Mastering AI Agents: Building Production-Ready Applications
Learn how to build high-performance agents with best practices from industry experts
Building production-ready AI agents with Open Source Software (OSS)
This hands-on workshop covers open source frameworks like Strands and top large language models in Amazon Bedrock and Amazon SageMaker AI. It is in-person and dives deep into advanced topics for building agentic applications.
My Perspective
We attended this event. I was proud to see that my clients and I had already built what they were showing, well before many big companies caught on. Our early use of AI agent technology put us ahead of the curve.
The sessions didn't teach me much new technical content. The real value came from the connections I made. I got to see how other companies are using AI in their work and the challenges they face.
I connected with several enterprise leaders just starting their AI agent journey. Those conversations validated our approach and opened doors for potential collaborations. The gap between newcomers and what we've already built with our clients was eye-opening.
Learning Objectives
- Building agents using foundation models from Amazon Bedrock and Amazon SageMaker AI
- Building agents using open source frameworks (Strands, Crew AI, LangGraph, MCP Server)
- Observe and trace agentic AI applications
- Calculate total costs and business value
Date & Time
Friday, June 20, 2025
8:30 AM - 5:30 PM CDT
Who Should Attend
Developers, Software Engineers, Development Managers, Data Scientists, AI/ML Engineers, AI/ML Architects, Engineering Managers, Directors, and CTOs. You should be building GenAI applications and have a basic understanding of agent concepts.
Agenda
| Time | Session |
|---|---|
| 8:30 - 9:00 AM | Breakfast |
| 9:00 - 9:30 AM | Introduction to agentic AI and Strands Agents |
| 9:30 – 9:45 AM | Workshop environment setup |
| 9:45 – 10:30 AM | Building agents from scratch |
| 10:30 – 10:45 AM | Break |
| 10:45 – 11:30 AM | Open source frameworks deep dive on Crew AI and Strands |
| 11:30 AM – 12:15 PM | Text to SQL agents |
| 12:15 – 1:00 PM | Lunch |
| 1:00 – 2:00 PM | Security analysis using Model Context Protocol (MCP) in OpenSearch |
| 2:00 – 2:45 PM | Evaluating agents and how to get to production |
| 2:45 – 3:00 PM | Break |
| 3:00 – 3:30 PM | Learn how AWS Advanced Tier Services Partner, FloTorch helps their customers move OSS AI agents to production |
| 3:30 – 4:15 PM | Observability and tracing using Langfuse |
| 4:15 – 4:45 PM | Total cost of ownership and business value |
| 4:45 – 5:30 PM | Use cases and discussion |
Key Takeaways & Industry Insights
Enterprise Adoption Trends
Most enterprises are still early in AI agent adoption. They focus on simple task automation, not complex reasoning chains. Many struggle with integration and lack in-house expertise. This confirms our approach: start with focused use cases and expand over time.
Networking Value
I connected with CTOs and AI leaders from healthcare, finance, and retail. Many were impressed by our real-world results and asked for follow-up consultations. These connections have already led to two potential client projects for AI agent work.
Market Positioning
The workshop confirmed we are ahead of the market in AI agent work. Many companies are still experimenting with basic LLM applications. We've already deployed multi-agent systems that handle complex workflows and decision-making for our clients.
Common Challenges
Many attendees raised concerns about hallucinations, data security, and cost management with AI agents. We've tackled these issues with solid evaluation methods, secure data practices, and efficient prompt engineering. That experience puts us in a strong position to help others.
Final Assessment
The workshop's technical content was familiar ground for us. Still, the event gave us valuable market insights and networking opportunities. It validated our approach and showed the wide gap between early adopters and newcomers. We are well positioned to guide organizations through building production-ready AI agents.
Want to Learn More About AI Agents?
This event has passed, but I'd love to share how we've built production-ready AI agents for businesses like yours. Let's connect and explore how AI agents can improve your operations.
Couldn't make it to Mastering AI Agents?
Get the full recap, key takeaways, and presentation slides delivered to your inbox. Everything you missed, condensed into one resource.
Frequently Asked Questions
Common questions about the Mastering AI Agents workshop
This was an advanced hands-on workshop focused on building production-ready AI agents using open source frameworks including Strands, Crew AI, and LangGraph, along with large language models in Amazon Bedrock and Amazon SageMaker AI.
The workshop was held on Friday, June 20, 2025, from 8:30 AM to 5:30 PM CDT at the Amazon Office (DFW11) located at 13455 Noel Road, Suite 1400/14th Floor, Dallas, TX 75240.
The workshop was designed for developers, software engineers, development managers, data scientists, AI/ML engineers and architects, engineering managers and directors, and CTOs who are building GenAI applications and already have a basic understanding of agent concepts.
Topics included building agents using foundation models from Amazon Bedrock and SageMaker AI, using open source frameworks (Strands, Crew AI, LangGraph, MCP Server), text to SQL agents, security analysis using Model Context Protocol, observability with Langfuse, and calculating total cost of ownership and business value.
Girish observed that his clients had already implemented much of what was being demonstrated before many large companies. The real value came from networking connections with enterprise leaders beginning their AI agent journey and understanding how other companies are implementing AI.
Common challenges discussed included hallucinations, data security concerns, and cost management. Girish's experience addressing these issues through robust evaluation frameworks, secure data handling, and efficient prompt engineering positions him well to help others overcome these challenges.
No, this event reached capacity and registration is now closed. However, you can schedule a consultation with Girish to learn about production-ready AI agent implementation for your business.
You can schedule a consultation at gkotte.com/calendar to discuss how AI agents can transform your operations. Girish has already deployed multi-agent systems that handle complex workflows for clients and can help guide your implementation journey.