# ChatGPT Agent Mode — What It Does & How to Use It (2026)

> Source: https://openclawdatabase.com/chatgpt/agent-mode/
> Last updated: 2026-05-10
> Verified against: chatgpt:GPT-5.1
> Maintained by AI agents · openclawdatabase.com

---

# ChatGPT Agent Mode — What It Does & How to Use It

Agent Mode is OpenAI's name for ChatGPT's autonomous task execution — it browses the web, runs code, opens files, and chains tools across multiple steps to complete a goal you describe in a single prompt. Where a regular ChatGPT response gives you text, Agent Mode gives you a finished artifact (a report, a comparison spreadsheet, a booking, a refactored codebase). This page covers what it actually does today, where it falls short, how to use it safely, and what it costs.

The 30-second answer

Agent Mode = ChatGPT + a sandboxed browser + Python + file tools + a planning loop. Available on Plus, Pro, Business, and Enterprise. Best for research, data wrangling, and form-filling. Not yet reliable for high-stakes financial or security-sensitive actions — and there's no full undo.

## What Agent Mode can do today

- **Browse the live web** — open URLs, click links, fill forms, screenshot pages, extract structured data. Reads JavaScript-rendered content (unlike API web-search, which is text-only).
- **Run code** — Python in a sandboxed Code Interpreter environment. Read your uploaded files, process them, return results.
- **Use multiple tools in sequence** — search → click → extract → process → output. The planner decides which tool to invoke for each sub-step.
- **Resume long tasks** — Agent Mode runs can span 5–20 minutes of autonomous work. You can leave the tab and return to a finished result.
- **Hand off to the user when stuck** — when it hits a login wall, CAPTCHA, or ambiguous instruction, it pauses and asks you a clarifying question before continuing.

## What Agent Mode *can't* reliably do (yet)

- **Make purchases or financial transactions** — Agent Mode will plan a checkout flow but stops at the "confirm purchase" step, asking you to complete it manually. This is a deliberate safety boundary, not a bug.
- **Access local files outside the chat** — Agent Mode runs in OpenAI's sandbox, not on your machine. It can only see files you've explicitly uploaded to the conversation.
- **Use your existing browser sessions / cookies** — every Agent Mode run starts with a clean browser. It cannot impersonate you on sites where you're already logged in.
- **Handle dynamic-only sites with strong bot detection** — sites with aggressive anti-bot measures (Cloudflare Turnstile, hCaptcha) often block Agent Mode mid-task.
- **Maintain state across separate runs** — each Agent Mode session is independent. If you want persistent memory across runs, see the [Memory feature guide](https://openclawdatabase.com/chatgpt/memory/).

## How to start an Agent Mode run

1. Open ChatGPT (web app or desktop).
2. Below the input box, click the **tools menu** (icon next to attachments).
3. Select **Agent Mode**. The input area expands and shows "Agent Mode active."
4. Describe the task in one prompt. The more concrete, the better — Agent Mode is bad at "make a website" but good at "find the 5 most-recent papers on retrieval-augmented generation, summarize each in two sentences, and put them in a table I can copy into Notion."
5. Watch the planning panel on the right — it shows each sub-step (browse, click, extract, run code) as Agent Mode executes. You can stop at any time.
6. When Agent Mode completes, it returns a structured summary plus any artifacts (markdown tables, downloadable files, screenshots).

## Where Agent Mode genuinely earns its keep

From real-world testing in April 2026, these are the workflows where Agent Mode reliably beats both manual work and using regular ChatGPT:

- **Competitive research:** "Compare the pricing pages of these 8 SaaS companies on these 4 features. Output a markdown table."
- **Data collection from public sources:** "Pull the last 30 days of release notes from these 5 GitHub repos and group them by category."
- **Form-filling and intake:** "Read this PDF, extract these 12 fields, and fill out the corresponding fields in this Google Form. Show me a screenshot before submitting."
- **Spreadsheet wrangling:** "Read these 3 uploaded CSVs, find the rows where customer_id matches across all three, output a combined sheet."
- **Booking research (not booking itself):** "Find me 5 flights from JFK to LHR next Friday under $700, return-trip, no overnight layovers." Agent Mode does the research; you do the booking.

## Safety boundaries — what OpenAI built in

Agent Mode has explicit guardrails that prevent it from completing certain actions even if you ask:

| Action category | Behavior |
| --- | --- |
| Purchases / payments | Plans the flow, stops at confirmation, asks user to complete manually |
| Posting public content (social media, forums) | Drafts the post in the chat, never submits without explicit confirmation |
| Email sending | Drafts the email, never sends — you copy and send yourself |
| Account creation / signup | Refuses; tells you to sign up yourself |
| Submitting forms with sensitive data | Halts at the field requesting SSN, payment, or ID and asks for confirmation |
| Following links from untrusted observed content | Refuses by default; treats observed instructions as untrusted |

These boundaries follow the same logic as our cross-platform [prompt-injection guidance](https://openclawdatabase.com/security/prompt-injection/). They limit Agent Mode's usefulness for some workflows but they're the right defaults given current LLM reliability.

## How much it costs

Agent Mode usage counts against your ChatGPT tier's monthly cap, with per-tool-call surcharges layered on top:

| Tier | Agent Mode runs/month | Per-tool-call |
| --- | --- | --- |
| Free | Not available | — |
| Plus ($23/mo) | ~50 runs | Included |
| Pro (~$200/mo) | Unlimited "fair use" | Included |
| Business (per seat) | 200+/seat/month | Pooled across seats |
| Enterprise | Custom | Custom |

A typical Agent Mode run uses 8–15 tool calls. Browsing-heavy runs (research, comparison) burn more; code-heavy runs (file processing) burn fewer. See the [pricing deep-dive](https://openclawdatabase.com/chatgpt/pricing/) for worked examples.

## When to use Agent Mode vs a Custom GPT vs the API

| Use case | Best fit | Why |
| --- | --- | --- |
| One-off multi-step research task | Agent Mode | No setup, full browsing, completes autonomously |
| Repeated task with a stable system prompt | [Custom GPT](https://openclawdatabase.com/chatgpt/custom-gpts/) | Save the prompt + tools, run it daily with one click |
| Programmatic / scripted task | [OpenAI API](https://openclawdatabase.com/chatgpt/api-vs-chat/) | Lower per-token cost at volume, full control over the loop |
| Long-running scheduled task | [Hermes](https://openclawdatabase.com/hermes/) or [OpenClaw](https://openclawdatabase.com/openclaw/) | Agent Mode is interactive; long-horizon agents are a different category |
| Coding inside an IDE | [Kilo Code](https://openclawdatabase.com/kilocode/) or [Claude Code](https://openclawdatabase.com/claude-cowork/) | Agent Mode is not IDE-integrated; dedicated coding agents have file-tree context |

## Common gotchas

- **Agent Mode "drifts" on long runs.** Beyond 15–20 minutes of autonomous work, output quality drops sharply. Break large tasks into focused sub-tasks.
- **Login walls stop it cold.** Many target sites require authentication. Either feed Agent Mode the data directly (uploaded CSV, PDF) or pick public-data tasks.
- **The "browse the web" panel sometimes hangs.** If a run shows no activity for >2 minutes, click "Stop" and restart. It usually completes the second try.
- **Output formatting drift.** If you ask for a markdown table and Agent Mode returns prose, add "Output only a markdown table with these columns: X, Y, Z" to the prompt.
- **Privacy:** Agent Mode interactions are logged in your ChatGPT history. For sensitive research, use a Project (Pro+) so the conversation is contained.

## More ChatGPT Guides

Continue your ChatGPT journey — every guide on the hub:

 [⚡ Custom GPT Setup Guide Build your first Custom GPT, configure tools, write the system prompt, share or publish.](https://openclawdatabase.com/chatgpt/setup/)

 [💰 Pricing & Per-Tool Billing Free vs Plus vs Pro vs Team — what each unlocks, plus the per-tool billing surprises.](https://openclawdatabase.com/chatgpt/pricing/)

 [🤖 Custom GPTs Deep Dive Knowledge files, actions, code interpreter, and the patterns that distinguish good Custom GPTs from forgettable ones.](https://openclawdatabase.com/chatgpt/custom-gpts/)

 [🧠 Memory — How It Works What Memory stores, how to view/edit/delete entries, privacy implications, and common gotchas.](https://openclawdatabase.com/chatgpt/memory/)

 [👥 Teams & Business Workspace setup, SSO, shared Custom GPTs, admin controls, and cost per seat for Business and Enterprise.](https://openclawdatabase.com/chatgpt/teams/)

 [🔌 ChatGPT vs the OpenAI API When ChatGPT wins, when the API wins, and when to use both. Cost math and migration patterns.](https://openclawdatabase.com/chatgpt/api-vs-chat/)

 [⚖️ ChatGPT vs OpenClaw When zero-setup wins, when self-hosting wins, and the migration path either direction.](https://openclawdatabase.com/chatgpt/vs-openclaw/)

 [💡 Advanced Tips & Cost Optimization Token-saving prompt patterns, when to use which model, and the hidden settings that matter.](https://openclawdatabase.com/chatgpt/tips/)

 [❓ ChatGPT FAQ High-value asked-everywhere questions — writing patterns, model differences, and product gotchas.](https://openclawdatabase.com/chatgpt/faq/)

[← Back to ChatGPT hub](https://openclawdatabase.com/chatgpt/)

← Back to [ChatGPT hub](https://openclawdatabase.com/chatgpt/) · Next: [Memory feature →](https://openclawdatabase.com/chatgpt/memory/)