Skip to content
The AI Tech Lead Path
The path
0413 min read · 170 XP

Agents, tools & MCP

When to let the model act — and when not to.

0%

Agents let a model plan, call tools, observe results and loop. They're powerful and over-hyped. Your job is to know when an agent is the right tool, how to build one safely, and how to keep it bounded.

Key ideas

  1. 1

    The agent loop: plan → act (call a tool) → observe → repeat until done. Tools are how the model affects the world.

  2. 2

    Prefer the simplest thing that works: a single well-prompted call or a fixed workflow often beats a free-roaming agent. Reach for agents when the path is genuinely dynamic.

  3. 3

    MCP (Model Context Protocol) is the emerging standard for exposing tools/data to models — learn it; it's how you'll integrate enterprise systems.

  4. 4

    Bound your agents: limited tool scope, allow-lists, sandboxing, step/time/cost limits, and human-in-the-loop for risky actions.

  5. 5

    Agents amplify failure modes: prompt injection via tool output, runaway loops, and cost blowups. Observability and guardrails are mandatory.

Workflow vs agent

  • Workflow: you orchestrate fixed steps (predictable, testable, cheaper) — default choice.
  • Agent: the model decides the steps (flexible, needed for open-ended tasks) — use when the task space is dynamic.
  • Many 'agents' should be workflows with one or two tool calls.

Building them safely

  • Scope tools tightly; treat every tool as an attack surface.
  • Sandbox side-effects; require approval for irreversible/expensive actions.
  • Cap steps, time and spend; trace every tool call for debugging and audit.
  • Treat tool outputs as untrusted input (indirect prompt injection).

Watch

How we build effective agentsBarry Zhang, Anthropic
Model Context Protocol (MCP), explainedFind it on YouTube →

Do the work

0/4 · 0%

Test yourself

Question 1 / 3

What is the agent loop?

27 chapters · progress saves automatically