Agent-Enabled Backends
A model choosing a tool is a client choosing an endpoint. Authorization, budgets, timeouts and audit still belong to the backend, not to the prompt.
What an Agent Adds to a Backend
The request path when a model sits in the middle: what is genuinely new, and what is the backend you already know.
Q · What changes in a backend when a language model decides which work to do, and what stays exactly the same?
A Tool Call Is a Backend Call
The model choosing a tool is a client choosing an endpoint — and the server owes exactly what it always owed.
Q · If the model selects the tool and fills in the arguments, what is still the backend's responsibility?
Agent Authorization
An agent acts on behalf of a user and must be limited to that user's permissions — not to the service account it happens to run under.
Q · Whose permissions does an agent act with, and how do you make sure it cannot do more than the person who asked?
Budgets, Deadlines and Step Limits
An agent loop terminates because you made it terminate — bounded in time, in steps, in tokens and in money.
Q · What stops an agent loop from running forever, and from spending an unbounded amount of money while it does?
Agent Audit Logs
What was asked, what the agent decided, which tools ran with which arguments, and what changed as a result.
Q · A customer says the assistant refunded the wrong order. What record lets you answer what happened, and why?