02 // Resources

Technical assets, ready to reuse.

Reference architectures, working code, and templates from real enterprise AI engagements — the artifacts behind the writing, packaged to be lifted into your own programs.

Code13 July 2026

ADK eval harness starter

A minimal, extensible evaluation harness for agents built on Google's Agent Development Kit — run a dataset against an agent, capture traces, and score outcomes.

adk
agents
evaluation
python

Architecture13 July 2026

Reference architecture: enterprise agentic AI platform

A layered reference architecture for running agentic AI in a large enterprise — channels, agent orchestration, grounding, and the governance plane that makes it production-viable.

agents
architecture
google-cloud