Lesson 10 · ChatGPT Mastery Pro+ ~14 min Supervision + cost control

GPT-5 agents: workflows that run themselves.

GPT-5 agents run multi-step workflows on their own — visiting sites, filling forms, taking actions. Powerful, and risky if misused. The skill was never "using an agent." It's supervising one: the safety guardrails, the cost-control playbook, and knowing when a plain script would do the job better.

The mental model

An agent is an intern with internet access.

It does impressive multi-step work autonomously — and it can also confidently complete the wrong task, burn tokens fast, and make changes you can't undo. So you treat it exactly like a brand-new intern: clear scope, limited access, and a check on anything that matters.

The one rule

Never give an agent access to anything you wouldn't give a brand-new intern. No banking, no production systems, no account where one wrong action is irreversible. Throwaway browsers, throwaway accounts, public data. The capability is real; the trust is still being earned.

Do it · arm the guardrails

Set up an agent run you can trust.

You're about to launch a real agent task. Switch on the guardrails that make it safe and cost-controlled. The launch button stays locked until the run is properly guarded — and one of these toggles is a trap.

Agent task
"Compare 8 business credit cards for a SaaS company and rank the top 3."
Arm the guardrails before you launch.
Not ready
Your call · agent or script?

Sometimes a script is the better tool.

Agents shine on fuzzy, judgment-heavy work. For deterministic, repetitive tasks, a plain script (Python, Zapier) is faster and far more reliable. Make the call.

Where agents earn their keep

Three workflows worth supervising.

1

Research & synthesis at scale

A research question → 20–30 sources visited, synthesized, cited.

Set a token budget; spot-check sources — agents sometimes cite SEO-spam.
2

Multi-step web tasks

Find, compare, and rank across many pages against your criteria.

Recommendations are inputs to your decision, not the decision — verify before acting.
3

Periodic monitoring

A scheduled weekly run: check competitor blogs, summarize, flag what matters.

Sites change layout and agents break silently — audit monitoring setups monthly.

Run one supervised agent task

Pick a research-or-monitoring task you do manually that takes 30+ minutes. Run it through a GPT-5 agent — watch it closely the first time, verify every claim, iterate on the prompt. If it works, schedule it. If it doesn't, learn why and try a different task type.

What you can do now

  • Treat an agent like an intern — clear scope, limited access, no irreversible power
  • Arm guardrails before launch: cost budget, throwaway account, confirm-before-act, verify, public-data-only
  • Use agents for research, comparison, and periodic monitoring
  • Verify agent output against source data before you act on it
  • Reach for a script when the task is deterministic and repetitive
Pro+
Up next in ChatGPT Mastery

Lesson 11 · ChatGPT API, projects, and advanced prompting

When to use the API instead of the app, project organization for power users, evaluation patterns, and advanced reasoning prompts — the advanced curriculum. Start lesson 11 →

🎓
AI Coach
Ask anything about this lesson
Hey! I'm your AI Coach for this lesson. Ask me anything about what you just read — concepts, examples, how to apply it to your work. What's on your mind?
Free lesson coaching is limited to 3 questions. Upgrade to Pro for unlimited coaching on every lesson.