← Autonomous AI Agents
0/15 complete

Module 04 · Operational Guardrails

Cost Controls: Preventing Runaway Agent Loops

20 minfocused lesson5practical steps4grounded questions3source links
Open lesson + course map

On this lesson

Course outline

Agent cost is not only tokens. It includes model calls, tool APIs, search, storage, compute, queue time, retries, human review, and the cost of wrong actions. Control cost at admission, per run, per tool, per tenant, and per billing period.

After this lesson, you can create a budget envelope and stop a runaway run without corrupting state.

// concept

Define the Budget Envelope

// prompt — copy me9 lines
max elapsed time
max agent turns
max model input/output units
max tool calls by type
max concurrent workers
max retries
max subtasks and depth
max estimated currency cost
daily tenant and system caps

Estimate before a run and update from actual usage. If provider prices or exchange rates change, version the estimate. Never promise an exact PKR cost from a stale model price.

// concept

Apply Admission Control

Reject or queue work when the tenant cap, concurrency cap, dependency circuit, or human-review capacity is exhausted. Reserve budget for cleanup and status notification so crossing a cap does not leave an unknown partial effect.

On stop:

  1. stop creating new tasks;
  2. cancel safe in-flight model calls;
  3. let committed tool actions report final state;
  4. checkpoint pending tasks;
  5. notify the owner with reason and resumable scope;
  6. require approval for additional budget.

// concept

Reduce Waste Before Changing Models

Use deterministic routing, smaller context, retrieval of only relevant records, cached approved facts with expiry, schema validation, batch operations, and early exit. Use a capable model only where evaluation shows it adds value. Cache keys must include tenant and version and must not leak private results.

// worked_example

Worked Example

A content-quality run covers 1,000 products. The system allows 20 workers, two attempts per item, six tool calls per task, and a versioned estimated budget. It first validates product records deterministically; 140 invalid records go directly to correction instead of consuming model calls.

A malformed instruction causes repeated evaluator failures. After two attempts per item, tasks enter review. The run-level error rate crosses its stop threshold, so new work pauses. The owner sees completed, pending, failed, estimated/actual usage, and the exact version. No recursive repair agents are spawned.

// failure_cases

Failure Cases to Diagnose

7 cases to diagnose

  • Only a monthly API budget

    one run can consume it before detection.

  • Workers enforce caps independently

    use shared atomic counters or reservations.

  • Retry cost ignored

    include attempts and failure thresholds.

  • Stopping kills a payment call blindly

    reconcile consequential effects.

  • Cache crosses tenants

    include identity, authorization, and version.

  • Cheapest model selected without quality test

    optimize cost per accepted outcome.

  • Human review is “free”

    measure time and queue capacity.

// pakistan_angle

Pakistan Angle

Maintain foreign-currency and PKR views with the exchange assumption and date. Add card/payment-provider limits and tax/accounting treatment as business constraints. Notify the owner before caps, not after a foreign-currency bill becomes unaffordable.

Design offline-safe pause behavior for connectivity or power problems. A recovered worker must read central budget and checkpoint state before continuing; it cannot assume yesterday’s remaining allowance. Smaller Pakistani teams especially need a visible kill switch and simple approval for extra spend.

// hands_on

Hands-On Exercise

5 steps

  1. Define per-run, per-tenant, daily, and monthly envelopes.

  2. Implement or diagram atomic reservations.

  3. Add error-rate and cost stop thresholds.

  4. Test concurrent cap crossing and safe cancellation.

  5. Calculate cost per accepted outcome including human time.

// completion_rubric

Completion Rubric

6 checks — tick as you verify

0/6

// sources

Sources

3 official sources — check every claim yourself

// check_yourself

Check yourself

4 questions · answers and options are taken word-for-word from this course

0/4

  1. 1 / 4 · diagnose

    Your work shows this failure mode: “Workers enforce caps independently.” What does the lesson tell you to do about it?