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
prompt_linking_langchain
observability-prompt-linking-langc-prompt-linking-in-langfuse-traces-fails-or-produce-2692fee6
IFPrompt linking in Langfuse traces fails or produces 'Unsupported message type' error when using LangChain V1 site_1 with `langfuse_prompt` metadata in the invoke config.
THENSet the `langfuse_prompt` metadata on the `ChatPromptTemplate` object itself, not in the invocation config. Create a `ChatPromptTemplate` from the Langfuse prompt using `get_langchain_prompt()`, then set its metadata: `ChatPromptTemplate(..., metadata={'langfuse_prompt': langfuse_prompt})`. For site_1, format messages manually and omit the metadata from config. Do not pass a `ChatPromptTemplate` as messages directly.
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