Agent Building Blocks - Q&A Review Bank

A consolidated review set for the module, grouped by chapter. Difficulty: [Easy] = recall, [Medium] = design decisions and trade-offs, [Hard] = system design, debugging and edge cases.

---

Tool Use

Q1: Who executes a tool call? [Easy] Your code. The model only proposes a call (name, arguments, id); the harness validates, executes and returns the result. Server tools (web search, code execution) are executed by the provider. See Tool Use & Function Calling.

Q2: What does strict mode guarantee, and what doesn't it? [Medium] Arguments that match the JSON Schema (via constrained decoding). It does not guarantee the values are correct - an id can be well-formed and wrong - so tools must still validate meaning, ownership and state.

Q3: How do you express an optional parameter in OpenAI strict mode? [Medium] Every property must be in required and objects need additionalProperties: false; make the optional field nullable, e.g. "type": ["string", "null"].

Q4: What belongs in a tool description? [Medium] What it does and when to call it; preconditions; where each argument's value comes from ("never guess ids"); what it returns; and which neighbouring tool to use instead for related requests.

Q5: Design a good tool error. [Medium] Say what failed, why, whether retrying can help, and what to do instead: "Order O1003 is shipped; only pending orders can be cancelled. Offer a return after delivery." Mark it as an error (is_error on Claude). Retry transient errors in the harness before the model sees them.

Q6: Why do write tools need idempotency keys? [Medium] Harnesses and agents retry after timeouts. A key derived from the episode and step makes a retried call return the original result instead of duplicating the side effect.

Q7: Your agent has 150 tools and picks the wrong ones. What do you do? [Hard] Consolidate overlapping tools around tasks; namespace them; use deferred loading with tool search so only relevant definitions are loaded; split tool groups across sub-agents or a router; measure selection accuracy before and after. Anthropic reported tool search raising MCP-eval accuracy from 49% to 74% on Opus 4.

Q8: What is programmatic tool calling and when does it help? [Hard] The model writes code that calls tools inside a sandbox; intermediate results stay in the sandbox and only the final output returns to the context. It helps when chaining many calls or filtering large intermediate data (Anthropic reported 37% fewer tokens on complex research tasks).

Q9: Is forcing a tool call with tool_choice portable? [Medium] No. Some newer models reject forced tool choice. Prefer auto plus an explicit instruction and a check that a call was made; use structured outputs when the forced call only existed to extract JSON.

---

Memory

Q10: Give the course's memory taxonomy. [Easy] Parametric (weights) vs external. External by scope: working memory (this call's context), task state (this thread, checkpointed), long-term (across sessions). Long-term by kind (CoALA): semantic (facts), episodic (experiences), procedural (how-to). See Agent Memory.

Q11: Compare hot-path and background memory writing. [Medium] Hot path: the agent calls memory tools during the conversation (Letta, Claude's memory tool) - immediate, but adds latency and depends on the agent's judgement. Background: a separate process extracts memories after the conversation (Mem0, LangMem) - no user-facing latency, consistent extraction, but memories lag.

Q12: How does Mem0 keep its memory store consistent? [Medium] For each extracted candidate fact it retrieves similar existing memories and chooses ADD, UPDATE, DELETE or NOOP, instead of appending contradictory facts.

Q13: What problem do Zep's temporal knowledge graphs solve? [Medium] Facts that change over time: each fact carries a validity interval, so a superseded fact is marked invalid rather than deleted, supporting temporal questions and preserving history.

Q14: What techniques manage working memory in a long episode? [Medium] Trimming, truncating or paginating tool outputs, context editing (clearing stale tool results), compaction (summarising history), offloading large results to files or state, and a pinned task summary.

Q15: What is memory poisoning and how do you defend against it? [Hard] Getting false facts or instructions stored so they influence future episodes - via documents, web pages or crafted queries (AgentPoison, MINJA). Defend by treating memories as data not instructions, storing provenance, validating before writing, gating procedural-memory updates, and namespacing per user.

Q16: A user asks to be forgotten. What must you delete? [Hard] Everything derived from them in every store: semantic and episodic memories, vector-index entries, graph nodes and edges, summaries and consolidated memories, caches, and logs per retention policy - keyed by user namespace.

---

Planning & Reasoning

Q17: How do reasoning models change agent planning? [Medium] They reason internally, including between tool calls, so prompting for visible "Thought:" lines is unnecessary; use effort settings and keep reasoning items in the history. The harness still owns durable plans (todo lists in state) for compaction, approval and resume. See Planning & Reasoning.

Q18: Compare ReAct and plan-and-execute. [Medium] ReAct interleaves reasoning and actions step by step - adaptive but myopic on long tasks and re-reads the full history each step. Plan-and-execute writes an explicit plan, executes it (often with a cheaper model) and re-plans on failure - reviewable and efficient, but brittle if early findings should change later steps.

Q19: What do ReWOO and LLMCompiler add? [Medium] ReWOO plans all tool calls up front with placeholders, so observations aren't fed back to the planner each step (fewer tokens). LLMCompiler plans a dependency graph and runs independent calls in parallel (lower latency).

Q20: When does reflection help an agent? [Hard] When driven by an external failure signal (tests, validation, environment reward) as in Reflexion, or by an evaluator with different information (a rubric, sources). Asking a model to re-check its own reasoning with nothing new is unreliable (Huang et al., 2024).

Q21: When should an agent re-plan? [Medium] On a non-retryable failure, a result contradicting a plan assumption, a changed goal, or stalled progress - not after every step.

---