FanSim
Invitation only · Private beta

Test your launch on a modeled fandom — before it ships.

FanSim generates synthetic fan agents from your real audience segments and lets you A/B test copy, visuals, pricing and timing against a statistically modeled fan population. Decide with evidence, not guesswork.

20+
fan attributes per agent
6
simulation types
4
AI engines
simulations
Built by bemyfriends

A decade of fandom expertise, distilled into AI

FanSim is built and operated by bemyfriends — the team that has run fandom businesses for 1,000+ artists and IPs over more than 10 years. Its models are trained on bemyfriends’ hands-on know-how, proprietary data and real campaign cases, so they understand the artist and the fan at the same time.

1,000+
artists & IPs
10+ yrs
in fandom business
Artist + fan
understood together
Simulate

Six ways to simulate a decision

Every candidate is judged by individual agents — not an average.

Text

Copy, subject lines, announcements

Visual

Thumbnails, covers, photocards

Pricing

Tickets, goods, membership tiers

Timing

Best release & on-sale windows

Risk

Stress-test sensitive moves for backlash

Churn

Which win-back offer retains at-risk fans

Platform

A full fandom intelligence studio

Synthetic fan agents

Turn segments into a population of statistically modeled fans, each with demographics, spending, affinity and churn signals.

Launch simulator

Run live A/B tests and watch each agent react in real time, with per-segment winners and revenue estimates.

Fandom radar

Channel intelligence grounded in real public data — including YouTube — with sentiment, desires and frustrations.

Focus groups

Qualitative, in-character reactions and 1:1 interviews with synthetic fans for the nuance numbers miss.

Outcome calibration

Record real results and feed them back so predictions sharpen against your fandom over time.

Copy optimizer

Generate, score and iterate messaging automatically until the winning variant emerges.

Knowledge base (RAG)

Ground every analysis in your own research, reports and brand guidelines via semantic retrieval.

Multi-engine AI

Choose Claude, Gemini, OpenAI or MiniMax — switch engines and model versions from the admin.

Ask your fans

Put your questions to up to 1,000 virtual fans

Ask up to 1,000 virtual fans (agents) anything about your artist’s activities and get ahead of the response before you act — or sit down 1:1 with a single fan for focused, in-character analysis.

Synthetic focus group

Pose a question or plan to up to 1,000 fan agents and read the room — in-character reactions, stance, and a synthesis you can act on.

1:1 fan interview

Chat one-on-one with a single fan persona for deeper, focused insight into the “why” behind the numbers.

Workflow

How it works

1

Model your fandom

Add a fandom and let AI draft 3–5 fan segments with demographic and behavioral distributions.

2

Generate agents

Sample a synthetic fan population — hundreds of agents that genuinely reflect each segment.

3

Simulate & decide

A/B test your candidates, read per-segment results, and launch the winner with confidence.

Always current

Real-time external data, trend-matched analysis

FanSim continuously checks live public signals across channels and grounds every analysis in what’s happening right now — so recommendations stay in step with the trend, not last month’s snapshot.

Live signals

YouTube · X · Weverse · Communities · News

bemyfriends engine

Real-time fetch + grounding in 10 years of fandom data

Trend-matched output

Channel intelligence, simulations & strategy

Invitation only · Private beta

Currently available by invitation only

FanSim is in private beta with a small group of partners. Have an access code? Sign in. Otherwise, get in touch and we’ll set you up.