Chapter 01 of 12 · Aishwarya Ashok
Peanut gets a job
Begin with the model, then follow what changes when software can act. A predictable workflow and an agent can use the same model; the difference is who decides the next step.
A large language model is a machine-learning model trained on large amounts of data to process and generate language.
A generative language model produces a response from the input it receives, using patterns learned during training. That response may be prose, code, or a structured tool request. To turn a proposed repair into an action, an application needs tools and software to run them. This distinction becomes useful as soon as we start building agents.
Training adjusts a model's learned parameters; inference uses a trained model to produce outputs from new inputs.
Training is where the model's parameters change through an optimization process. Inference is where the trained model computes a response. A document added to a prompt supplies information for that response; retraining would change the model itself. For a builder, this helps separate two decisions: what information to provide now, and whether additional training is warranted.
A system that uses an AI model to choose and carry out actions toward a goal.
In an agent system, the model chooses an action and the surrounding software executes it through a tool. The result returns to the model, which can choose another action, ask for help, or finish. You supply the goal and constraints. How much the agent can do along the way depends on its available tools, permissions, and stopping rules.
A workflow whose next steps are determined by predefined rules and its inputs or state.
A predefined workflow can include branches, loops, and error handling. What makes its control logic deterministic is that the same relevant inputs and state select the same path. This is useful when the process is understood well enough to encode. A variable model response or changing external data can still produce different outcomes inside that fixed structure.
A process that includes model-driven decisions or actions, often alongside predefined software steps.
You can introduce model judgment at one useful point in an otherwise fixed process. An incoming request might follow standard intake steps, then use a model to choose its handler. “Agentic workflow” is used broadly, so identify the actual decision the model owns. That tells a builder more than the label alone.
The degree of freedom an agent has to make decisions and take actions without further human input.
You might let a research agent browse freely while requiring approval before it emails a customer. That is a choice about autonomy.
Make the permitted decisions explicit, then support those boundaries with tool permissions and review gates. The agent’s freedom should fit the job it has been given.
The repeated cycle of model decision, action execution, and observation that moves an agent's work forward.
Each tool result supplies evidence for the next model decision. A failed repair may lead to a different action; a successful check may end the run. The surrounding software keeps this cycle moving and applies stopping limits. This is how an agent can adapt its next step to what actually happened.
An AI model trained to use intermediate reasoning computation to work through problems before or while producing a response.
Some models are trained to spend intermediate reasoning computation on a problem before or while producing a response. That extra work can help with tasks that require several connected steps. It also uses time and compute, and correctness needs to be assessed from the result. A visible explanation is distinct from a complete record of internal processing.