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.
IFCalling getLangchainPrompt() without resolving all placeholders causes Langchain error because unresolved placeholders are returned as {variableName, optional} instead of {type: 'placeholder', name: ...}.
THENUpgrade to Langfuse JS/TS SDK v4.2.0 or later, where the issue is fixed. If upgrade not possible, manually transform the output: map objects with variableName and optional to { type: 'placeholder', name: msg.variableName } before passing to ChatPromptTemplate.fromMessages().
IFWhen using getLangchainPrompt without providing all placeholders, the SDK returns unresolved placeholders as { variableName, optional } objects instead of Langchain's expected { type: 'placeholder', name } format, causing ChatPromptTemplate.fromMessages to throw an error.
THENManually map unresolved placeholder objects by converting { variableName, optional } to { type: 'placeholder', name: variableName } before passing to Langchain, or upgrade to Langfuse JS/TS SDK v4.2.0+ where the issue is fixed. Example: const fixedMessages = rawMessages.map(msg => msg.variableName ? { type: 'placeholder', name: msg.variableName } : msg);
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