Why cap each agent run with a cost-per-task budget?

Attempt it

Your answer

Quick reference

TL;DR

A hard runtime cap on tokens, tool calls, or dollars per task. Without one, runaway loops turn $0.10 tasks into $100 bills because token cost grows quadratically with step count.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Imagine giving an assistant a credit card to buy office supplies. Most days they spend twenty dollars. One day they get stuck in a loop trying to find the perfect stapler, comparing models, ordering and returning, ordering and returning, and rack up a thousand-dollar bill before lunch. Setting a daily card limit of fifty dollars stops the disaster before it happens. A cost per task budget is that limit for an agent. Each task gets a hard ceiling on how many tokens, tool calls, or dollars it can use. The moment the agent hits the ceiling, the task stops, even if the answer is not finished, because the alternative is a five hundred dollar bill on what should have been a ten cent task.

Key concepts

Cost Budget Runaway Loop Step Cap

Detailed answer & concept explanation

~8 min read

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.

Sign in for 5 free unlocks/day or go Pro for unlimited. See Pro pricing.

Quick scan · 2–4 min

Everything important, quickly.

Define a cost per task budget as a hard cap enforced by the runtime. Explain quadratic cost growth from prompt accumulation. Name the four cap dimensions and what each guards. Stress runtime enforcement, not prompt-level instructions. Close on tuning caps from empirical task-cost distributions and the role of observability.

Real-world examples

Real products, models, and research that use this idea.

LangGraph supports per-graph and per-run step caps and integrates with cost-tracking middleware to enforce token and dollar limits at the runtime layer.
Helicone and Langfuse report per-task token and dollar cost from their tracing data, making per-task budgets observable and alertable in production dashboards.
OpenAI's Responses API and Anthropic's tool-use loops expose max-iterations parameters that act as a step cap at the model-side runtime.
Production coding agents like Cursor and Devin enforce per-task cost ceilings that stop the loop when consumption exceeds a configured envelope.
Enterprise teams running multi-tenant agents typically combine per-tenant dollar budgets with per-task step caps to bound both worst-case incidents and average spend.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QWhy does agent cost grow quadratically with step count instead of linearly?

Sign in or go Pro to see the approach for this follow-up.

QIf you can only have one cap, which would you pick and why?

Sign in or go Pro to see the approach for this follow-up.

QHow do you tune the budget without surfacing too many false-positive budget-exceeded errors on legitimate long tasks?

Sign in or go Pro to see the approach for this follow-up.

Don't say this

Red flags and common mistakes that signal junior thinking. Click to expand.

Most common mistake

Believing token cost per step is the right unit to budget. Cost grows non-linearly because each step's prompt includes every prior step's history, so the right unit is total tokens or dollars per task, not per step.

Sign in or go Pro to see all red flags and common mistakes. See Pro pricing.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.