like LiteLLM) inserts a thinking block at the beginning of every assistant message that follows a tool result. As an alternative, use the default tool calling mechanism instead of native tool calling.
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