Shubham Londhe
Happy Learning :)
Pune, India
Actions
Hi, I am Shubham Londhe, a Senior Developer Advocate, passionate about developing and deploying production-ready applications while building and working with teams of Software Developers, DevOps Engineers and Solutions Architects.
After developing Applications in a product-based startup and a mid-size service-based firm, I gained experience in Python, Django, Flask, AngularJS, SQL, Neo4J, MongoDB, DevOps, Docker, AWS, Leadership Skills, and Soft skills.
Getting the responsibility of working with a team of enthusiastic software developers was one of the biggest achievements which improved my communication skills and I could share my knowledge and experience with college students from Symbiosis, MIT, and Pune as well as freshers and Associates.
I believe continuous learning and development to keep myself up-to-date and up-skilled is the solution to modern-day application development for customers and community.
Area of Expertise
Topics
Stepping Into The Agentic Web: Building Smart Applications in the Era of AI
The future of the web is Agentic - where intelligent AI Agents collaborate to create dynamic, responsive applications. In this eye-opening session, we’ll explore the cutting-edge world of Strands Agents and MCP (Model Context Protocol) Servers, and discover how you can leverage these powerful technologies to build the next generation of smart, adaptive web applications.
Through hands-on demos and real-world use cases, you’ll learn how to design and deploy Strands Agents that can autonomously gather information, make decisions, and coordinate with multiple Agents to deliver personalized, context-aware experiences for your users. We’ll delve into the inner workings of MCP Servers, the decentralized hubs that facilitate seamless agent collaboration and communication, empowering your applications to adapt and evolve in real-time.
Discover how to:
- Architect agent-based systems that can do more with less code.
- Leverage MCP Servers to enable secure, scalable agent interactions and context awareness for LLMs
- Unlock the boundless potential of Strands Agents SDK and integrating MCP Servers.
Managing Multi Environment Deployments on GKE using Kustomize
Handling Application deployments in different settings like:
- Development
- Staging
- Production
This can be quite a challenge, especially with container applications managed by Kubernetes.
Google Kubernetes Engine (GKE) provides a strong platform for these tasks, but keeping everything consistent across environments is tough.
That's where Kustomize comes in. It's a tool that makes managing these settings easier, helping to keep everything running smoothly.
In this talk, we will see a practical walkthrough of managing GKE and environments using Kustomize, audience will see a live demonstration of the same by a project.
Towards the end we will also see the industry use cases and best practices of GKE and Kustomize.
Building Durable Agent Harness with Amazon Bedrock Agentcore and Temporal
Building an agent that works once is easy. Building one that survives crashes, retries and long tasks in production is the hard part. In this session I'll show how to wrap your agents in a durable harness using Amazon Bedrock AgentCore for the agent runtime and memory, and Temporal for the durability layer that keeps state and retries alive through any failure. We'll look at where agents break and how to build ones you can actually trust to run on their own.
Context Aware Clusters: Scaling Kubernetes Clusters with EKS MCP Server
Deploying and managing production-ready Kubernetes can be a complex and time-consuming task, especially as your footprint grows. Fortunately, Amazon EKS MCP Server is here to simplify your cloud-native journey.
In this session, we'll dive deep into the power of EKS MCP Server with EKS Auto Mode, and uncover how it can revolutionize the way you approach Kubernetes operations. Learn to leverage intelligent automation to:
- Provision highly available, secure, and scalable Kubernetes clusters with a single click
- Automatically manage your control plane and data plane with Karpenter
- Reduce the operational burden of Kubernetes lifecycle management
- Ensure your clusters are always running the latest version and security patches
- Unlock the full potential of your Kubernetes deployments and free up your team to focus on building innovative applications. Join us and discover how EKS Auto Mode can help you streamline your path to production-ready Kubernetes at scale.
Building Long Running Crash-proof AI Agents with MCP
Everyone's building AI agents with MCP right now, but almost nobody is testing what happens when things crash halfway through a tool call.
Spoiler Alert: Your agent loses everything and you have no idea where it stopped.
In this workshop, we'll build an AI agent from scratch that talks to tools via MCP. First we'll build it the naive way, break it on purpose, and see how bad it gets.
Then we'll rebuild it by wrapping MCP tools in durable workflows so your agent survives crashes, restarts, and network failures as if nothing happened.
No slides. Just code. You break things, you fix things, you leave with something real.
Tech Stack needed:
- Python 3,12+
- Temporal
- AWS Strands Agents or Langchain
- Docker
- mem0
Rest we can do live, even if you're a complete beginner,
Building Durable AI Agents with AWS Strands, MCP, and Temporal
AI agents are everywhere, but most demos fall apart the moment something goes wrong
— a tool call fails, an API times out, or a long-running workflow loses its state.
In this hands-on workshop, you'll learn how to build AI agents that actually work
in the real world.
We'll start from scratch using AWS Strands Agents SDK to build an AI agent, then
connect it to external tools and data sources using the Model Context Protocol
(MCP). Finally, we'll tackle the hardest part of production AI — reliability — by
integrating Temporal to make our agent workflows durable, resumable, and
fault-tolerant.
What you'll learn:
- How to build AI agents using the Strands Agents SDK
- Connecting agents to external tools with MCP servers
- Why AI agent workflows fail in production and how to fix it
- Using Temporal to add durability, retries, and state management to agent
workflows
Who should attend: Developers curious about AI agents, whether you're just getting
started or looking to move beyond basic chatbot demos. No prior experience with
Strands, MCP, or Temporal required — just bring your laptop and a sense of
curiosity.
Prerequisites: Basic Python knowledge and a laptop with Python 3.10+ installed.
Shubham Londhe
Happy Learning :)
Pune, India
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top