Skip to main contentSkip to footer
Examples

Browse by problem

Find examples by the agentic design failure mode they prevent.

Delegation failures

Examples in this group address agents that act without a clear boundary: taking destructive actions without approval, assuming intent from incomplete context, or proceeding past failure without surfacing it. Look for examples tagged with the delegation cluster principles.

Visibility failures

Visibility failures include: background tasks that run silently with no progress feedback, async operations that complete with no confirmation, and agents that show internal state (log lines, token counts) instead of meaningful operational state. Examples in this group show the correct pattern for each failure type.

Trust and orchestration failures

Trust failures: actions that cannot be undone, handoffs without explicit user awareness, and approval flows that are bypassed under time pressure. Orchestration failures: pipelines that do not degrade gracefully, subagent errors that surface as generic failures, and output types that are not inspectable. Use search_examples via MCP to filter by cluster.

Model calls and outputs31

Agent patterns12

Workflow and orchestration8

MCP tool use14

Knowledge and retrieval11

Framework integrations10

Context management10

Also in this section