How I Built a Fully Autonomous AI Chatting System for Fanvue — Runs 24/7, Zero VAs

[Akaroth]

Hi, how long does it take to get the Fanvue API keys? I heard that when you ask for them, they include you in a waiting list.

I'm thinking about creating a chatter for Fanvue, but I don't know if it's worth with their API or if I should try a different approach.

Thank you!

 

[untaxed]

Hi, how long does it take to get the Fanvue API keys? I heard that when you ask for them, they include you in a waiting list.

I'm thinking about creating a chatter for Fanvue, but I don't know if it's worth with their API or if I should try a different approach.

Thank you!

not sure where you got that info. There's no waiting list, go check the docs or ask the AI. You can start building right now.

 

[subagh]

**TL;DR:** I built a system that manages fan chats across 4 Fanvue creator accounts completely autonomously. No VAs, no manual work. It runs on a $24/month VPS, handles conversations 24/7, sends PPV at optimal times, auto-welcomes new subs, runs win-back sequences on expired ones, and has a live dashboard I check from my phone. Total build cost was about 3 weeks of development. Now it just... runs.
I'm not selling anything in this post. I'm sharing what I built, how it works, and the results so far because I've seen a lot of people on here asking about AI chatting and most of the answers are "use ChatGPT in a Chrome extension" which is... not it.
---
## The Problem I Was Solving

I manage 4 AI influencer accounts on Fanvue. The content generation side was automated (AI images, AI video, automated posting across IG/Threads/Twitter), but the CHATTING was still manual. I was either doing it myself or paying people.

The math wasn't working:

- A decent chatter costs $15-25/hr
- For 24/7 coverage you need 3 shifts minimum
- That's $1,200-2,000/week PER CREATOR
- Across 4 creators: $5K-8K/month just in chatter labor
- Quality was inconsistent — some chatters close $500/day, others $50
- Overnight shifts were impossible to fill reliably
- Every time a chatter quit, I lost 2-3 weeks training a replacement

So I built the whole thing from scratch.
---
## What The System Actually Does

This isn't a Chrome extension that suggests replies. This is a fully autonomous system that runs on a server with zero human involvement.

### Per-Creator AI Chatbot

Each creator has their own AI persona. Not just "respond like a hot girl" — it's trained on:

- The creator's actual messaging style (slang, emoji patterns, sentence structure)
- Revenue strategy (when to tease, when to push PPV, when to pull back)
- Fan tier awareness (free followers get different treatment than $50/month subs)
- Conversation memory (remembers previous chats, fan preferences, what they've bought)

The AI doesn't just reply — it follows a full revenue maximization strategy:

**Fan Tiering:**

- New subscriber → Welcome sequence → Build rapport → First PPV offer
- Active buyer → Drip exclusive content → Upsell bundles
- Dormant fan → Re-engagement sequence → Win-back offer
- Free follower → 10 message engagement limit → Push to subscribe

**PPV Dripping:**

The AI sends locked content at optimal times based on when each fan is most active. Not a blast to everyone at 3 PM — individualized timing.

### Auto-Welcome

Every new subscriber gets a personalized welcome within 60 seconds. The first message sets the tone and gets them engaged before they forget they subscribed. I tested this vs manual welcome (1-4 hour delay) and the conversion to first reply was 3x higher with instant welcome.

### Win-Back Sequences

When a subscription expires, the system runs a 4-step win-back campaign over 2 weeks:
1. Day 0: Casual "miss you" message
2. Day 3: Exclusive offer / tease
3. Day 7: FOMO trigger
4. Day 13: Final attempt with a deal
Each step has 3-4 message variants so it doesn't feel templated.

### Live Dashboard

I built a real-time dashboard that shows:
- Messages sent per creator per hour
- Fan engagement rates
- Token health status (more on this below)
- Revenue tracking per creator
- System health monitoring
I check it from my phone once a day. Usually everything is green.

### Token Management

This was the hardest part. Fanvue uses Ory Hydra with one-time-use refresh tokens. If you use a refresh token twice, it permanently dies. I've seen other people's systems break because they had two processes trying to refresh the same token.
My solution: a single Docker container that handles ALL token refreshes on a 15-minute cycle. Nothing else touches the tokens. It's been running for weeks without a single token death.
---
## The Tech Stack

Not going to gatekeep the architecture:

- **Server:** $24/month Vultr VPS (Ubuntu, Docker)
- **Orchestration:** n8n (self-hosted, workflow automation)
- **AI:** Mistral via OpenRouter for conversation generation (best price-to-quality ratio for this use case)
- **Database:** MySQL (fan records, conversation state, purchase history)
- **Token Refresh:** Custom Python script in Docker container
- **Dashboard:** Custom Python web app behind Cloudflare
- **Monitoring:** Health check workflow runs every 10 minutes, alerts me on Telegram if anything breaks

Each creator runs as a separate n8n workflow on a staggered timer (67s, 71s, 73s, 79s — all prime numbers so they never overlap). This prevents rate limiting and ensures only one API call happens at a time.
---
## What I Learned (The Hard Way)

**1. Fanvue's API is undocumented and full of gotchas.**

- Chat objects have NO uuid field — the fan UUID is at `chat.user.uuid`
- GET endpoint for messages is plural (`/messages`), POST endpoint for sending is singular (`/message`)
- Messages come newest-first. If you don't reverse them before sending to AI, the conversation is backwards and the AI gives nonsensical replies
- No `is_creator` field on messages — you have to check `sender.handle` to figure out who sent what

**2. Token management is life or death.**

If your refresh token gets used twice (race condition between two processes), it's permanently dead. You have to re-authenticate through the browser. I lost 3 days debugging this before I realized the solution was radical simplicity: ONE process refreshes tokens. Period.

**3. The AI needs guardrails, not freedom.**

Early versions would occasionally go off-script — promising things the creator doesn't offer, being too aggressive with PPV, or switching personality mid-conversation. The fix was strict system prompts with explicit boundaries and a "humanization" layer that adds natural imperfections (typos, delayed responses, varied message lengths).

**4. Free followers are a time sink.**

Unlimited free messaging = the AI spending all its time on people who will never pay. I added a 10-message limit for free followers, then a gentle push to subscribe. Revenue went up immediately.
---
## Results So Far

The system has been running autonomously for several weeks now. Key numbers:

- **Response time:** Under 60 seconds, 24/7 (vs 1-4 hours with VAs)
- **Uptime:** 99.9% (one restart in 3 weeks, auto-recovered)
- **VA cost eliminated:** $0/month (was projecting $3-5K/month)
- **Server cost:** $24/month
- **Messages per day:** 200-400 across all creators
- **No fan complaints** about AI detection (persona training works)

The system handles the entire fan lifecycle — from new subscriber welcome to dormant win-back — without me touching anything. I check the dashboard once a day, usually for 2 minutes.
---
## What's Next

I'm expanding the system to handle:

- Automatic PPV content creation (AI-generated images sent as locked messages)
- Cross-platform fan tracking (same fan on multiple platforms)
- Revenue prediction per fan (predict who will buy next and prioritize them)
---
## Questions?

Happy to answer technical questions about the architecture, Fanvue API, token management, or anything else. I'm NOT going to share the actual code or system prompts, but I'll answer "how did you solve X" type questions.

If anyone is running a similar setup or considering building one, I'm curious what your biggest bottleneck is. For me it was 100% the token management — everything else was straightforward once that was solved.

I would be very interested in this, me and my AI partner, are creating models, and we are fining the chatting to be a very key element in this whole business model, would you be interested in making and ap that people can rent, i am not a coder, i make the videos and images, coding is a different ball game,

 

[gtxgtxgtx]

no matter what i use fanvue just never worked for me

 

[Avarage12]

Can I create this with lovable?

 

[untaxed]

I would be very interested in this, me and my AI partner, are creating models, and we are fining the chatting to be a very key element in this whole business model, would you be interested in making and ap that people can rent, i am not a coder, i make the videos and images, coding is a different ball game,

I'm not a coder either. Visit the fanvue store, they have chatting apps and so on. I combine Claude + an AI agent for the chatting

Can I create this with lovable?

I don't know ask chatgpt or Claude

 

[yarek]

Some updates on your chatbot? Do you sell subscription? Whats your conversion rate?

 

[untaxed]

Some updates on your chatbot? Do you sell subscription? Whats your conversion rate?

Found a way to use claude for NSFW with custom instructions, nobody notices it's AI.

 

[saifafzal241]

It looks quite affordable at the cost of $24 per month for VPS. I will only make sure that all accounts are using the same IP address, as problems with one of the accounts can lead to problems with other accounts as well. Wondering how it has worked with multiple accounts till now?

 

[untaxed]

It looks quite affordable at the cost of $24 per month for VPS. I will only make sure that all accounts are using the same IP address, as problems with one of the accounts can lead to problems with other accounts as well. Wondering how it has worked with multiple accounts till now?

My setup is enough as it is.

 

[untaxed]

These are stats for my 4 models last month, 100% AI CHATTING, I sent 0 replies, told claude code what to do. Most money came from PPV's and tips, had free trials for the 4 models.

 

[PINKAI]

Hi, how long does it take to get the Fanvue API keys? I heard that when you ask for them, they include you in a waiting list.

I'm thinking about creating a chatter for Fanvue, but I don't know if it's worth with their API or if I should try a different approach.

Thank you!

create an account as a creator and you get access to the API and documentation

 

[megarampo]

Solid writeup, the token management part alone saves people weeks.
To answer your bottleneck question from the other side of the table: I run the supervised version of this (AI drafts, a human reads and sends every line) for operators who can't or don't want to build their own stack, and my bottleneck was never the tech. It was the humanization layer you mention in point 3.
What I found after a few hundred fan conversations: the model doesn't get caught on content, it gets caught on shape. Same message length every time, always answering every question, tidy punctuation, never having an opinion. Fans don't think "this is AI", they think "she's not really here" and stop buying. The fixes that moved PPV conversion for me were boring ones: mirror the fan's register (if he writes 4 lowercase words, she answers in 4 lowercase words), split replies into 2-3 short bursts instead of one paragraph, and let her occasionally not answer something. Your "typos + delays + varied length" list is the right direction, I'd add register mirroring as the biggest one.
For the people asking "can I do this without coding": the store apps untaxed mentioned work, but none of them fix the shape problem out of the box. Someone still has to tune the persona per creator and read what goes out, at least for the first weeks. That's the part I'd budget for before the VPS.
Curious whether your free-trial subs convert to paid at a different rate with the 10-message cap, or if the cap mostly just saves tokens.

 

[kurera]

Absolute monster setup you got, very interesting read. I’ve been planning on setting up an automated messaging configuration myself and this has given me some ideas. Good read!

 

[itsworth]

Hey bro, good to leave claude .md file formatation schema, if anyone wanted to develop this you already sent the fundament in a way claude clearly understand!

 

[untaxed]

Solid writeup, the token management part alone saves people weeks.
To answer your bottleneck question from the other side of the table: I run the supervised version of this (AI drafts, a human reads and sends every line) for operators who can't or don't want to build their own stack, and my bottleneck was never the tech. It was the humanization layer you mention in point 3.
What I found after a few hundred fan conversations: the model doesn't get caught on content, it gets caught on shape. Same message length every time, always answering every question, tidy punctuation, never having an opinion. Fans don't think "this is AI", they think "she's not really here" and stop buying. The fixes that moved PPV conversion for me were boring ones: mirror the fan's register (if he writes 4 lowercase words, she answers in 4 lowercase words), split replies into 2-3 short bursts instead of one paragraph, and let her occasionally not answer something. Your "typos + delays + varied length" list is the right direction, I'd add register mirroring as the biggest one.
For the people asking "can I do this without coding": the store apps untaxed mentioned work, but none of them fix the shape problem out of the box. Someone still has to tune the persona per creator and read what goes out, at least for the first weeks. That's the part I'd budget for before the VPS.
Curious whether your free-trial subs convert to paid at a different rate with the 10-message cap, or if the cap mostly just saves tokens.

I stopped the free trials. 99% don't sub they just try to get free content peeking. I'd rather just let AI chat people that actually made a minimum investment (sub fee).

Most people are just time wasters trying to get free gf experience.

Instead of the 10 message sequence, I now let AI get info about the sub to see how much can he spend, first step is to try to build a relationship then slowly get more into more spicy stuff and start with cheaper to more expensive PPVs as the conversation flows.

Tag sub whale potential - > Build relationship - > Sell image PPV (less expensive) - Selling Video PPV (more expensive). And repeat

 

[untaxed]

Hey bro, good to leave claude .md file formatation schema, if anyone wanted to develop this you already sent the fundament in a way claude clearly understand!

Yes you need to keep updating the memory with the lessons and chatting instructions to not let AI do random stuff

 

[ledrig]

Love the setup, must have been satisfying getting that automation up, haha. A quick question regarding what you wrote in the orignal message:

"The content generation side was automated (AI images, AI video, automated posting across IG/Threads/Twitter)".

Could you expand on that part, even before the users get to Fanvue? In the hopes this does not land out of the scope of this thread. How can I imagine such a system? Like what models are used for image/video generation?

 

[untaxed]

Love the setup, must have been satisfying getting that automation up, haha. A quick question regarding what you wrote in the orignal message:

"The content generation side was automated (AI images, AI video, automated posting across IG/Threads/Twitter)".

Could you expand on that part, even before the users get to Fanvue? In the hopes this does not land out of the scope of this thread. How can I imagine such a system? Like what models are used for image/video generation?

You can get comfyui workflows to generate images and videos and rent a powerful gpu on runpod. Then you can connect runpod with Claude Code via MCP and have Claude generate 100s of images on autopilot for Fanvue. Same with videos.

 

[megarampo]

makes sense, free trials attract exactly the guy who wants the gf experience for $0. that ladder is basically what good human chatters call spend mapping, interesting to see it works automated too. How do you tag whale potential early - explicit signals in what they say (job, lifestyle) or purely from behavior like tip speed and first PPV reaction?