AI Agents Explained: the Thought-Action-Observation Loop

An engineer demonstrates how AI agents use a Thought-Action-Observation loop to solve multi-step tasks by calling tools like calculators and search. The agent iterates until completion, with each real observation fed back into context to guide subsequent decisions. The implementation includes safety measures such as iteration caps and input validation.

A chatbot answers in one shot. An AI agent runs in a loop, uses tools, and acts — Thought → Action → Observation → repeat — until the job's done. Watch one solve a multi-step task by calling a calculator and a search. 🤖 Run the agent: https://dev48v.infy.uk/ai/days/day11-agents.html https://dev48v.infy.uk/ai/days/day11-agents.html You describe tools to the model name, purpose, arguments . It can't divide big numbers reliably or know today's data — but it CAN decide "call the calculator with this expression". Tools cover the model's weak spots. js while true { const step = await llm history ; // model emits a Thought + Action if step.type === "answer" return step.text; const result = tools step.tool step.args ; // run the tool history += Observation: ${result} ; // feed the real result back } The model writes a Thought plan , emits an Action tool + args , your code runs it and returns an Observation , which goes back into context. Then it thinks again. Each observation is REAL, fed back before the next decision — so it's not guessing the tip amount, it sees 126 from the calculator. And it plans the steps itself: "population of France's capital, doubled" becomes search → then calculator, chained because the model worked out the dependency. Cap iterations no infinite loops , validate tool inputs, gate risky actions email, payments behind approval. Autonomy is the point; limits make it safe. Run a task https://dev48v.infy.uk/ai/days/day11-agents.html and watch the Thought→Action→Observation trace build.