Tracy Developer Meetup Tracy Developer Meetup
Home Speak for Us Sponsor About

AI Agents: Tool and Function Calling Under the Hood

October 02, 2026 at 06:00 PM [UPCOMING]

Most people can build a chatbot, but few can build an autonomous agent. What is the secret sauce that allows a probabilistic model to execute deterministic functions?

Join us for a technical deep dive into the mechanics of Tool and Function Calling. We will peel back the curtain on how LLMs transition from mere text predictors to active agents. We'll explore the engineering behind decision-making: How does a model recognize a tool's necessity? How do we enforce structured JSON outputs without hallucination? And how do we manage the 'reasoning loop' where the model interprets a tool's output to decide its next move?

We will go beyond the high-level APIs to discuss the underlying prompt engineering, parsing logic, and state management required to build reliable systems. We’ll wrap up with a live, hands-on demo where we build a functioning agent that interacts with real-world tools to solve a complex, multi-step scenario.

Faster Attackers, Smarter Defenders: Security in the Age of AI

September 18, 2026 at 06:00 PM

Cybersecurity isn't meant to be for the specialists. Everyone who programs or interacts with computers should be aware of the flaws and possible outcomes of computer security.

In this talk, we’ll discuss how AI has changed the cybersecurity landscape. We’ll begin by exploring how traditional security has been broken down by AI. We’ll cover changes in bug bounties, CVE discovery, bug validation, and software distribution.

Big problems need big solutions. We’ll discuss how Kubernetes is becoming the platform for inference workloads and how new technologies secure it. We’ll then discuss technologies like attestation, Image Validation, and live patching as ways of mitigating vulnerabilities in Kubernetes environments.

Let's Build JeolAI: Building Production AI Agents with Vertex AI and FastAPI

August 14, 2026 at 06:00 PM

Building production systems are different from that building a chatbot that works. They need observability, governance, cost controls, tool orchestration, and human approval workflows before they can be trusted in real applications.

In this hands-on workshop, you'll build "JeolAI", a production-inspired AI shopping agent using "Vertex AI", "FastAPI", "React", and "Gemini models".

Together we'll build an agent that can:

  • Route requests to different models based on budget policies
  • Call multiple backend tools for search, inventory, promotions, cart management, and checkout
  • Track tokens, latency, tool calls, and estimated cost for every request
  • Visualize agent execution in real time
  • Apply budget guardrails that automatically change model behavior as spending increases
  • Enforce domain guardrails to reject out-of-scope requests
  • Require human approval before completing high-cost operations
  • Generate a complete session summary with execution metrics and conversation history

Along the way you'll learn how to structure a production AI application using FastAPI, connect it to Vertex AI, implement deterministic tool calling, and build the operational controls that engineering teams expect in real deployments.

By the end of the workshop, you'll have a complete end-to-end AI agent running locally, understand how modern agent architectures work, and leave with a project you can continue extending after the session.

Prerequisites

  • Basic Python knowledge
  • Familiarity with REST APIs is helpful
  • Please create a FREE Gmail account (gives $300 credits)
  • VS Code installed
  • A laptop capable of running Python 3.11+

Bring your laptop. This is a build-along workshop, and you'll leave with a working production-style AI agent running on your own machine.

Local AI: Run Smarter Not Bigger

July 03, 2026 at 06:00 PM

Cloud AI costs tokens, adds latency, and ships your data off-machine. In this session, Mehfuz will demo how to orchestrate small local LLMs to handle real workflows — interactive chat, external data via MCP servers, and multi-step skills — all on your own hardware, at zero cost.

From Idea to iOS App in Minutes: Building with Codex and Xcode

June 12, 2026 at 06:00 PM

What if you could go from a rough idea to a working iOS app—UI, logic, and structure—in minutes instead of days?

In this session, you’ll see a live demo of using Codex to build a real iOS app using Xcode from scratch. Instead of treating AI as a gimmick, we’ll use it as a practical development partner—generating views, structuring code, and iterating quickly while staying inside Codex and using Xcode.

What This Session Covers:

  • How to prompt Codex to generate usable SwiftUI code using Xcode
  • Turning rough ideas into structured app features
  • Iterating on UI and logic without starting over
  • Where AI helps—and where it absolutely doesn’t
  • How to keep your codebase clean and maintainable

By the end of this session, you’ll walk away with:

  • A clear workflow for using Codex to build iOS apps
  • Practical prompt patterns that actually produce usable code
  • An understanding of how to integrate AI into your existing dev process
  • A working sample app (or the foundation of one)
  • A realistic sense of what AI can and can’t do for you as a developer

Show up to the session ready to learn and follow along. Maybe you'll even be inspired to release your first iOS mobile application!

Turn Enterprise Data into Contextual Answers with RAG and Microsoft Foundry

April 24, 2026 at 06:00 PM

This presentation explores how to build intelligent, agent‑driven applications using Retrieval‑Augmented Generation (RAG) with Microsoft Foundry. It covers the ingestion, embedding, and searching of enterprise and external data through vector stores, and showcases a practical scenario where invoices and work‑performed documents are linked to deliver accurate, contextual responses via AI agents and workflows—all with low‑code implementation.

Vibe Coding Night, from Hobbyist to Enterprise

March 06, 2026 at 06:00 PM

Whether you're a seasoned enterprise developer or you're getting started with your development career, bringing AI into your development workflow can seem like a daunting task.

At the 2026 kickoff event for the Tracy Developer Meetup, we're going to explore AI assisted development, vibe coding in particular, and how you can accelerate your development at any stage of your career.

Bring your laptops, your questions, and your eagerness to learn.

Low-level JavaScript​: Multithreading

November 21, 2025 at 06:00 PM

Together we’ll redefine what it means to call JavaScript a “single-threaded" language. You’ll walk away with a firm grasp of what threads are, how they're used to manage concurrency and what it means to perform concurrent actions in a "single-threaded" language.

Key Takeaways

  • Understand what threads are and what multithreading is
  • Understand JavaScript's relationship to threads
  • How to take advantage of additional threads in JavaScript

10x Your LinkedIn Presence & Unlock Every Opportunity

October 24, 2025 at 06:00 PM

Join this session to learn how to leverage LinkedIn to your benefit.

This session will show you how to transform your LinkedIn presence into a magnet for career and business opportunities.

What you’ll learn:

  • Proven strategies to grow your visibility and attract the right audience.
  • How to turn your personal story into a compelling professional brand.
  • Practical tips for creating content that drives meaningful engagement.
  • An actionable framework to leverage LinkedIn for networking and opportunity.

Vibe Coding and the Future of AI-Assisted Software Development

September 26, 2025 at 06:00 PM

This talk explores how AI is changing the way we build software. We'll start with vibe coding, a new method where you describe what you want an AI to build in simple, everyday language, and it gives you the code. It’s a very conversational process, like giving a goal to an assistant and then guiding it with feedback. Then, we'll look at the next step: agentic AI. This is where the AI starts to become more autonomous, taking a high-level goal and breaking it down into a plan, writing the code, and even testing it all on its own. While vibe coding is a great way to get started and get things done fast, agentic AI represents a future where the AI can take on entire projects with minimal human oversight. Both approaches are transforming how we code, making the process more about clear communication and less about manual work.

  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
  • Next
Next
Upcoming Events
  • AI Agents: Tool and Function Calling Under the Hood
Subscribe

Join the mailing list to get reminders about events and on-demand recordings.

Past Events [All]
  • Faster Attackers, Smarter Defenders: Security in the Age of AI
  • Let's Build JeolAI: Building Production AI Agents with Vertex AI and FastAPI
  • Local AI: Run Smarter Not Bigger
  • From Idea to iOS App in Minutes: Building with Codex and Xcode
  • Turn Enterprise Data into Contextual Answers with RAG and Microsoft Foundry
Sponsors
  • The Polyglot Developer
Upcoming Partner Events

Events happening in neighboring cities such as Modesto, Merced, Stockton, and Sacramento!

    LinkedIn
    Luma
    1981 Chester Dr, Tracy, CA 95376
    Copyright © Tracy Developer Meetup 2026