solo-developer

Multi-agent system for news aggregation

Semantic KernelAutoGenFastAPIAzure Cosmos DBAzure AI SearchAzure Maps WeatherBing SearchAzure Communication ServiceStreamlitOpenAI WhisperOpenAI TTSAzure AI Evaluation SDK
Stack tools12
AddedMar 2026
StatusPublished

Achieved functional correctness metrics >3.0 pass threshold across IntentResolution, TaskAdherence, ToolCallAccuracy; strong correlation between tool calls and token usage; proof-of-concept for automating campus event workflows

solo-developer

Why they built it

To automate complex manual campus event processes like resource allocation, conflict-free scheduling, cost estimation, and participant communication burdened on staff.

What worked

AgentGroupChat pattern for multi-agent collaboration; automation of scheduling/budgeting/communication; high functional correctness scores exceeding pass thresholds

What broke or was painful

High token consumption in multi-turn coordination; reliance on engineered prompts limiting flexibility; variable latency in complex tasks; limited testing on synthetic data

The result

Achieved functional correctness metrics >3.0 pass threshold across IntentResolution, TaskAdherence, ToolCallAccuracy; strong correlation between tool calls and token usage; proof-of-concept for automating campus event workflows

References