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 site_1.create in the request path for every Managed site_2 session
THENsite_1 are persistent objects — create once, reference by ID. Store the agent ID returned by site_2.create and pass it to every subsequent sessions.create. Do not call site_3.create in the request path.
IFUsing Managed site_1 for stateful, multi-turn tasks with persisted configs.
THENCreate site_1 once and store the returned agent ID. Use that ID in every subsequent sessions.create call; do not call site_2.create in the request path. Use the Anthropic CLI for creating site_3 and environments from version-controlled YAML. C# users must use cURL-style raw HTTP as Managed site_4 is not supported in the C# SDK.
IFCode in the request path calls `site_1.create` (or equivalent) to create a Managed Agent instead of reusing a previously stored agent ID.
THENStore the agent ID returned by `site_1.create` and pass it to every subsequent `sessions.create`. Do not call `site_2.create` in the request path; site_3 are persistent objects and should be created once, then referenced by ID. The Anthropic CLI can help manage site_4 from version-controlled YAML.
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