Building @ChatFrom_io, a platform to build your own AI chatbot. 12 startups in, now going solo. I test LLMs and agents and share what I learn along the way
Berlin
Joined January 2011
- Tweets9.9K
- Following421
- Followers891
- Likes14.7K
Pinned Tweet
ChatFrom has quietly been live for about 10 days and I never officially announced it 😄 So here it is.
@ChatFrom_io lets you build your own AI chatbot, and it runs on the open-source chatbot engine I built a month ago. It can be anything you need, a customer support bot, an internal assistant for your team, or something else entirely. I wanted the whole flow to stay really simple.
1. Add your knowledge from documents, your website, Q&A, Google Docs, Notion or any kind of text
2. Set the system prompt, settings and guardrails yourself, or let ChatFrom Assist do it for you
3. Pick your models
4. Connect tools like Stripe, Shopify, Calendly, any MCP or API, and hand off to a human when needed
5. Keep it as simple Q&A on your docs, or draw your own workflow with different paths and conditions
6. Put it on your website, Telegram, WhatsApp, Slack or Discord in minutes
On top of that you can run evals on your models and workflows, and connect Langfuse for analytics.
Under the hood my engine uses advanced RAG, so searching your docs is fast, cheap and reliable. It re-ranks the results and works in any language, no matter what language your docs are written in. Workflows run on LangGraph, so you can build pretty much any kind of flow for your chats.
Would love your feedback, link in the first reply 👇
iPhone Duo hands-on.
It feels really premium. Touching the inner screen doesn’t feel like touching a plastic screen at all, it feels like glass
And of course, it’s sold out everywhere
Your shop's chatbot can answer everything on your website except the one thing customers ask the most. Where's my order?
That answer lives in Shopify, not on a page, so most bots just tell people to check their email.
So I made @ChatFrom_io connect to your store. The customer gives their order number and email, and it finds the order and sends the tracking link. They can even start a return, and you just approve it in Shopify.
I wrote up the whole setup, it takes under an hour 👇
Here's the full guide, with how the order lookups and returns work and how to set it up step by step
chatfrom.io/blog/ecommerce-c…
Rouzbeh retweeted
ChatFrom has quietly been live for about 10 days and I never officially announced it 😄 So here it is.
@ChatFrom_io lets you build your own AI chatbot, and it runs on the open-source chatbot engine I built a month ago. It can be anything you need, a customer support bot, an internal assistant for your team, or something else entirely. I wanted the whole flow to stay really simple.
1. Add your knowledge from documents, your website, Q&A, Google Docs, Notion or any kind of text
2. Set the system prompt, settings and guardrails yourself, or let ChatFrom Assist do it for you
3. Pick your models
4. Connect tools like Stripe, Shopify, Calendly, any MCP or API, and hand off to a human when needed
5. Keep it as simple Q&A on your docs, or draw your own workflow with different paths and conditions
6. Put it on your website, Telegram, WhatsApp, Slack or Discord in minutes
On top of that you can run evals on your models and workflows, and connect Langfuse for analytics.
Under the hood my engine uses advanced RAG, so searching your docs is fast, cheap and reliable. It re-ranks the results and works in any language, no matter what language your docs are written in. Workflows run on LangGraph, so you can build pretty much any kind of flow for your chats.
Would love your feedback, link in the first reply 👇
So Anthropic is building its own personal agent app, like Grok Bot and Dots, with Claude Duet.
I already use Opus 5.5 to write my code every day, so an agent running on it that keeps working while I'm away sounds pretty wild.
Really want to get my hands on this, already in the waitlist
Rouzbeh retweeted
crew member @justrouzbeh just shipped ChatFrom 🚢
ChatFrom lets you build and customize AI chatbots for any purpose using visual workflows, without writing code.
shipped 0 days away from certain death
feedback from the crew — the captains reviewed it:
"super clean! I'd tighten the hero by leading with one concrete use case, like support or Shopify order lookup, because the current top section packs in a lot at once. Keep going, captain."
You can try ChatFrom at @ChatFrom_io
chatfrom.io
and the open-source engine behind it is here github.com/rouzbeh-abadi/cha…
Two cheap Flash models in two days, DeepSeek yesterday and MiniMax today.
In ChatFrom I use a cheap, fast model for the small jobs that run before the chatbot replies. It works out what the customer is asking for, like a question, a booking or billing, and makes sense of short follow-ups in the chat. Right now that's Claude Haiku 5.5. Last week I tested it against 3 other models on the same 20 tasks, and they all got every one right, so I picked Haiku because it was the fastest of the cheap ones.
Now I'm thinking of putting both new Flash models through the same test. What do you think, could either of them beat Haiku?
I make ChatFrom, so I tried hard to be fair comparing it with Chatbase.
They do the exact same job, a chatbot that answers your customers from your own docs. Both even charge in credits. The difference is how far those credits go.
Where Chatbase wins
1. Way more AI models, including the big ones like Opus
2. Messenger, Instagram, phone and mobile app kits
3. A built-in help desk and team seats
4. You can remove the branding
Where ChatFrom wins
1. The same answers cost a lot less every month
2. Shopify, Stripe and booking tools on every plan
3. Telegram, Discord and Crisp
4. Data kept in Germany, even on the free plan
5. It shows the source under every answer
If you're already happy on Chatbase and use those extras, stay. If you're a small business picking for the first time, I think ChatFrom fits better.
Full breakdown in the first reply 👇
Price, models, channels, tools and hosting side by side, with the gaps I haven't closed yet chatfrom.io/blog/chatfrom-vs…
Rouzbeh retweeted
DO NOT change anything on your paywall after the review.
Neither from RevenueCat Remote Paywall nor through any kind of dynamic config
I think a lot of people are confusing remote config with hidden config
Remote config is fine:
- A/B testing your paywall or onboarding
- Changing your paywall design without an update
- Testing different prices and offers
Hidden config is the problem:
- Showing Apple one paywall during review
- Switching to a different one once you're approved
- Turning on things Apple would never accept, like a hidden close button
If Apple could see it during review and approve it, you're fine
If you're using a flag so Apple doesn't see it, that's what 2.5.19 is going after
So for most of us nothing really changes
DO NOT change anything on your paywall after the review.
Neither from RevenueCat Remote Paywall nor through any kind of dynamic config
I think a lot of people are confusing remote config with hidden config
Remote config is fine:
- A/B testing your paywall or onboarding
- Changing your paywall design without an update
- Testing different prices and offers
Hidden config is the problem:
- Showing Apple one paywall during review
- Switching to a different one once you're approved
- Turning on things Apple would never accept, like a hidden close button
If Apple could see it during review and approve it, you're fine
If you're using a flag so Apple doesn't see it, that's what 2.5.19 is going after
So for most of us nothing really changes
Most people think the big model does all the work in a chatbot. It doesn't.
Before it answers, a tiny model has already done 3 jobs
Followed the conversation. Someone asks "do you ship to Germany?" and then "how long does it take?", and it knows they still mean Germany
Worked out what they want, a quick answer, a booking or help with billing
Matched a question in Spanish or Japanese to the right part of English docs
This week I swapped that model in ChatFrom and tested 4 options on the same 20 tasks. All 4 got 20/20, so price and speed picked the winner.
- GPT-4.1 mini (my old one) $0.107 per 1k calls, 0.82s
- Gemini 3.5 Flash-Lite $0.086, 0.76s
- GPT-6 Luna $0.042, 2.0s
- Claude Haiku 5.5 $0.042, 0.98s
Claude Haiku 5.5 won. It's the same price as GPT-6 Luna at half the wait, and about 60% cheaper than my old one.
It's live for every ChatFrom chatbot now.
