Skip to content

Latest commit

 

History

History
30 lines (23 loc) · 2.03 KB

File metadata and controls

30 lines (23 loc) · 2.03 KB

Agentic Application Patterns and Framework Support

Overview

Modern agentic AI applications follow various architectural patterns. This guide shows which patterns each framework supports and how Monocle instruments them.

Agentic Patterns

  • Single Agent - One agent handles all tasks
  • Multi-Agent Sequential - Agents work in sequence, passing results
  • Multi-Agent Parallel - Agents work simultaneously
  • Orchestrator/Supervisor - Coordinator agent manages specialized sub-agents
  • Agent Delegation/Handoffs - Agents transfer control to other agents (different frameworks use different terms: handoffs, handoff_to_*, transfer_to_*)
  • Session/Thread - Multi-turn conversation context preservation

Framework Support and Monocle Instrumentation

Framework Single Sequential Parallel Orchestrator Delegation/Handoffs Session/Thread Monocle Support
Google ADK
SequentialAgent

ParallelAgent

LoopAgent

Built-in

session_id
Full
LangGraph
Supervisor

transfer_to_*

thread_id
Full
OpenAI Agents ⚠️
handoffs=[]

thread
Full
Microsoft Agent Framework ⚠️
handoff_to_*

thread
Full
LlamaIndex ⚠️ ⚠️
session_id
Partial ⚠️
CrewAI
Sequential

Hierarchical
⚠️ Partial ⚠️
Strands ⚠️ ⚠️ ⚠️
session_id
Partial ⚠️
LangChain ⚠️ ⚠️ ⚠️ Basic ⚠️
Haystack
Pipeline
⚠️ ⚠️ ⚠️ Basic ⚠️

Legend: ✅ Full support | ⚠️ Partial/Limited | ❌ Not supported