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 a tool registered with an outputSchema throws an error, the error is swallowed and a generic schema validation error is thrown instead.
THENEnsure that error responses from tools with output schemas always include the `isError: true` field. In SDK version 1.15.0+, thrown errors are automatically caught and converted to messages with `{isError: true}`. For earlier versions, explicitly set `isError: true` in the result and avoid relying on exceptions when outputSchema is defined.
IFWhen a tool is registered with an outputSchema and throws an error, the framework returns a misleading MCP error instead of the original error.
THENEnsure that when using outputSchema, errors thrown in tool calls either (a) upgrade to SDK version >= 1.15.0 where errors are automatically wrapped with isError and structuredContent, or (b) manually catch errors and return a response object containing both a text content field and a structuredContent field matching the outputSchema shape, with isError set to true.
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