Perplexity's citations teardown
Updated June 15, 2026
Perplexity’s trust model is evidence in the reading flow. Sourcing stays tied to claims as you scan, verification depth matches how skeptical you are, and you can challenge bad citations without leaving the answer. Feedback even treats wrong sources as a first-class failure mode, not an afterthought.
Domain chips in the prose
What works
- Chips show publisher domain first, users recognize ESPN vs FanDuel before clicking.
- +N communicates multiple sources for one claim without cluttering the sentence.
- Chips sit inline so skeptical readers spot sourcing while scanning bullets.
What we would push on
- Domain abbreviations (sportsbook.fanduel) may confuse non-US users. Tooltip with full title helps.
Business strategy
Inline domain chips are Perplexity’s brand in the reading flow. Publisher-first labels build trust faster than footnote numbers and keep sourcing visible while users scan.
Tradeoff
| Decision | Benefit | Cost |
|---|---|---|
| Publisher-first inline chips with +N count | Sourcing visible while scanning; recognizable domains | Abbreviated domains may confuse some users |
Takeaway
Use publisher-first inline chips with a count, not footnotes at the bottom of the page.
Pattern: Citations
Steps show what was searched
What works
- Research steps make retrieval visible, users see the system looked before asserting favorites.
- Expand/collapse keeps auditors happy without wall-of-log noise for casual readers.
- Step wording mirrors user mental model (Checking predictions) not API names.
What we would push on
- Steps do not list domains fetched, auditors still jump to Links or chips for specifics.
Business strategy
Showing retrieval happened before claims appear is table stakes for a search AI. Steps justify latency and differentiate Perplexity from chat models that answer from memory.
Tradeoff
| Decision | Benefit | Cost |
|---|---|---|
| Collapsed research steps in plain language | Trust signal without log noise for casual readers | No domain list; auditors need Links or chips |
Takeaway
Trust starts with showing retrieval happened. Then show which sources matter.
Pattern: Progress Steps
Pattern: Citations
Sources row on the answer block
What works
- One glance shows how many sources backed the answer and which domains dominated.
- Sources row lives in the action bar, same elevation as copy and share, not footer debris.
- Count sets expectation before users open the full Links tab.
What we would push on
- Favicon stack truncates; users cannot see all ten without clicking through.
Business strategy
The sources summary row puts breadth on the answer chrome at the same elevation as share and copy. Users see “10 sources” before they commit to reading, which supports Perplexity’s cited-answer positioning.
Tradeoff
| Decision | Benefit | Cost |
|---|---|---|
| Favicon stack and source count on answer bar | Global source breadth at a glance | Favicon stack truncates; full list needs click-through |
Takeaway
Summarize source breadth on the answer chrome, inline chips for local, row for global.
Pattern: Source Browser
Pattern: Citations
Links tab for full audit
What works
- Links tab is a dedicated audit view, same query, every reference as a scannable card.
- Each card shows title, URL, snippet, and preview image before opening a new tab.
- Tab sits beside Answer and Images so audit does not require leaving the result.
What we would push on
- Users must discover the Links tab, no inline jump from a chip number to card N in list.
Business strategy
A full Links tab is the audit layer for skeptical users and power researchers. It keeps verification inside Perplexity instead of opening ten browser tabs from inline chips alone.
Tradeoff
| Decision | Benefit | Cost |
|---|---|---|
| Links tab as peer tab beside Answer and Images | Full source browser without leaving the result | No inline jump from chip +N to card N in list |
Takeaway
Offer a full source browser as a peer tab, not only hover cards on chips.
Pattern: Source Browser
Pattern: Citations
Feedback includes Wrong sources
What works
- Wrong sources separates citation failures from generic Inaccurate, routes triage correctly.
- Sits beside Out of date for stale odds/news, common on time-sensitive search.
- Optional chips keep the modal lightweight.
What we would push on
- No follow-up to mark which source was wrong, product learns less than per-citation flagging.
Business strategy
Wrong sources as a first-class chip trains retrieval quality directly. For a citation product, distinguishing bad sources from bad writing is core product signal, not a nice-to-have.
Tradeoff
| Decision | Benefit | Cost |
|---|---|---|
| Wrong sources chip in negative feedback | Citation failures routable separately from Inaccurate | No per-source follow-up from the modal |
Takeaway
Search products need source-specific negative feedback, not only “bad answer.”
Check sources on a selection
What works
- Users can challenge one paragraph , “Why this is still uncertain” , without re-running the whole query.
- Check sources pairs with Add to follow-up: verify vs iterate on the same selection.
- Selection stays highlighted until the user acts.
What we would push on
- Discoverability is select-first only. Skeptical users may never find Check sources.
Business strategy
Check sources on a selection makes trust UX local. Skeptical users audit one claim without abandoning the answer or re-querying, which keeps them in Perplexity instead of opening rival tabs.
Tradeoff
| Decision | Benefit | Cost |
|---|---|---|
| Check sources on text selection | Local claim audit without re-querying | Discoverable only after highlighting |
Takeaway
Let users audit a claim span directly, trust UX is local, not page-level only.
Pattern: Citations
Pattern: Response Refinement
Sources sidebar from the answer bar
What works
- Sources sidebar keeps the answer visible while users audit references, no full-page tab switch.
- Each card repeats favicon, domain, title, and snippet, same shape as Links tab, faster to reach from the action bar.
- Panel header shows total count (10 sources) with a close control to return to reading.
What we would push on
- Sidebar narrows the answer column on smaller viewports, verify mobile falls back to full-width sheet.
Business strategy
One-click sources sidebar from the action bar lowers friction for mid-read audits. Users keep the answer visible while scanning references, which supports the cited-answer brand without a tab switch.
Tradeoff
| Decision | Benefit | Cost |
|---|---|---|
| Sources sidebar from answer bar | Audit without leaving Answer tab or full tab switch | Narrows answer column; mobile needs sheet fallback |
Takeaway
Offer a one-click sources panel beside the answer, not only a separate Links tab.
Pattern: Source Browser
Pattern: Citations
Chip opens a source popover
What works
- Chip click surfaces source detail in place, favicon, domain, headline, and excerpt before opening a new tab.
- 1/2 navigation when a claim cites multiple sources (+1), users browse stacked evidence without the full sidebar.
- Popover anchors to the chip so the connection between claim and source stays obvious.
What we would push on
- Popover competes with sidebar and Links tab, three paths to sources may confuse first-time users.
Business strategy
Chip popovers are quick-verify for skeptical readers who want one source detail without opening the sidebar or Links tab. +N pagination keeps multi-source claims inspectable in place.
Tradeoff
| Decision | Benefit | Cost |
|---|---|---|
| Inline chip popover with 1/N source navigation | Quick verify anchored to the claim | Third path to sources alongside sidebar and Links tab |
Takeaway
Let inline chips expand into quick-verify popovers with pagination when +N > 0.
Pattern: Citations
Pattern: Citation Tooltips
How citations fit with output
The pattern
- Layered trust: domain chips on claims → research steps → sources summary row → chip popovers → sources sidebar → Links tab audit.
- Check sources on selections and Wrong sources in feedback close the loop on local and global verification.
- Output teardown covers tabs, follow-ups, export, and rewrite; this guide is the evidence stack underneath.
Where it varies
- Verification depth: inline chip popover vs sidebar vs full Links tab depending on skepticism.
- Three paths to source detail (popover, sidebar, Links tab) may overlap for first-time users.
- Feedback captures Wrong sources globally but not per-citation from the modal.
Business strategy
Perplexity’s moat is cited answers. The citation stack keeps evidence in the reading flow at every depth, from inline chips for skimmers to Links tab for auditors. That supports trust, retention, and differentiation from chat-only products.
Tradeoffs
| Decision | Benefit | Cost |
|---|---|---|
| Publisher-first inline chips with +N count | Sourcing visible while scanning; recognizable domains | Abbreviated domains may confuse some users |
| Collapsed research steps in plain language | Trust signal without log noise for casual readers | No domain list; auditors need Links or chips |
| Favicon stack and source count on answer bar | Global source breadth at a glance | Favicon stack truncates; full list needs click-through |
| Links tab as peer tab beside Answer and Images | Full source browser without leaving the result | No inline jump from chip +N to card N in list |
| Wrong sources chip in negative feedback | Citation failures routable separately from Inaccurate | No per-source follow-up from the modal |
| Check sources on text selection | Local claim audit without re-querying | Discoverable only after highlighting |
| Sources sidebar from answer bar | Audit without leaving Answer tab or full tab switch | Narrows answer column; mobile needs sheet fallback |
| Inline chip popover with 1/N source navigation | Quick verify anchored to the claim | Third path to sources alongside sidebar and Links tab |
Takeaway
Steal the layered model if your product makes factual claims: inline chips, summary row, popover verify, sidebar or tab for depth. Unify discovery so three paths to sources do not compete.
Steal this
- Publisher domain +N chips inline on claims
- Visible research steps before the answer
- Favicon stack and source count on the answer bar
- Links tab as a full audit view beside Answer
- Sources sidebar opened from the 10 sources row
- Citation chip popover with 1/N source navigation
- Wrong sources in negative feedback taxonomy
- Check sources on text selections
Skip this
- Links only at the bottom of long answers
- Citation markers with no domain name visible
- Feedback that cannot distinguish bad sources from bad writing
- Forcing users to open ten tabs to verify one claim
How others trust, privacy & settings
Same job, different product bets, and what each tradeoff reveals.
Original gallery pages: Citations & Trust