Short answer: collect primary sources as open tabs, have the sidebar extract claims with URLs into a table, reconcile disagreements yourself, then draft from that table. Never draft from a prose summary.

Why start from tabs instead of a search query?

A search query returns whatever ranks. Open tabs let you curate: you pick the regulator’s PDF, the vendor’s pricing page, and two independent analyses. Comet’s assistant reads exactly what you opened, which kills a whole class of sourcing error.

Aim for six to twelve primary sources. Fewer and you cannot cross-check; more and the context gets diluted.

How do you extract claims with their sources?

1. Open your curated tabs in one window.
2. Ask the sidebar: “From these tabs only, list every quantitative claim with the exact URL and the sentence that supports it.”
3. Require a table format: claim, value, source URL, supporting quote.
4. Export that table to your notes before doing anything else.
5. Keep the tabs open while drafting so you can re-query individual sources.

The phrase “from these tabs only” matters. Without it, the assistant quietly brings in outside knowledge and your source trail breaks.

How do you handle sources that disagree?

This is the actual value of the workflow. Once you have the claim table, sort by topic and look for conflicting values on the same metric.

Flag unresolved conflicts in the report rather than picking one silently. Readers of research trust a document more when it names its uncertainty.

What does the drafting step look like?

Draft from the table, not from chat history. Each paragraph should map to one or two rows. If a sentence needs a fact that is not in the table, go get the source or cut the sentence.

Ask Comet to check the final draft as a separate step: paste the report and ask it to flag any claim without a citation. That catches sentence three of a paragraph where citation two quietly covers four claims.

Where does this workflow not pay off?

It is slow. Curating ten sources and building a claim table takes two to four hours for a mid-size report. For a quick internal memo, that is absurd overhead.

Use it for anything public, legal-adjacent, or financial — documents where a wrong number has consequences. For a Slack update, just ask the assistant and move on.

Quick Summary

• Curate six to twelve primary sources as tabs before asking anything.
• Extract claims into a table with URL and supporting quote, from those tabs only.
• Reconcile conflicting values explicitly instead of silently picking one.
• Draft from the claim table so every sentence maps to a source row.
• Worth the overhead for public or financial reports, not for quick memos.

Short answer: download Comet for macOS or Windows, sign in with a Perplexity account, and use the sidebar assistant to summarize the current tab or compare pages. Start on read-only tasks before letting it click anything for you.

What is Perplexity Comet?

Comet is a desktop browser where the assistant has page-level context. Ask about the article you are reading and it answers from that page plus the open web, with citations. It also has an agent mode that can navigate, fill forms, and shop.

It imports bookmarks and passwords from Chrome, so migrating is quick. Free accounts get the browser with limited assistant queries; Perplexity Max unlocks higher limits and full agent access.

How do you set up Comet for research?

1. Download and install the Comet desktop app.
2. Sign in with your Perplexity account and import browser data from Chrome.
3. Pin the sidebar assistant so it is always visible.
4. Set a default answer style — concise or detailed — in preferences.
5. Decide up front which sites you will allow agent actions on.

The sidebar is the whole point. A browser with a chat tab somewhere else gives you nothing new; a persistent side panel is what makes page-aware queries fast.

What research tasks does Comet handle well?

Asking “what do these five tabs disagree about” is where it saves the most time, because the assistant reads all of them and surfaces contradictions instead of a bland summary.

How do you verify what it tells you?

Always click the citation. Comet is better than most at surfacing sources, but the summary can still compress a nuance into something misleading.

Watch for citation drift: a source may support a related claim without supporting the specific number the assistant quotes. For anything that will end up in a decision document, open the source and read the relevant paragraph. Thirty seconds of checking beats a retracted claim in a report.

Is the agent mode safe?

Same risk profile as any agentic browser. Pages can contain hidden instructions aimed at the agent, and the assistant may follow them. Comet asks for confirmation on sensitive actions by default, and you should leave that on.

Keep the agent away from banking, email, and anything with saved payment details. The convenience gain on those sites does not justify the exposure.

Comet fits analysts, students, and writers who read a lot of web pages and want cited answers inline. If you mostly use a small set of SaaS apps, a standard browser plus a search tool covers you fine.

Quick Summary

• Perplexity Comet is a Chromium browser with a page-aware Perplexity assistant.
• Free accounts get limited assistant queries; Max unlocks full agent features.
• Its strength is comparing multiple open tabs and surfacing contradictions.
• Always click the citation — summaries can distort a source’s actual claim.
• Keep confirmation prompts on and avoid agent mode on banking or email.