Generative AI and LLMOps Resources

Fiddler Guardrails, an extension of Fiddler Trust Service, enables real-time scoring to detect risky LLM issues like hallucinations and prompt injection, rejecting malicious inputs before they reach the model.

The Fiddler Trust Service detects and monitors hallucinations, toxicity, PII leakage, and other LLM metrics, ensuring accurate, safe, and secure applications.

See Fiddler in action and discover how Fiddler Trust Models detect and help you safeguard your LLM application while driving business growth.

Practical lessons and experiences on developing AI applications and chatbots using retrieval-augmented generation (RAG) methods.

In this workshop, see how Fiddler users can use the Fiddler Report Generator (FRoG) to create customizable reports for model risk management (MRM) and periodic model health reviews.

Watch this demo to explore how the Fiddler AI Observability Platform for LLMOps streamlines end-to-end LLMOps by enabling data scientists and AI practitioners.

Watch this demo to explore how the Fiddler AI Observability Platform for MLOps enables data scientists and AI practitioners to monitor, explain, analyze, and improve ML models.

Watch this panel of industry leaders share their insights on LLM implementation and their significant impact on business ROI in their respective fields.

In this workshop, Murtuza Shergadwala shares his experiences in building the RAG-based Fiddler Chatbot, and provides tips and tricks on prompt engineering, and more.

Watch this session as Josh Rubin explores the question of whether LLMs can be explained, emphasizing that understanding a model's behavior is crucial for identifying weaknesses, ensuring robustness, and aiding human decision-making.

In this fireside chat with CEOs Krishna Gade and Lukas Biewald, they discuss AI trends, leveraging LLMs, and the complexities of LLM deployment at scale.

In this session, Stanford Professor James Zou discusses how ChatGPT's behavior is changing over time. Discover the fascinating research findings and implications for AI language models.

Watch this workshop to learn the importance of evaluating LLMs using Fiddler Auditor, strategies to mitigate prompt injection attacks, and developments in LLMs.

Watch this AI expert panel discuss the advancements and challenges in LLMs from proof-of-concept to production, the complexities of LLMOps, and regulatory compliance.

Watch this expert panel discuss generative AI in enterprise, focusing on model efficiency, personalization, RAG's role, and aligning AI with business needs.

Watch this keynote from Hanlin Tang on the discussion of the science and engineering behind LLMs in enterprise applications, the choice between buying LLM services from external providers and building custom models, specialized domain-specific models, and more.

Improve LLMs with robustness testing before deploying them to production.

Learn how Fiddler’s unique, clustering-based method accurately monitors data drift in NLP models and LLM-based embeddings.

Learn more about Fiddler Auditor, the open source robustness library that facilitates red teaming of LLMs. Improve LLMs with robustness testing before deploying them to production.

Learn about Fiddler Auditor, the open source robustness library that facilitates red teaming of LLMs. Robustness testing is a critical step in pre-production to minimize hallucinations, bias, and adversarial attacks.

Learn how to track the performance of LLM-based embeddings from OpenAI, Cohere, Anthropic, and other LLMs by monitoring drift using Fiddler.

Watch this session from Ali Arsanjani, PhD, Head of the AI Center of Excellence at Google, to learn about the importance of explainability, adaptability, and risk-minimizing in enterprise generative AI.

Hear from Amit Prakash, CTO and Co-founder at ThoughtSpot; Diego Oppenheimer, Partner and CEO in Residence at Factory; and Roie Schwaber-Cohen, Staff Developer Advocate at Pinecone on how LLMOps optimizes MLOps for LLMs, the key pieces of a generative AI workflow, and how ML teams can leverage LLMs in their applications.

Saad Ansari, Director of AI at Jasper AI, dives into how AI can be used for societal benefit, the importance of intentionality when designing new technology, and applications for generative AI.

Watch this panel session with Ricardo Baeza-Yates, Director of Research at Institute for Experiential AI, Northeastern University; Miriam Vogel, President and CEO at EqualAI, Chair at National AI Advisory Committee; Toni Morgan, Responsible Innovation Manager at TikTok, to learn why responsible AI principles and frameworks are necessary, why model governance is important, and the limitations of LLMs.

Watch this session with George Mathew, Managing Director at Insight Partners to learn about the current state of AI, the different modalities of human and machine interaction, the advancements, and challenges AI presents.

Watch this panel session with Payel Das, Principal Research Staff Member and Manager, Trusted AI a IBM Research; Srinath Sridhar, CEO and Co-founder at Regie.ai; Casey Corvino, CTO and Co-founder at Lavender AI to learn how engineering teams are using generative AI to improve productivity and how IBM is using generative AI to drive medical advances.