Can Google ADK Talk to Microsoft Foundry on Azure? A Cross-Cloud A2A Benchmark
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Step-by-step cross-cloud AI agent benchmark with Google ADK and Azure, highly actionable and directly relevant to multi-agent systems.
A cross-cloud benchmark demonstrates that a Microsoft Agent Framework coordinator hosted on Azure Foundry can successfully invoke a Google ADK agent on Cloud Run via A2A v1.0, with no framework-specific glue. The test measures three modes—MCP-only, A2A-only, and verified—revealing that protocol-version skew (A2A v0.3.0 vs v1.0) caused initial failures due to lack of negotiation, and that independent verification over A2A adds measurable latency but improves correctness when both clouds agree on the same Frankfurter API data. The project uses a domain layer of framework-independent Python with pydantic models and Decimal for math, avoiding LLM arithmetic entirely.