Generative AI
SearchStart here

Module deck

Context, memory and multi-agent systems flashcards

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

Loading your cards...

Back to the module12 cards in this deck

Read all 12 cards as a list

Context engineering and memory

  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.

Multi-agent systems: when to use them and what they cost

  1. Front
    Multi-agent: when is it justified?
    Back
    When the work is broad and parallel, or when separate windows or distinct tools and permissions matter. Otherwise it adds tokens (Anthropic reported about 15 times a chat for its research system), latency and failure modes.
  2. Front
    Workflow vs agent vs multi-agent?
    Back
    Workflow: predefined code path. Agent: the model directs its own steps. Multi-agent: several coordinating agents. Choose the simplest structure that meets the bar.
  3. Front
    Why do long agent chains fail more often than their steps suggest?
    Back
    Errors compound: with independent steps, success is p to the power n. Illustrative: 0.9 over 8 steps is about 0.43. Use shorter chains, checks and checkpoints.

Agent evaluation: state, trajectory, pass^k and release gates

  1. Front
    What to trace per agent step?
    Back
    Prompt version, chosen tool and arguments, result, tokens, latency, cost and errors: enough to replay a failure.
  2. Front
    pass@k vs pass^k, and which fits a one-shot agent?
    Back
    pass@k: at least one of k runs succeeds. pass^k: all k succeed. A one-shot agent needs pass^k, which exposes the run-to-run variance that pass@k hides.
  3. Front
    Why grade an agent by state, not by its final message?
    Back
    The message is a claim and can be false. Check the world afterwards (the database row, the passing tests, the file), then use trajectory metrics for cost and risk.