Agent Systems · core
Tool Calling
Letting an LLM invoke functions/APIs via structured calls.
Mental model
Tool calling turns the LLM into a planner: it emits a structured request to a named tool, your code executes it, and the result goes back into context. The model never runs code — it decides what to run.
How to study Tool Calling
Begin by restating the mental model in your own words, then connect it to a concrete system you have built or operated. Name the mechanism, the constraint it addresses, and the trade-off it introduces. Use Anthropic — Tool use to check details, but close the source before writing your explanation. Retrieval is the learning step; rereading is only preparation.
Next, compare Tool Calling with Agent Loops, RAG. Ask what changes in correctness, latency, resource use, operability, and failure recovery. Complete Build a tool-calling loop and preserve the command, input, output, and one failed attempt as evidence. Finish by explaining the idea without jargon to someone who has not studied the track.
Proof of understanding
- Explain the mechanism from first principles and identify the state it reads or changes.
- Give one situation where the concept is the right choice and one where it is not.
- Predict a realistic failure mode before running the drill, then compare the prediction with evidence.
- Connect the result to a roadmap or build artifact instead of treating the concept as isolated trivia.
Where it matters
MCP servers, agent frameworks, Claude/OpenAI tool use.
Common mistakes
- Vague tool descriptions, so the model picks the wrong tool
- No error handling for failed tool calls
- Letting tools take dangerous actions without approval
Learn from primary sources
- Anthropic — Tool use (doc)
Practice and explain it back
Build a tool-calling loop
Give an LLM two tools (e.g. search and calculator). Run a loop: model emits a tool call, you execute it, feed the result back, repeat until done.
Expected evidence: A task solved across multiple tool calls.
Open the interactive drill →Review prompts
- In tool calling, what does the LLM actually do — and not do?
Build evidence
Synthesize: Agent Systems
Engineer useful agents with bounded loops, tools, memory, protocols, durability, permissions, and long-running control. Produce one working system, benchmark, or evidence-backed design that integrates the path.
- Implements or precisely models the core mechanisms from all three milestones
- Includes at least one injected failure or adversarial case and demonstrates recovery
- Reports quality, latency, resource, reliability, or usability measurements relevant to the domain
- Ships a concise architecture note explaining decisions, trade-offs, and remaining risks