AI assistant for English Premier League Fantasy Football (FPL): works out optimal transfers, captain picks and chip strategy from expected points, and can also rate your team.
Author Spiros turned his National Technical University of Athens thesis "Machine Learning in Fantasy Premier League" (2023) into an FPL solver. He registered the domain and the X account on the same day in 2023-05, first posted prediction results to the FPL Twitter crowd and built 6,000+ followers, ran a Streamlit prototype and opened a Discord in 2024, then rebuilt it as a full website six months ago, with tool pages and gameweek-by-gameweek blog posts around "fpl ai / rate my fpl team / chip strategy" to cover search. Returning users come back every gameweek to adjust their lineups. In three months ago the Premier League and Microsoft launched the similarly named "FPL Companion powered by Copilot", which may also send brand-keyword traffic here by mistake (speculation).One-line growth story, compiled by us from public sources; speculation is marked separately below.
The main engine is SEO: organic search is the top channel at 45%, the top terms are tool terms like fpl ai and rate my fpl team, and paid search is 0.
The lubricant is the rhythm of gameweeks: every gameweek existing users come back to adjust transfers and pick a captain, and visits last month rose 47% month over month.
By our estimate, about 40% of visits are existing users coming back each gameweek; about 2.8 of every 100 visits click through to the checkout page.
Model: Lenny's racing growth framework. Engine = SEO (tool pages for 'fpl ai', 'rate my fpl team' and 'chip strategy', and a timely blog post every gameweek); lubricant = the gameweek rhythm, with existing users coming back every week to adjust their lineup; it got started through the FPL Twitter circle.
Real data: 308,900 visits, month-over-month +46.85%, top channel organic search at 44.92%, the top-three channel ranking (organic search, direct, referrals), organic search at 100% of search, top search terms (fpl copilot, fpl ai, rate my fpl team, fpl ai rating, fpl team rater), social sources (X, Facebook), countries (UK 29.12%, US 10.85%, Netherlands 6.9%, South Africa 6.49%, India 5.49%), bounce rate 46.06%, 3.95 pages per visit and average stay 3 minutes 34 seconds all come from the Similarweb public page for last month; the shares of the second and third channels are not given on the public page. Fantasy sports sites at 76% of referrals comes from the Similarweb record saved earlier. The 8,596 visits (about 8,600) to the Stripe checkout page come from quietmoney checkout-page data. The profile's 'search 44.9%, direct 41.3%, referrals 8.3%' has an unclear basis and is not used here.
Supporting evidence: The author Spiros turned his 2023 thesis into an FPL solver and registered the domain and X account the same year; the About page says early results were posted on X and the FPL community helped spread them, and X now has 6,165 followers; in 2026 it was redesigned into a full website with a blog written by gameweek; in 2026 the Premier League and Microsoft launched FPL Companion powered by Copilot, after which the About page stated that it is not an official product.
Inference: The two channel circles are real; how each route splits is an inference: search 138,800 = searching tool terms 90,000 + existing users searching fpl copilot 30,000 + searching the name after seeing an X post 10,000 + searching after seeing a roundup or the official product with a similar name 8,800; other channels 170,100 = existing users opening the site directly 100,000 + community sites and roundup articles 35,100 + X posts 35,000. The visit rates of 10% click-through after finding it, 5% after seeing an X post and 10% after seeing a roundup are guesses. That the official product with a similar name brings mistaken searches is only speculation, with no data.
Checkout: checkout.stripe.com
“"I'll find your best transfers. You just hit go."; "Minileagues" in nav (not described)”Quote from the site
New-user source: SEO (Non-brand search). Search 44.9%, direct 41.3%, referral 8.3%; non-brand search about 35.9%, with terms "fpl ai", "rate my fpl team", "fpl team rater"; social comes from X and Facebook. Users return every gameweek to adjust transfers, so the revisit frequency is high.
Top channel measured by Similarweb, others estimated by rank
| Attributable new users, last month | Share |
|---|---|
| SEO | 36% |
| Other | 64% |
Direct + brand search 50%. Direct and brand search count as viral only when the site shows sharing mechanics; the largest share wins, under 5% means Other.
| Country | Share of visits |
|---|---|
| United Kingdom | 29.12% |
| United States | 10.85% |
| Netherlands | 6.9% |
| South Africa | 6.49% |
| India | 5.49% |
English
X (Twitter), Facebook
331 keywords · brand ~50% · organic 100% / paid 0%
| Similarweb top 5 keywords |
|---|
| fpl copilot |
| fpl ai |
| rate my fpl team |
| fpl ai rating |
| fpl team rater |
Non-brand queries: fpl ai, rate my fpl team, fpl ai rating, fpl team rater
| Category | Share of referrals |
|---|---|
| Fantasy Sports | 76.03% |
About 8,596 last month (Similarweb estimate), #403 of 606; the month before was 9,010. Opening checkout is not paying, so this is not revenue.
New-user source: SEO (Non-brand search). New users mostly come from need-based searches Search 44.9%, direct 41.3%, referral 8.3%; non-brand search about 35.9%, with terms "fpl ai", "rate my fpl team", "fpl team rater"; social comes from X and Facebook. Users return every gameweek to adjust transfers, so the revisit frequency is high.
Paid subscription and free trial available; price not found
Dossier confidence: medium. Parts 1 and 2 come from reading the site and Similarweb data; part 3 from public reporting, founder posts, Wayback snapshots, WHOIS and similar, with speculation marked.
The number: checkout visits is Similarweb's estimate of visits from the site to a checkout payment page; opening checkout is not paying, so this is not revenue. Small sites land on fixed buckets.
Data through last month. Page updated 2026-10-31.