The “durable core” of AI citations kept its size — and replaced a third of its members in six days.

Wellows vs Profound: how often four AI engines cited each vendor's own site, week by week

The one query Google shows this page for compares two of the vendors in the table below, Wellows and Profound. This page does not review either product and we have used neither. What it can show is the one thing the panel measures: how many of the 144 answers to 12 buyer questions about AI visibility cited tryprofound.com or wellows.com, and which engines did the citing, on every weekly run from 2026-07-28 to 2026-09-28 (artifact content/news/wellows-profound-series-2026-10-04.json, read 2026-10-04). The 09-21 and 09-28 rows are lower for every domain because the instrument changed on 2026-09-20 (see Limits).

On the eight like-for-like runs (07-28 to 09-14) both sites were cited on every run. tryprofound.com: 2 to 14 answers per run, median 8, multi-engine on 7 of 8 runs; cited by Gemini on all 8 runs, Perplexity on 6, Claude on 5, ChatGPT on 1. wellows.com: 2 to 10 answers per run, median 6, multi-engine on 6 of 8 runs; cited by Claude on all 8 runs, Perplexity on 6, Gemini on 2, ChatGPT on 1. The engines differ more than the counts do: Profound's site enters this panel through Gemini, Wellows' through Claude. On pricing, the only fact we hold is that tryprofound.com/pricing printed no price when we read it on 2026-10-01; the dated price table is on the cheapest AI-visibility tools page. We have not read Wellows' pricing. The multi-engine core this post is about held between 98 and 101 domains on all eight like-for-like runs, and reads 72 and 76 on the two runs after the instrument change, a fall that belongs to the instrument, not to the engines.

Method, stated before the numbers

Same instrument, both runs: 12 pinned buyer questions × 4 engines (ChatGPT, Perplexity, Gemini, Claude) × 3 samples = 144 answers per run, citations read from each engine's returned citation array, URLs collapsed to registrable domains, one count per (domain, answer). A domain is “multi-engine” if ≥2 distinct engines cited it anywhere in the run. Run one (2026-07-28) cited 538 distinct domains, 99 of them multi-engine; run two (2026-08-03) cited 506, again 99 multi-engine. Today's cut diffs the two 99-domain membership lists. The raw diff, with per-domain engines and answer counts, is the dated cut we publish and share on request.

Where today's 99-domain core came from

And the outflow that made room, computed from the same two lists: of the 99 domains that were multi-engine on 07-28, 65 stayed multi-engine (65.7%), 27 were demoted to a single engine (27.3%), and 7 were cited nowhere in run two (7.1%). The turnover happens to balance exactly — 34 in, 34 out — which is why the core's size looks stable while a third of the names on the list changed. A stable aggregate hiding heavy churn underneath is exactly the kind of thing a one-off AI-visibility screenshot cannot show.

The entry rates: the door is open, and measured

Two admission rates fall out of the diff. From the 439-domain single-engine tail, 26 domains — 5.9% — climbed to multi-engine within six days. And of the 229 domains that entered the corpus fresh in run two, 8 — 3.5% — landed multi-engine immediately, skipping the tail entirely. Put next to yesterday's survival split (single-engine citations survive at 42.1%, two-engine at 90.2%), the ladder is now measured at every rung: uncited → cited-once is a lottery with weekly drawings, cited-once → multi-engine happens to ~1 in 17 tail domains per week, and once you are multi-engine you mostly stay.

The 34 new members, in full

Which engines are the door

Admission is not evenly distributed across engines. Gemini participated in 25 of the 34 admissions and Perplexity in 23; ChatGPT in 11 and Claude in 14. The single most common combination is Gemini + Perplexity (11 of the 29 two-engine admissions). That is consistent with what we measured on retention: Gemini and ChatGPT keep less than half of their own citation sets week to week, so they are also the engines most often handing out new citations. The engine most likely to admit you and the engine most likely to keep you are not the same engine.

Limits

• Sampling luck is real at the entry boundary. Multi-engine membership takes as little as one citation from each of two engines; with 3 samples per question, a domain can cross the line by draw. The direction of the bias is known: some of the 34 “new” members are variance, so 34.3% is an upper bound on true six-day turnover — the incumbents' 65.7% retention is the harder number.
• Six days, two runs, one panel. 12 buyer questions about AI visibility for small businesses; the instrument runs weekly, so the turnover series accumulates from here.
• We have a commercial interest. We sell AI-visibility audits. Every number is reproducible from the two dated citation cuts, shared with anyone who asks.
• The instrument changed on 2026-09-20. From that run the stored citation list holds only the sources an answer cites, not every source the engine returned; Perplexity went from 20 stored sources per answer to a median of 7.5. Runs on either side of that date are not comparable, and the 09-21 and 09-28 rows in the week-by-week table are lower by construction. Added 2026-10-04.
• Two stagings of the 08-03 run differ by a few domains. The figures in this post come from the 2026-08-04 cut (506 distinct domains, 99 multi-engine). The weekly series file for the same run, staged 2026-08-08 under the series' domain rule, collapses to 520 distinct domains and 100 multi-engine; diffed against 07-28 it reads 33 in, 67 stayed, 27 demoted, 5 gone. The reading is the same: the core held its size and turned over a third of its members. Added 2026-10-04.

The practical reading: yesterday's cut said a multi-engine citation is the only durable kind; today's says the club that confers that durability admits new members every week — about 1 in 17 of the single-engine tail climbed in, in a single six-day window, and 8 domains went from invisible to multi-engine in one step. Which side of the door your business is on is a measurable fact, not a guess — run the four-engine measurement on your business in 60 seconds.