I also tested something that requires an external API and it's pretty magical. This bot allows Claude to get the latest charts from Billboard, tap into the Spotify API, authenticate the user, and generate a playlist based on the latest standings.
https://t.co/A3is5ENqh6
Another big launch today!
There're a lot of visual workflow builders out there, but I believe this is the most accessible way for anyone to start building AI workflows, without having to learn a new interface.
Just chat with our Script Bot Creator and voilà!
Introducing script bots, a new way to combine models and automate workflows on Poe.
Script bots are created through vibe coding with Script Bot Creator and can combine any of the 200+ text, image, video, and audio models on Poe, plus any other bot on the platform. (1/9)
It was super easy to use. I was able to one-shot a script bot to automate a multi-step task. This bot takes a long PDF, converts each page into an image, then stitches all of them together, and finally outputs an image that you can download. Check it out!
https://t.co/rcGiYeL9wK
@wreckitneil @poe_platform You can bring multiple bots into the same chat by @-mentioning them, either by doing it one at a time, or all at the same time. https://t.co/XJ0z09kDqL
Congrats to the team on such a big milestone after months of work and overcoming all the challenges. Poe is now multi-bot, multi-modality, and multi-user!
Bring all your friends into a single chat with all the latest LLMs, to build and play games or plan your next outing.
Introducing group chat on Poe: a new way to collaborate with any AI and anyone you know, all in a single conversation.
Now available to all users worldwide, groups can interact with any of the 200+ text, image, video, or audio models on Poe, plus any creator-made bots. (1/8)
Four new OpenAI models are now on Poe: GPT-5.1-Instant, GPT-5.1, GPT-5.1-Codex, and GPT-5.1-Codex-Mini.
Instant is smart and more conversational, the full 5.1 model includes dynamic reasoning, and Codex models power coding via the Poe API. (1/2)
We are launching an API for Poe today. Poe accounts can now be used to power Cursor, Cline, Roo Code, and anything else you or others build. All models and bots can be accessed via the API, and you can purchase points at cost to go beyond subscription limits. See thread below.
We are opening up a new role at Quora: a single engineer who will use AI to automate manual work across the company and increase employee productivity. I will work closely with this person.
Now on Poe: Veo 3!
Veo 3 sets a new standard as the most advanced video model yet, producing highly realistic visuals and immersive audio from text and image-based prompts. (1/2)
In building Poe Apps, we wanted to test interesting ways to combine multiple AI models into intuitive visual tools. Chibify is a fun example of what’s possible - transforming photos into 3D anime-style art by connecting GPT-4o with FLUX-Pro-1.1. (1/3)
HUGE Launch today!
Up til this point, it requires a lot of effort to build apps that are powered by LLMs, not to mention across different modalities. We've made that possible through Poe because we offer 100+ models.
Introducing Poe Apps: a new, easy way to create and use visual interfaces into any combination of the 100+ text, image, video, and audio models on Poe. (1/5)
Here's an idea I'm working through... just vibe coding here:
Use Poe's web-search capabilities to get today's headlines, pass those headlines to Claude to write an article, then have Elevenlabs read the article. It's not there yet, but I'm using App Creator to iterate on it.