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.
IFBedrock Guardrails configured with only post_call hook do not check input for harmful content.
THENConfigure both pre_call and post_call hooks to ensure guardrails apply to both input and output. This workaround addresses the inconsistency where the post_call hook only runs on output. Verify that both hooks are enabled in LiteLLM configuration for complete coverage.
IFWhen Bedrock guardrails are configured with `disable_exception_on_block: true` in `pre_call` mode, a blocked prompt's guardrail response (e.g., 'I cannot answer this question') is forwarded to the LLM instead of being returned directly to the user.
THENAvoid setting `disable_exception_on_block: true` with pre_call guardrails. Use the default (`false`) and handle the HTTP 400 exception in your client application (e.g., catch 400 errors in OpenWebUI or Claude Code). If you must suppress exceptions, apply only the post_call guardrail or wait for the pending LiteLLM fix that prevents the guardrail response from reaching the model when exceptions are disabled.
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