gamussa/langchain4j-agentic
Build and demo Java AI agent systems with langchain4j-agentic: workflow patterns, supervisor, custom Planner strategies (incl. the flagship typed-verdict / CriticResult-style critic pattern), plus MCP tools, A2A remote agents, build setup, and conference-demo storylines. Pinned to 1.15.0 / 1.15.0-beta25.
84
89%
Does it follow best practices?
Impact
100%
4.76xAverage score across 2 eval scenarios
Passed
No known issues
Evaluation results
100%
87%Parallel Article Quality Pipeline
Parallel batch processing with iterative loop refinement
No ChatMemory on parallel sub-agents
33%
100%
Explicit Executor provided
33%
100%
loopBuilder sets maxIterations
0%
100%
loopBuilder has exitCondition
0%
100%
parallelMapper fan-out over the batch
0%
100%
AgentMonitor and HtmlReportGenerator
0%
100%
outputKey not outputName
30%
100%
100%
70%Travel Itinerary Builder with Verification
CriticResult typed-verdict verify-adjust system
Typed inter-agent verdict object
100%
100%
No bare score/double
100%
100%
Typed solution record
100%
100%
Planner method signatures
0%
100%
call() and done() helpers
0%
100%
outputKey not outputName
0%
100%
HtmlReportGenerator at end
0%
100%
-parameters compiler flag
0%
100%
Beta artifacts pinned explicitly
0%
100%
Core BOM or explicit 1.15.0
0%
100%
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6