AI browser workflows
Before you buy another tool, put your open Chrome tabs to work
Use ChatGPT to compare three software pages, check the full cost, and make one practical decision for your side hustle—with five illustrated steps and prompts to copy.

In this guide
- The useful starting point
- Make the next purchase earn its place
- Before you begin: connect the browser you actually mean
- Step 1 — Open side chat beside one public page
- Step 2 — Name the three tabs and the decision
- Step 3 — Check the answer against the original pages
- Worked example: the headline price is not the team cost
- Step 4 — Review the tab list, then group only those tabs
- Step 5 — Finish with a recommendation and one open question
- Try the same method on a single article
- Your finished-work checklist
- Put this into practice
- Questions you might be asking
- Sources and further reading
The useful starting point
Choose three relevant public pages, state the decision criteria, verify the comparison, and keep a short source-linked recommendation. Group the reviewed tabs in Work only where that action is available.
A promising side hustle can turn into a collection of subscriptions before it turns into a paying customer. You open a few pricing pages, lose track of which feature belongs to which plan, and choose the one with the most convincing headline. A better research habit starts with the job you need done this month.
Make the next purchase earn its place
Before opening a pricing page, write down the failure you want to fix. If the problem is missed handoffs, you need clear ownership and reminders. If nobody knows where the current files live, another task board may not solve it. List the features you will actually use in the next four weeks. Treat every extra subscription as an experiment with a review date.
Before you begin: connect the browser you actually mean
OpenAI documents a browser extension that can use open tabs and provide side chat. In the desktop setup, open Settings → Computer Use, choose your browser, and follow its installation flow. That route points you to the appropriate extension. Use the profile where you installed it. Availability and controls depend on your account, app version, and workspace settings.
This guide uses a public-page practice task. The cover is AI-generated editorial imagery; the five step graphics are conceptual illustrations, not screenshots of an actual ChatGPT session. Allow about 20 minutes for a first attempt; that is a suggested practice time, not a measured result.
Step 1 — Open side chat beside one public page
Open one of your sources and select ChatGPT from the browser toolbar or Extensions menu. Use the tab mention or page-context control your version provides. Begin in Chat for reading where available. If the panel cannot see the page, confirm the correct profile and connection before continuing.
Read only the page I selected. Tell me its title and URL, what information you can actually access, and anything you cannot verify. Do not change the page.
Step 2 — Name the three tabs and the decision
Open three official project-management pricing pages. Select or mention each tab explicitly. Replace the placeholders in this prompt with the actual page titles or URLs. A list of links is not proof that ChatGPT has read every page; ask it to identify any failed or partial reads.
Use only these three tabs: [title and URL 1], [title and URL 2], [title and URL 3]. My task: Choose a project tool for five collaborators with a $75 monthly-equivalent budget, task ownership, due dates, and exportable records. Create a comparison with one row per option, the source URL for each important claim, and a separate column for missing information. Use “not verified” when a page does not establish a detail. Do not start trials, buy, register, or send messages.
Step 3 — Check the answer against the original pages
Open the source behind each decision-changing claim. Separate a visible statement from AI’s interpretation. For prices, check currency, billing period, paid-seat count, minimum seats, required add-ons, and any tax or fee exclusions. For events, check date, time zone, venue, and registration status. Do not convert a blank field into a favorable assumption.
Audit your comparison against the three source pages. For each important claim, show the supporting page and explain the calculation or inference. Mark contradictions and missing details. List what I must confirm before making the decision.
Worked example: the headline price is not the team cost
Illustrative exercise: fictional plans and prices, not current vendor quotes. Five people need task ownership, due dates, and exportable records. The limit is $75 per month on an annual-equivalent basis. Assume the sample rates below require annual billing and all five people need paid seats. Taxes and add-ons are excluded.
| Fictional plan | Per person / month, annual billing | 5-person monthly equivalent | Annual commitment | Open question |
|---|---|---|---|---|
| Plan A | $12 | $60 | $720 | Export format not stated |
| Plan B | $15 | $75 | $900 | Guest seat rules not stated |
| Plan C | $25 | $125 | $1,500 | Over the example budget |
Show the arithmetic: 5 × $12 × 12 = $720 per year. A $12 headline is not the team price, and $60 per month as an annual equivalent does not mean a $60 monthly invoice is available. If the page requires a six-seat minimum, Plan A becomes $72 per month equivalent and $864 per year. Ask about minimums before calling the first number complete.
Example decision note: Plan A is the first option to investigate because its stated annual-equivalent cost is below the budget. Export is a required feature, so it is not yet an approved choice. Plan B uses the entire budget before tax or add-ons. Plan C exceeds it. Next question: does Plan A include a usable export on this exact tier?
For a real practice run, open Asana pricing, Trello pricing, and ClickUp pricing. Compare only equivalent requirements and the billing options visible on the day. These links are practice sources; the fictional table is not a ranking or a price comparison of those products.
Step 4 — Review the tab list, then group only those tabs
If browser actions and tab grouping are available in Work, select that mode and name Chrome explicitly. Reading pages and changing the browser are separate tasks. First ask for a preview of the three tab titles and URLs. After you check the list, request the grouping action below. Inspect the actual Chrome group afterward.
In Chrome, show me the exact three tab titles and URLs you would group as “Side hustle tool shortlist”. Do not change the browser yet.
Group only those three reviewed tabs as “Side hustle tool shortlist”. Leave the other tabs where they are. Do not close pages, navigate to checkout, register, or send anything. Report the group name and the tabs actually included.
If grouping is unavailable, create the group manually in Chrome and keep the comparison. A useful research result does not depend on this optional action. If the extension fails to connect, use OpenAI’s linked troubleshooting guidance; do not grant wider access just to complete a practice exercise.
Step 5 — Finish with a recommendation and one open question
Write a decision note under 150 words: the goal, the best-supported next step, the source links, the main tradeoff, and one unanswered question that could change the recommendation. Distinguish facts, calculations, and your judgment. If the evidence is insufficient, recommend the next check instead of choosing a winner.
Keep the existing workflow until the comparison identifies a meaningful improvement. If the shortlisted tool passes your requirements, define a small pilot: one project, one owner, and one week. Record setup time, subscription cost, and whether a handoff improved. A cheaper tool that adds work is not automatically a better choice.
Try the same method on a single article
Select the article tab and ask for a short evidence review. This is useful when a headline makes a broad promise but the body describes a narrow example.
What is the main claim in this article? What evidence does the author present? Which statements are interpretation, which details remain unresolved, and what original source would I need to inspect before relying on the claim? Include the article URL.
Your finished-work checklist
- The comparison uses the three sources you selected.
- Decision-changing claims link back to an accessible page.
- Costs and dates use the correct assumptions.
- Missing information remains visible.
- The actual tab group matches the reviewed list, if grouping was used.
- The final note names a next step and one question.
Save the note with the date checked. When a price, policy, or event changes, revisit the original page before reusing the recommendation.
Put this into practice
Bring one idea and learn to turn it into a useful first offer, a practical workflow, and a next step you can take.
Questions you might be asking
Is the extension the same as the cloud browser?
No. Use the connected browser extension when the task depends on your existing Chrome tabs. Name Chrome and the selected tabs explicitly.
What if my account cannot group tabs?
Complete the comparison and create the tab group manually. The group is optional; source checking is the essential skill.
Sources and further reading
Sources checked November 11, 2026. Review the linked publisher information for current details.
Put one idea to work
Bring one idea and learn to turn it into a useful first offer, a practical workflow, and a next step you can take.
Build your idea with Two Mondays →Explore more from Wealth ExperimentGet the Wealth Experiment field notes →Keep practicing
Agent-Friendly Website: A Small Business Test You Can Run
Run a bounded agent-readiness experiment with a baseline, a short llms.txt file, a test log and an honest decision about what to do next.
November 11, 2026 · 8 min readWill someone pay for your AI skill? Run this 14-day experiment
A list of emerging AI jobs can spark an idea. A small experiment can help you decide what to do with it. Test one useful service with a clear deliverable, a limited time budget, and a real buying decision.
November 11, 2026 · 6 min read