
Build chat memory that knows its boundaries.
Separate session context, durable memory, and retrieved knowledge without losing user control.
Read the guideNeural Notes / Topic
Source-aware answers and contextual memory without losing provenance or permissions.
Read the RAG pipeline guide for document preparation, chunking, retrieval checks, and answer support. The chat-memory guide adds corrections, session scope, and durable settings. Together they show why information that looks relevant still needs an explicit source, access decision, and freshness policy.
Use this collection to compare how the same design question changes across tasks. Read the source-backed explanation before adapting an example. Identify which assumptions apply to your environment, which information is unavailable, and which checks must remain in ordinary application code. A reference pattern is a starting point for that review, not evidence that a connected service or deployment already exists.
Keep a small set of difficult cases as you explore: an incomplete input, conflicting evidence, a changed permission, and an operation whose result is uncertain. Record what should happen in each case. When you finish a guide, revisit those expectations instead of judging the design only by its most fluent answer. The linked articles offer complementary perspectives, so a useful reading order follows the consequences of your task rather than the publication date alone.

Separate session context, durable memory, and retrieved knowledge without losing user control.
Read the guide
Build a retrieval pipeline you can inspect, from document preparation to evidence-backed answers.
Read the guideChoose one article, outline the input and accepted outcome, and identify a failure the application must catch. Then connect that decision to the wider learning track.
Explore the companion track