Fetching from the wire…
01
02
03
04
05
06
07
08
Top 5 · 2026-05-17 · source-backed
The #1 production agent failure mode is context loss across sessions. Your agent works great for 20 minutes, then you close your laptop, and tomorrow it's forgotten everything. Google's ADK team published a tutorial on May 12 that addresses this directly with a pattern I think every agent builder needs to learn.
The core idea: stop treating conversation history as your state mechanism. Instead, define explicit state schemas (they use 6 named states with linear progression), persist checkpoints via DatabaseSessionService, and use event-driven webhooks with state_delta for atomic transitions. The agent doesn't poll. It doesn't maintain a conversation thread across days. It checkpoints its state, shuts down, and reconstructs context from the checkpoint when a webhook fires.
This is a state machine pattern, not a chatbot pattern. And that distinction matters more than it sounds. When you build agents as chatbots that remember, you get context drift, hallucinated progress, and ballooning token costs from replaying conversation history. When you build agents as state machines that checkpoint, you get deterministic resume and zero token waste on reconstruction.
I've been wrestling with this exact problem on a project where agents need to wait for external approvals that take hours or days. The ADK pattern of replacing conversation replay with compiled state views is the right architecture. Google also published a companion piece on tiered context engineering: Session (current conversation), Memory (persistent knowledge), and Artifacts (files and outputs), with explicit processors handling transformation and compaction at each tier boundary.
If you're building anything that runs longer than a single session, read both posts. The state machine pattern is how production agents will work. The chatbot pattern is how demos work.
Each link below shares sources, entities, or timing with this story.
Google released ADK / Shared entities / Shared topic / What happened next
Linked by a graph relationship (Google released ADK); both cover Google, When; overlapping topics (agent, google, session).
Google released ADK / Shared entity: Google / Same source domain / Shared topic / What happened next / Tension
Linked by a graph relationship (Google released ADK); both cover Google; reported by the same outlet (developers.googleblog.com).
Google released ADK / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Google released ADK); both cover Days, Google; overlapping topics (agent, doesn, session).
Google released ADK / Shared entities / Same source domain / What happened next
Linked by a graph relationship (Google released ADK); both cover Google, Session; reported by the same outlet (developers.googleblog.com).
Google released ADK / Shared entities / Shared topic / What happened next
Linked by a graph relationship (Google released ADK); both cover Google, When; overlapping topics (agent, google).
Linked by a graph relationship (Google released ADK); both cover Google, When; overlapping topics (agent, google).
Linked by a graph relationship (Google released ADK); both cover Google, When; overlapping topics (agent, google).
Google released ADK / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Google released ADK); both cover Google, Instead; overlapping topics (agent, google).