surface_selectionTier 1 · 70% confidence

ai-agents-surface-selection-determining-which-claude-surface-single-api-call-t-38cc2276

agent: ai_agents

When does this happen?

IF Determining which Claude surface (single API call, tool use, Managed site_1) to recommend for a new project

How others solved it

THEN Use the decision tree: first check if deploying via third-party (Bedrock/Vertex/Foundry) → Claude API only. For a single LLM call (classification, extraction, Q&A) → Claude API. For multi-step pipelines with code-controlled logic → Claude API + tool use. For server-managed stateful site_1 with workspace, persisted configs, or long-running turns → Managed site_2. Default to the simplest tier that meets needs.

Related patterns

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics