Google Agent Development Kit

Google Agent Development Kit, or ADK, is Google's framework for building agents. In ^[src-101], the Google Developers Blog uses ADK to show how production agents can pause, resume, persist workflow state, and survive multi-day enterprise processes.

Key facts

Publisher: Google / Google Developers Blog ^[src-101]
Use case in source: A long-running new-hire onboarding coordinator agent ^[src-101]
Architecture pattern: durable state machine, persistent sessions, event-driven dormancy gates, and multi-agent delegation ^[src-101]
Production lesson: ADK is framed as a way to move beyond stateless chatbots into recoverable workflow agents that can wait on human approvals or external events ^[src-101].
Cross-language update: Google shows ADK orchestrating a Python extraction agent and a Go validation agent connected through Agent To Agent Protocol ^[src-145].
July 2026 assessment: sessions, state, memory, multi-agent composition, evaluation, MCP and A2A make ADK broad, while cross-vendor A2A operations remain comparatively young ^[src-252].

Related entities

Related concepts

Source references

^[src-101] Shubham Saboo and Eric Dong – "Build Long-running AI agents that pause, resume, and never lose context with ADK" (2026-05-12)
^[src-145] Shubham Saboo and Eric Dong – "Build Cross-Language Multi-Agent Team with Google's Agent Development Kit and A2A" (2026-06-22)

Robin Cartier perspective

This page is part of Robin Cartier's working AI knowledge graph: a practical research layer for production AI, recommendation systems, experimentation, GEO, and agentic web readiness.

The useful next step is to connect this concept back to applied product leadership and operating models.

Recommended next

Keep reading from this thread

From 477 indexed pages and articles.