Real-World AI Automation with Lambda & Bedrock

Where can AI change the game for your business? Are you expanding your product suite for AI opportunities? Pivoting the entire business? Starting fresh with a new venture? Maybe considering AI as tailwinds for your existing business? In this talk I cover Custom Ink's real world usage and how we used the WINS framework from HBR to focus our opportunities and learning where GenAI can be applied. What is an AI Agent and what is the hype? We cover all this and how easy you can make your own agents with AWS Lambda and Amazon Bedrock using simple JavaScript API calls.

Transcript

1. Real-World AI Automation with Lambda & Bedrock
2. 🌎 What Does Real-World Mean?
3. https://www.coatue.com/blog/company- update/coatues-2023-emw-conference
4. 🔵 Expand Product Suite with AI
5. 🔵 Expand Product Suite with AI GenAI Sprinkles
6. 🟢 Pivot Entire Business
7. 🟢 Pivot Entire Business https:/ /www.databricks.com/dataaisummit
8. 🟣 Start Fresh New Venture
9. 🔴 New Tailwinds for Existing
10. 🔴 New Tailwinds for Existing
11. 🔴 New Tailwinds for Existing https:/ /dev.to/aws-heroes/rags-to-riches-part-1-generative-ai-retrieval-4pd7
12. Q: Where Should Your Company Start? https:/ /hbr.org/2023/09/where-should-your-company-start-with-genai
13. A: Use The WINS Framework https:/ /hbr.org/2023/09/where-should-your-company-start-with-genai (W)ords (I)mages (N)umbers (S)ounds More refined & precise category of knowledge work for GenAI adoption. Lever: Enhances productivity in non-digital fields Crucible: Essential for tech-heavy sectors Balcony: Min. impact on manual labor sectors. Next: Improves engagement in traditional Industries
14. • 🗺 New Tailwinds for your Existing Business • 🎛 WINS Holding a Lever: “Selling” part of SG&A • ⏭ WINS Next in Line: Digital Front Door or Engagement 🌎 Real-World AI Summary 🧠
15. 🤖 AI Agents & Automation
16. • Digital assistants similar to Siri or Alexa but more advanced. • Uses Generative Pre-Trained (GPT) models to Reason & Act. • Can use Data and Tools to help inform decision making. • Can automate routine or large complex business tasks. • Fast to market and easy to augment with new data. • No upfront investments in compute training or data science. • Can fine-tune pre-trained models to increase accuracy. 🦾 What are AI Agents? 🧠
17. I AM HERE! 🦾 What are AI Agents? 🧠 https:/ /blog.langchain.dev/openais-bet-on-a-cognitive-architecture/
18. 🦿OpenAI’s Custom GPTs https:/ /openai.com/blog/introducing-gpts
19. 🦿OpenAI’s Custom GPTs https:/ /openai.com/blog/introducing-gpts
20. 🦾 What are AI Agents? 🧠
21. 🦾 What are AI Agents? 🧠
22. Real-World AI Agent Example 🤖
23. 🎈 Real-World AI Automation
24. 🔍 Real-World AI Automation
25. 🔍 Real-World AI Automation
26. 🔍 Real-World AI Automation
27. ➕ Bedrock is Simple. Easy API Usage. Serverless Billing. ➕ Anthropic Claude Models are Amazing! Bedrock PE Guide. 𝚫 Wrapped API Access lacks new Tools & System Prompts. 𝚫 Token Usage is in CloudWatch Metrics vs. API Responses. 𝚫 Moving from Token to Provisioned has HUGE $$$ Gaps. ? Value or Not in Bedrock’s Agents & Knowledge Products? ? New Local Development Patterns. Dataset-Driven. 🪨 Real-World Bedrock Learnings https:/ /docs.google.com/presentation/d/1tjvAebcEyR8la3EmVwvjC7PHR8gfSrcsGKfTPAaManw/edit?usp=sharing