Generative AI
SearchStart here

Lesson deck

Context engineering and memory flashcards

Reviewing needs JavaScript. You can read every card in the list below.

Loading your cards...

Back to the lesson6 cards in this deck

Read all 6 cards as a list
  1. Front
    What are the four agent memory types, with one storage example each?
    Back
    Working (the window or a rolling summary), episodic (timestamped summaries of past interactions in a vector store), semantic (facts in a profile or key-value store), procedural (instruction or skill files). A teaching split, not a standard.
  2. Front
    The four context-engineering moves?
    Back
    Write (persist outside the window), select (bring in only what is relevant now), compress (summarise or trim), isolate (give a sub-task its own clean context and take back a short result).
  3. Front
    How do you lay out a prompt for caching, and what breaks it?
    Back
    Stable content first (tools, system rules, reference documents), variable content last. A change at one level invalidates it and everything after it: a new tool invalidates the whole cache, and a timestamp at the top of the system prompt invalidates the system prompt and what follows.
  4. Front
    A summary made the agent forget a constraint. What is the fix?
    Back
    This is drift. Pin must-keep rules verbatim in the system prompt or a note that compaction never rewrites, and test with a probe question about each pinned fact after every compaction.
  5. Front
    What does a memory design have to answer besides what to store?
    Back
    When to write, how to recall (similarity plus recency and importance), how to update and expire, and how to delete one user's data from records, summaries and embeddings. Treat recalled memory as untrusted data, not as instructions.
  6. Front
    Overflow, distraction, drift, tool-output bloat (course taxonomy): what does each measure look like?
    Back
    Overflow: tokens per step against the limit. Distraction: accuracy with and without the extra context. Drift: probe questions after compaction. Bloat: share of tokens from tool results and p95 tokens per call.