Agents & Tool Use

Models that act: function calling, agent loops with memory and planning, and how to measure long-horizon autonomy without fooling yourself.

3 lessons • 26 min read

1. 01

   Tool use and function calling

   A language model can only emit tokens. "Tool use" is the set of conventions that let some of those tokens be read as a request to run code, search, or call an API, and that feed the result back as more context. It is the mechanism behind every agent, and the place where most agent security problems begin.

   8 min read
2. 02

   Agent loops: planning, memory and long-horizon tasks

   An agent is a model that decides its own next step, takes it, looks at the result, and repeats until it judges the task done. This lesson covers the structure of that loop, why long tasks are hard for it, and the methods (planning, memory, sub-agents and verification) that let 2026 agents work for hours instead of minutes.

   9 min read
3. 03

   Evaluating agents: benchmarks, time horizons and their pitfalls

   How do you measure whether an agent can do a job, when the job takes hours, has many valid solutions, and is graded by software the agent can sometimes manipulate? By late 2026 the leading agent benchmarks had either saturated, been found contaminated, or needed audits to separate real successes from exploits. Reading agent results well now means understanding how they are made.

   9 min read