Memory hook: Session is now; memory is selected history.
Must remember
- ADK supports custom agent composition and tools. Choose large/small, managed/self-hosted and open/proprietary models according to task quality, security, latency, cost and operational control.
- Session state holds current interaction context; durable memory retains selected information across sessions. Managed sessions and Memory Bank help with lifecycle, but applications still need user/tenant isolation and deletion rules.
- RAG pipelines ingest, chunk, embed, retrieve, filter and rerank. Evaluate recall and relevance separately from generated-answer quality; use metadata and identity filters before exposing evidence.
- Agent Retrieval/Vector Search and database-backed retrieval serve different scale and access patterns. Keep embedding versions, index freshness and source identifiers aligned.
- Tools expose explicit schemas and bounded capabilities. Validate arguments and results, use timeouts and safe retries, and distinguish read-only retrieval from irreversible business actions.
- Agent Identity/Registry and supported MCP servers help discover and authorize capabilities. Discovery is not an access grant; authenticate each call and propagate the user context when needed.
Choose under exam pressure
| Requirement | Choice and reason |
|---|---|
| Remember a preference across sessions | A scoped durable memory record with consent, provenance and expiry where appropriate. |
| Retrieve current internal facts | Permission-aware RAG rather than relying on model weights. |
Traps
- A long context window is not a durable database.
- Similarity search alone cannot guarantee exact entity identity or authorized access.
Active recall
1. What distinguishes session state from long-term memory?
Session state supports the current interaction; long-term memory deliberately persists selected information.
2. Why rerank retrieved passages?
To improve relevance ordering after an initial broader retrieval.
3. What should a tool schema constrain?
Permitted arguments, types and required fields, supplemented by authorization and business validation.
4. How avoid cross-tenant memory leakage?
Enforce tenant/user partitioning and authorization on writes, retrieval and caches.
5. Why retain source identifiers?
To cite evidence, refresh changed content and remove deleted or unauthorized data.