Guardrails AI

We are doing a fireside chat with Demetrios Brinkmann, Founder of @mlopscommunity on how simulation is reshaping the way we systematically test AI applications. When: Weds 10/29 at 9am PST Register: home.mlops.community/public/events/… See you there!

Final Reminder Join our co-founder and CEO, Shreya Rajpal, tomorrow at 9am PT to see how you can build reliable AI through simulation testing. If you’ve built AI agents then you know how challenging it is to test them. Learn to simulate realistic user behavior for AI applications with Snowglobe Register here: go.guardrailsai.com/reliable-ai

If you’ve built AI agents, you know how challenging it is to test them. How do you even begin formulating a test plan for a technology whose input space is infinite? Join our co-founder and CEO, Shreya Rajpal, on Sep 11 at 9am PT to see how you can build reliable AI through simulation testing with @snowglobe_so. Register here: go.guardrailsai.com/reliable-ai

Introducing ❄️ @snowglobe_so, the simulation engine for AI chatbots. Magically simulate the behavior of your users to test and improve your chatbots. Find failures before your users do.

Join us today at 10am PT as we introduce the LLM Guardrails Index—the most comprehensive evaluation of LLM guardrails. Built on open-source data and code for reproducibility, this webinar will reveal key findings on PII, jailbreaking, and more. Register now! go.guardrailsai.com/indexweb

Introducing the AI Guardrails Index—the most comprehensive evaluation of LLM guardrails. Built on open-source data and code for reproducibility, this index reveals key findings on PII, jailbreaking, and more. Check it out! go.guardrailsai.com/index

We’re writing Alfredo’s Pizza Kitchen as a RAG app. It’s simple chroma db that indexes delivery, pickup, location, employee, menu, payment, and account management information. It should be able to help users with all of these. Let us know what’s missing! We’ll open source this bot once it’s ready.

We’re building a model LLM app to find how easy it is in 2025 to build reliable apps on primary models. The bot is going to service the fictional “Alfredo’s Pizza Cafe”. It’s meant to answer questions about the fictional place, and try to stay on topic and hide sensitive information. Follow along to see how this develops!

We’ve revamped our llamaindex integration! Check it out here: go.guardrailsai.com/PYg8SUE

Happy New Year from Guardrails AI! 🎉 2024 was incredible thanks to you: 1M+ LLM calls protected weekly 64 validators (largest out there!) 500K+ installations 2,700+ commits Help shape 2025—fill out our quick survey: go.guardrailsai.com/srv25

By popular demand, we’ve launched Guardrails PII Detection and Jailbreak Prevention. 2 powerful new AI validators to help you build robust, reliable, and trustworthy AI applications Now available on the Guardrails Hub: go.guardrailsai.com/pjb #LLMSafety #AISafety #AIValidation

This week our CEO, Shreya, will be speaking at SmallCon, a free virtual conference for GenAI Builders, hosted by Predibase! Shreya will be joining Nvidia, Mistral, Salesforce, Meta, and other AI leaders to discuss the future of GenAI and how to mitigate risk with model governance and guardrails. The event is free- sign up here: pbase.ai/smallconguardr…

We are excited to share that our CEO will be speaking at SmallCon, a free virtual conference for GenAI Builders, hosted by Predibase! Shreya will be joining Nvidia, Mistral, Salesforce, Meta, and other AI leaders to discuss the future of GenAI and how to mitigate risk with model governance and guardrails. The event is free, save your spot:  pbase.ai/smallconguardr…

This Thanksgiving we're thankful to our community, customers, contributors, partners and team for helping us crossing 1 million in weekly protected LLM requests! 🥳 Thank you all!

Hear from the Guardrail AI co-founders explain how Guardrails Pro can secure AI operations — enabling faster, safer adoption of LLMs at scale. Register here: us06web.zoom.us/webinar/regist… #AIsecurity #LLMsecurity #LLMguardrails #AIguardrails

Join us tomorrow for @Zettaventures' 2024 AI Native Summit in Mountain View! We're proud to be exhibiting at this year's event, which features a speaker lineup of AI researchers, practitioners & founders. Seats are nearly sold out, so register soon: events.zettavp.com/zetta/rsvp/reg…

As GenAI and LLMs rapidly evolve, the impact of data leaks and unsafe AI outputs makes it critical to secure your AI infrastructure. Learn how MLOps and ML Platform teams can use the newly launched Guardrails Pro to: - Provide comprehensive risk coverage to increase AI reliability and innovation - Increase governance efficiency to accelerate LLM adoption - Foster trust in AI while ensuring responsible and secure use #AIsecurity #LLMsecurity #LLMguardrails #AIguardrails

🚨 Last chance to register! Join the Guardrail AI co-founders on Nov 19 to see how Guardrails Pro can secure AI operations — enabling faster, safer adoption of LLMs at scale. Register here: us06web.zoom.us/webinar/regist…

Join us for a webinar on Nov 19 with Guardrail AI co-founders Safeer Mohiuddin and Zayd Simjee to see how Guardrails Pro can secure AI operations — enabling faster, safer adoption of LLMs at scale. Register here: us06web.zoom.us/webinar/regist…

New short course: Safe and Reliable AI via Guardrails! Learn to create production-ready, reliable LLM applications with guardrails in this new course, built in collaboration with @guardrails_ai and taught by its CEO and co-founder, @ShreyaR. I see many companies worry about the reliability of LLM-based systems -- will they hallucinate a catastrophically bad response? -- which slows down investing in building them and transitioning prototypes to deployment. That LLMs generate probabilistic outputs has made them particularly hard to deploy in highly regulated industries or in safety-critical environments. Fortunately, there are good guardrail tools that give a significant new layer of control and reliability/safety. They act as a protective framework that can prevent your application from revealing incorrect, irrelevant, or confidential information, and they are an important part of what it takes to actually get prototypes to deployment. This course will walk you through common failure modes of LLM-powered applications (like hallucinations or revealing personally identifiable information). It will show you how to build guardrails from scratch to mitigate them. You’ll also learn how to access a variety of pre-built guardrails on the GuardrailsAI hub that are ready to integrate into your projects. You'll implement these guardrails in the context of a RAG-powered customer service chatbot for a small pizzeria. Specifically, you'll: - Explore common failure modes like hallucinations, going off-topic, revealing sensitive information, or responses that can harm the pizzeria's reputation. - Learn to mitigate these failure modes with input and output guards that check inputs and/or outputs - Create a guardrail to prevent the chatbot from discussing sensitive topics, such as a confidential project at the pizza shop - Detect hallucinations by ensuring responses are grounded in trusted documents - Add a Personal Identifiable Information (PII) guardrail to detect and redact sensitive information in user prompts and in LLM outputs - Set up a guardrail to limit the chatbot’s responses to topics relevant to the pizza shop, keeping interactions on-topic - Configure a guardrail that prevents your chatbot from mentioning any competitors using a name detection pipeline consisting of conditional logic that routes to an exact match or a threshold check with named entity recognition Guardrails are an important part of the practical building and deployment of LLM-based applications today. This course will show you how to make your applications more reliable and more ready for real-world deployment. Please sign up here: deeplearning.ai/short-courses/…