This webinar focuses on Generative AI, featuring global Cloud and AI leaders AWS, Microsoft and Google, covering RAG, Fine-Tuning, Prompt Engineering and Security, Deployment Recommendations, AI Virtual Assistants, and more.
Date/Time: September 17, 1 PM ET Start
Scroll down to see the full and detailed agenda, plus expert speakers. Click on their name to view their Linkedin profile, and session title for additional information. There is time for live interaction/Q&A with the speakers so have your questions ready. CPE credit hours are provided.
Please use your Angelbeat account - created on the secure Memberspace platform, at no charge - to register to attend this webinar (hosted on Zoom), which also lets you download slides, watch on-demand videos, plus signup for future programs with one-click. If you already have an account, you will be asked to confirm your registration. Otherwise you are prompted to fill out a simple contact form.
Speakers, Topics, Agenda
1 pm ET Ron Gerber, CEO Angelbeat
Angelbeat and Webinar Overview.
Angelbeat CEO and webinar emcee Ron Gerber summarizes the agenda and introduces the speakers.
He will discuss why every organization needs to create their own “AI Risk Management Framework”.
1:05 Priya Aswani, Director Architecture and Strategy, Microsoft
Prompt Engineering, Construction, Learning: GPT-3, GPT-3.5, and GPT-4 models from OpenAI are prompt-based. With prompt-based models, the user interacts with the model by entering a text prompt, to which the model responds with a text completion. This completion is the model’s continuation of the input text.
While these models are extremely powerful, their behavior is also very sensitive to the prompt. This makes prompt construction an important skill to develop.
Prompt construction can be difficult. In practice, the prompt acts to configure the model weights to complete the desired task, but it's more of an art than a science, often requiring experience and intuition to craft a successful prompt. The goal of this session is to help get you started with this learning process. It attempts to capture general concepts and patterns that apply to all GPT models. However it's important to understand that each model behaves differently.
Prompt Hacking and Shields: Generative AI models can pose risks of exploitation by malicious actors. To mitigate these risks, Microsoft integrates safety mechanisms to restrict the behavior of large language models (LLMs) within a safe operational scope. However, despite these safeguards, LLMs can still be vulnerable to adversarial inputs that bypass the integrated safety protocols.
Prompt Shields is a unified API that analyzes LLM inputs and detects User Prompt attacks and Document attacks, which are two common types of adversarial inputs.
1:25 Dr. Ravishankar Rao Vallabhajosyula, Senior Director, Data Science, Impetus
Towards Intelligent Enterprise: Harnessing GenAI to Transform Enterprise Operations
As enterprises explore the potential of Generative AI (GenAI) across diverse use cases, the demand for robust and scalable AI-driven solutions is at an all-time high along with the skills and expertise to deliver them. In this session, we will dive into practical applications of GenAI, focusing on various use cases like intelligent search, advanced chatbots, and document analysis solutions.
Join experts from Impetus as we showcase how we help customers build powerful GenAI solutions to collect critical information from documents via entity extraction and validate and reconcile data spread across multiple sources. We will address how GenAI can be utilized to identify, differentiate, and match documents with precision ensuring cost-effective and efficient solutions.
Additionally, discover how Impetus' GenAI Innovation Labs plays a pivotal role in accelerating AI adoption and innovation in the enterprise.
Key Takeaways:
Discover how GenAI enhances enterprise workflows with intelligent solutions
Learn how to automate document analysis, entity extraction, and validation using GenAI
Explore cost-effective methods for identifying, differentiating, and matching similar documents
Uncover real-world customer success stories with GenAI related to matching use cases for financial services along with development of a sentiment analysis solution for customer feedback
Explore how Impetus GenAI Innovation Labs, with industry’s first collaborative, rapid building-block approach, can help you design and develop enterprise-grade GenAI solutions in less than 6 weeks
1:45 Jeff Meacham, Principal Technical Engineer, Trellix
Unlocking AI-Driven Security: Trellix Wise and Amazon Bedrock in Action
In this session, attendees will explore how the integration of Amazon Bedrock telemetry with Trellix XDR delivers unparalleled observability into AI-enabled applications. This integration offers complete visibility into the outputs of generative AI (GenAI) workloads, helping to detect suspicious activities and malicious content. Attendees will also learn how to enforce guardrails around data privacy and promote responsible AI practices, ensuring the safe deployment and management of GenAI in their environments.
2:05 De'Shedric Boler, Solutions Architect, AWS
Amazon Bedrock, the Easiest Way to Build and Scale Generative AI Applications with Foundation Models, plus insights into Fine-Tuning and Retrieval Augmented Generation (RAG) Strategies
Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies like AI21 Labs, Anthropic, Cohere, Meta, Mistral AI, Stability AI, and Amazon through a single API, along with a broad set of capabilities you need to build generative AI applications with security, privacy, and responsible AI.
Using Amazon Bedrock, you can easily experiment with and evaluate top FMs for your use case, privately customize them with your data using techniques such as fine-tuning and Retrieval Augmented Generation (RAG), and build agents that execute tasks using your enterprise systems and data sources.
Since Amazon Bedrock is serverless, you don't have to manage any infrastructure, and you can securely integrate and deploy generative AI capabilities into your applications using the AWS services you are already familiar with.
2:25 Naresh Jasotani, Principal Technologist, Gen AI Ambassador, Google
Vertex AI offers access through the Google Cloud to Gemini models, which are capable of understanding virtually any input, combining different types of information, and generating almost any output.
Learn how to prompt and test in Vertex AI with Gemini, using text, images, video, or code.
With Gemini’s advanced reasoning and state-of-the-art generation capabilities, developers can try sample prompts for extracting text from images, convert image text to JSON, and even generate answers about uploaded images to build next-gen AI applications.
In addition to Gemini, you can access and deploy Gemma, a family of lightweight, state-of-the-art open source models, built from the same research and technology used to create the Gemini models.