Agents & Tool Use

Function calling, ReAct loops, MCP, agent memory architectures and evaluation harnesses.

15concepts
169flashcards
117minutes of reading
  1. 01 Agent Frameworks Compared LangGraph, CrewAI, AutoGen, and the OpenAI Agents SDK solve different problems; the harder question is whether you need a framework at all. intermediate 9m 5 cards
  2. 02 Agent Skills and Progressive Disclosure Packaging agent expertise as folders of instructions and scripts that load in layers, so a hundred specialisations cost a few hundred tokens until one of them is actually needed. intermediate 6m 15 cards
  3. 03 Agent-to-Agent Interoperability MCP standardises how one agent reaches tools and data; A2A standardises how two independently built agents discover each other and collaborate as peers, which is a different problem with a different failure surface. intermediate 6m 15 cards
  4. 04 Model Context Protocol (MCP) The open standard that replaces bespoke per-tool integrations with one protocol, so any compliant client can talk to any compliant server. intermediate 8m 5 cards
  5. 05 Planning and Task Decomposition in Agents Why an LLM that reasons well step by step still fails to produce a valid multi-step plan, and how decomposition, external planners, and replanning close the gap. intermediate 8m 15 cards
  6. 06 Tool Use and Function Calling How models invoke external tools to fetch data, run code, and take actions in the world. intermediate 7m 5 cards
  7. 07 Agent Evaluation Harnesses Single-output accuracy says nothing about an agent that takes thirty steps; evaluating agents means scoring trajectories, environment state, and reliability across runs. advanced 10m 5 cards
  8. 08 Agent Memory Architectures An agent whose only memory is its context window is amnesiac between sessions; persistent memory is the architecture that decides what to keep, where, and how to retrieve it. advanced 10m 5 cards
  9. 09 Agentic AI and ReAct From single tool calls to multi-step agents that plan, act, observe, and recover from errors. advanced 9m 6 cards
  10. 10 Code Execution as a Tool Interface Instead of calling tools one at a time through the context window, the agent writes code against tool APIs in a sandbox, which cuts both tool-definition overhead and intermediate results out of the token budget. advanced 7m 18 cards
  11. 11 Computer-Use Agents: Operating a GUI Through Pixels How agents that click and type on a real desktop differ from tool-calling agents, why GUI grounding is the bottleneck, and what OSWorld measured that API benchmarks cannot. advanced 8m 15 cards
  12. 12 Durable Agent Execution and Recovery Long-running agents fail mid-task for mundane reasons, so the loop needs checkpointed state, idempotent side effects, and the ability to resume from a step rather than restart from the prompt. advanced 6m 15 cards
  13. 13 Long-Horizon Agent Reliability Why per-step accuracy compounds into task failure, how METR's time-horizon metric reframes agent capability, and which architectural moves actually raise the exponent. advanced 8m 15 cards
  14. 14 Orchestrator-Worker Subagent Architectures A lead agent decomposes a task and spawns subagents with clean context windows that explore in parallel and return compressed summaries, buying breadth and context isolation at a large token cost and a coordination risk. advanced 7m 15 cards
  15. 15 Sandboxing and Least Privilege for Agents Why agent security has to be enforced outside the model, how capability scoping and human-in-the-loop gates work, and what the CaMeL design proves about the limits of prompting. advanced 8m 15 cards