It offers robust LLM Firewall solutions, ensuring your data and identity are protected in the AI space. Our service secures your data, offers prompt anonymity, and prevents unauthorized access. Perfect for users valuing security.
Congratulations on the launch !
It's great to see new products that start addressing privacy for LLMs!
Can you elaborate on what LLMs do you support right now?
And what do you think of automations with Zerotrusted, can you give some utility examples to the Zapier integration?
Best of luck !
Hey @abdellah_abbous ,
Here are your answers,
- We currently support ChatGPT 3.5, ChatGPT 4, Claude, Llama 2, CoHere & Palm LLMs.
- We have Zapier integrations to automatically send chat reports.
For example, if you have an automation to automatically create blog posts using ChatGPT and post it in your site, then your Zapier integration can be used in between to see if the ChatGPT generated post is Plagiarism & Copyright free as well as we give an AI text detection score to make your blog/posts stronger.
- Additionally, we have our Adapter library using the LangChain which allows you to quickly integrate our APIs.
I would love to show you a demo on Zapier integrations and LangChain integration, please reach out to contact@zerotrusted.ai to initiate a discussion on this.
wow, very cool! Are there any limitations or everything is the same as using the native apps but through the privacy firewall?
Great idea! Congrats on the launch :) !
@anthony_latona
Currently, it's hard for us to show the history like ChatGPT since we don't store it anywhere. The history is only visible per session and it's securely stored in session on your browser, so it'll be cleared after the logout. So, it's the limitation that we've exposed for security reasons.
That's the most limitation as of now.
Thanks! Glad you liked it.
@johny_burg While integrating for any business needs, if you use the Zapier integration, it'll be a low-code/no-code solution. It'll be easy for you to quickly integrate and maintain.
@sidraref congrats on the launch! I really like the focus of personal security / data protection as it relates to LLMs and the growing comfortability with common folks and AI in their lives.
Curious - what do you see as the biggest barriers re: hitting scale for a model like this?
@sidraref@dzaitzow thanks for the kind words and feedback!
Our challenges are actually vast to be honest.
But we knew what we were getting into was not going to be easy. We are constantly working on performance to ensure we do all the heavy lifting behind the scenes while maintaining decent response time.
With our reliability feature - it runs your query through multiple LLMs then scores the best result, we experience delays so we are re-designing our approach to improve performance by as much 75%.
Overall we are ecstatic as we continue to get great feedback from both individual users and our enterprise customers.
Please message us at contact@zerotrusted.ai if you have any questions or there is anyway we could be of assistance.
Report
@sidraref@dzaitzow@femitfash Can you please quantify the latency of your middleware here in public, so that the community knows? Thanks in advance.
Report
This product is great. I really like the fact that I can now anonymize my prompts! ZeroTrusted.ai is off to the races; get onboard now! Prompt with confidence!!!
With the fast pace of AI today, it's absolutely vital that we build trust into the systems being created. Right now, I'd argue that isn't happening. But I'm a big fan of this step you've taken! Incredible work. 🙌
@trent_kennelly thanks Trent. I also agree that we should not blindly trust the LLM providers to police themselves. Thus, we need additional measures to help ensure our individual or business privacies are maintained.
Hello, Product Hunt community! I am excited to share my first launch ZeroTrusted.ai's LLM Firewall with you all. In a world where data privacy and security are paramount, our solution offers a robust shield for your Large Language Model interactions.
Features like prompt anonymization, advanced encryption, and our unique ztPolicyServer ensure your AI experiences are not just secure but seamlessly integrated with your daily workflows.
We're here to support you every step of the way, with detailed documentation, responsive email support, and live training sessions for higher-tier plans. Your feedback is invaluable to us—it drives us to continuously improve and adapt our offerings to meet your needs.
Explore our plans, try out our features, and let us know how we can make your AI interactions not just safer, but smarter.
Thank you for your support and curiosity❤️
Devinstock
ZeroTrusted.ai
350+ E-Commerce Tools Database
ZeroTrusted.ai
Serand
ZeroTrusted.ai
Outcome
ZeroTrusted.ai
ZeroTrusted.ai
ZeroTrusted.ai
ZeroTrusted.ai
ZeroTrusted.ai
ZeroTrusted.ai