Skip to content
Agents and protocols

The agent loop

How a model works through a task: think, use a tool, read the result, and go round again.

Intermediate · 6 steps

Read first:Tool callingIn-context learning

Step 1 of 6· Scripted, illustrative trace and tools; the loop, budget, gate and stop logic work as described

in one minute

A chatbot answers once. An agent works in a loop. Given a goal and a set of tools, the model writes a short thought about what to do next, then asks for a tool to be run, such as looking up an order. Ordinary software runs the tool and adds the result to what the model can see, and the model decides again. The loop ends when the model says it has finished, or when a fixed step budget runs out. Anything that cannot be undone, such as sending money, should wait for a person to approve it. One influential research version of this pattern is ReAct: reasoning plus acting.

Why it matters for your product

Every pass is another model call, so agents cost more and take longer than a single answer, and small errors compound. On τ-bench, a customer-service benchmark, even GPT-4o completed under half the tasks, and under a quarter of retail tasks succeeded in all of eight repeat trials. So give agents a hard step budget, the narrowest tool permissions that work, and a human approval for anything that moves money or data. Anthropic advises starting with the simplest design that works; we usually try a fixed workflow before a free-running agent.

For engineersShow the maths

cₜ = (o₁, a₁, …, oₜ₋₁, aₜ₋₁, oₜ); aₜ ~ π(aₜ | cₜ)

At step t the agent's context c is everything it has seen and done so far, and the model π picks the next action from it. ReAct lets a thought count as an action too: it adds to the context but gets no observation back.

Worked example: After three passes, each with one thought, the context holds the goal plus 3 thoughts, 3 actions and 3 observations: 9 new entries.

repeat until action = finish or steps = B

The two stop conditions every loop needs: the model's own decision that it is done, and a hard budget B that the harness enforces whatever the model says.

Worked example: With B = 6 and a search tool that always comes back empty, the run makes its sixth call and is stopped: 6 of 6 steps, no refund sent.

P(whole run succeeds) = pⁿ

If each of n steps succeeds independently with probability p, the run succeeds only when every step does. Real failures are often linked, so treat this as a rough guide.

Worked example: p = 0.95 and n = 6: 0.95⁶ ≈ 0.74, so about one run in four fails.

where it stops working

A loop does not make a model wiser: one misleading tool result or wrong early thought can steer every later step, and in ReAct's error analysis on HotpotQA, unhelpful search results caused 23% of failures. Budgets and approvals limit the damage but do not make the agent right.

Key terms

The words you will hear

Agent

A model that chooses its own next step in a loop, including which tool to use and when to stop, instead of following a fixed script.
Where it came from

Primary sources

  1. 01ReAct: Synergizing Reasoning and Acting in Language ModelsYao et al. · 2022
  2. 02Building effective agentsSchluntz and Zhang · 2024
  3. 03τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World DomainsYao et al. · 2024
  4. 04LLM06:2025 Excessive AgencyOWASP Gen AI Security Project · 2025

Want this working on your data?

We design and build the systems these ideas power: retrieval, agents, voice and the models behind them. Start with a free discovery call.