Build //localhost:Mangaluru
🚀 Event Schedule & Tracks
Welcome to localhost/mang! We have an action-packed day split into two parallel tracks designed for builders, developers, and architects. Catch deep-dive technical talks in Track 1, or bring your laptop for hands-on sessions and rapid-fire lightning talks in Track 2.
🎙️ Track 1: Deep-Dive Talks
🕐 09:15 AM – 09:45 AM
Idea to Production-Ready Agent in Seconds on AI-Native Runtime
Agentic apps behave differently from traditional services-they make decisions, coordinate steps, and react to changing inputs. This session shows how to run agentic workloads on a fast, AI-native runtime on Azure Container Apps.
What we'll cover: Patterns for deployment, configuration, safe scaling for bursty traffic, and observability to move from idea to production-ready agents reliably and without surprises.
Cursor: Standardizing Codebases with Rules & Skills
Discover how Cursor Rules and Skills allow teams to embed coding standards, architectural patterns, and workflows directly into the AI assistant's context.
What we'll cover: A high-level overview of how these structural guardrails seamlessly fit into your development lifecycle to maintain repository consistency as AI-assisted development scales.
🕐 10:00 AM – 10:30 AM
Agent Mesh as the Next IDP Layer
In 2026, a growing percentage of code generation, infrastructure interaction, and operational workflows are being driven by AI agents rather than humans-but traditional Internal Developer Platforms (IDPs) weren't built for autonomous systems. This session explores building an Agent-Ready Platform using an Agent Mesh and an MCP (Model Context Protocol) Gateway.
Key Takeaways:
Designing an Agent-as-a-Service model using Agent Mesh architectures inside Kubernetes.
Standardizing agent-to-tool communication securely through MCP Gateway patterns.
Applying governance, RBAC, OPA (Open Policy Agent), and centralized auditing to autonomous actions.
Operational lessons and engineering trade-offs between execution speed, safety, and traceability.
🕐 10:30 AM – 10:45 AM (Lightning Interlude)
Beyond Linear AI: Dynamic Parallel Workflows with LangGraph
Mastering essential LangGraph primitives, specifically
SendandCommand, to unlock the potential of AI agents beyond static, linear pipelines.
Automated Test Case Generation Using Generative AI
A close look at a test case generation framework designed to help QAs and Devs build robust test cases using both "Engineer" and "End User" modes via Ticket and Documentation inputs.
🎙️ Track 1: Additional Sessions
Developer Tools & Frameworks: From CLI to PR: Automating the Path to Merged Code
Moving beyond conversational chat, this session shows how GitHub Copilot functions as a true agentic partner in your daily sprints by live-coding a full cycle-from planning in the terminal to delegating work to the cloud and automating PR reviews.
What You'll Learn: Strict technical mechanics without high-level abstractions-context management, advanced features with Copilot CLI, and the specific architecture patterns that make agentic development workflows stick in production.
From Commit to Production: Building an AI-Augmented CI/CD Pipeline
Modern engineering teams can use AI to extend far beyond code generation. In this demo-driven session, see how to build an AI-augmented CI/CD pipeline using GitHub Actions and modern AI tooling to assist developers throughout the entire journey-including pull request reviews, test generation, deployment validation, and log analysis.
API Sentinel: Building the Future of API Monitoring with AI
Even small API failures can impact users, payments, and business workflows. This talk introduces API monitoring in simple, practical terms: what it is, why it matters, and how teams can use it to quickly detect failures, performance issues, and unexpected behavior in production systems.
I Am a Frontend Developer, I Don’t Need DSA
There is a common misconception that frontend developers don't need to understand the fundamentals of Data Structures and Algorithms. This talk breaks down the internals of React at a high level-how it renders content, tracks state changes, and prioritizes updates-to show how foundational data structures power a library used by millions daily.
🛠️ Track 2: Workshops & Lightning Talks
🕐 09:30 AM – 10:00 AM
Any Cloud, Locally: Hands-on with Floci Cloud Emulators
Floci lets developers run cloud services locally without cloud accounts, auth tokens, or feature gates. In this hands-on session, we’ll explore how Floci replaces remote cloud dependencies with fast local emulators to speed up development, testing, and CI.
What we'll do: Demo running Floci locally, create and test cloud resources from the CLI, and see where Floci fits compared to mocks, real cloud environments, and tools like LocalStack.
Get Started with Models in Microsoft Foundry to Build AI Apps
In this hands-on lab, you will build a production-ready AI application using Microsoft Foundry with zero fine-tuning required.
What we'll do: Discover and select models, provision a Foundry project, connect to a hosted model using the OpenAI SDK, implement a comment moderation workflow, and package the solution as a hosted agent using Python.
🕐 11:00 AM – 11:30 AM
Crafting Reliable Software in the Era of Coding Agents
LLMs are stochastic and perform best when strong feedback loops exist to verify their output. Because coding agents rely heavily on these models, classical engineering practices like Domain-Driven Design, strong type systems, and comprehensive testing (Unit, Integration, E2E) are no longer optional.
What we'll cover: How these practices and human code reviews contribute to building reliable, scalable, and maintainable codebases when partnering with AI coding agents.
From Zero to Deployed on Azure with AI Agents
Bring your laptop for this hands-on deep dive! What happens when you let AI agents do the building? Go from an empty terminal to a fully deployed app on Azure using GitHub Copilot CLI and coding agents to handle scaffolding, coding, debugging, and deployment via natural language.
The Takeaway: This isn't a passive demo. You will walk out with a real, working development workflow you can take straight to your next production project.
Official Hashtags
#MSBuild
#localhostmang
#hmjun26
#GlobalAICommunity
Tag Our Official Social Accounts
X (Twitter): @GlobAICommunity
LinkedIn: Global AI Community
Join the AI Conversation on Global AI Discord Server