Brent Laster

GitHub Copilot is a popular AI assistant that helps software developers more easily create content, get answers to coding-related questions, and handle many of the boilerplate tasks of software development. But it can also do much more in the areas where it can be used. Join Copilot expert (and author of the upcoming “Learning GitHub Copilot” book from O'Reilly) for a quick overview of some of the additional tips and tricks to allow you to make the most from this AI assistant.

Most users know GitHub Copilot can help with the basics of code generation, creating test cases, documentation, etc. But because the tool is AI based, there's a lot more that it can help you with in these areas simply by asking it and giving it the right prompts. In this session, we'll take a look at some ways to leverage beyond the basics of these tasks to creating results that are usable more deeply and widely. We'll also look at some ways to compensate when Copilot does not have the most recent information, or needs to be picking up more relevant context.

In this ½ day course, author and trainer and DevOps Director Brent Laster will take you beyond the basics of Kubernetes to understand the advanced topics you need to know to ensure your success with K8S.

In plain and simple explanations and hands-on labs, you’ll learn about key concepts such as RBAC, admission controllers, affinity, taints and tolerations mean and how to use them. You’ll learn tips to debug your Kubernetes deployments and how to leverage probes to ensure your pods are ready and healthy – and what happens when they aren’t.

Along the way, we’ll give you hands-on experience and time to play with these concepts in a simple minikube environment running on your own virtual machine that you can keep as a reference environment after the course.

Learning and understanding AI concepts is satisfying and rewarding, but the fun part is learning how to work with AI yourself. In this presentation, author, trainer, and experienced technologist Brent Laster will help you do both! We’ll explain why and how to run AI models locally, the basic ideas of agents and RAG, and show how to assemble a simple AI agent in Python that leverages RAG and uses a local model through Ollama.

Join us to learn about all 3 topics in 90 minutes!

No experience is needed on these technologies, although we do assume you do have a basic understanding of LLMs.

This will be a fast-paced, engaging mixture of presentations interspersed with code explanations and demos building up to the finished product – something you’ll be able to replicate yourself after the session!

Learning and understanding AI concepts is satisfying and rewarding, but the fun part is learning how to work with AI yourself. In this 1/2 day workshop, author, trainer, and experienced technologist Brent Laster will help you do both! We’ll explain why and how to run AI models locally, the basic ideas of agents and RAG, and show how to assemble a simple AI agent in Python that leverages RAG and uses a local model through Ollama. And you'll get to follow through with hands-on labs and produce your own instance running on your system in a GitHub Codespace

In this workshop, we'll walk you through what it means to run models locally, how to interact with them, and how to use them as the brain for an agent. Then, we'll enable them to access and use data from a PDF via retrieval-augmented generation (RAG) to make the results more relevant and meaningful. And you'll do all of this hands-on in a ready-made environment with no extra installs required.

No experience is needed on these technologies, although we do assume you do have a basic understanding of LLMs.

This hands-on workshop teaches developers how to build modern AI-driven applications using local LLMs, intelligent agents, and standardized tool protocols. Participants learn to move beyond simple prompting to architect production-ready AI systems that integrate reasoning, retrieval, and external data sources. The course emphasizes real-world implementation through step-by-step labs in GitHub Codespaces, requiring no local installs.

By the end of the workshop, attendees will have created functional AI agents that use Ollama for local model execution, FastMCP for standardized tool communication, and RAG (Retrieval-Augmented Generation) for context-grounded responses—all deployable to Hugging Face Spaces.

The course begins with an explanation of running models locally with tools like Ollama and LangChain. Participants progressively advance through seven structured labs covering the following topics :

1.Running Models Locally: Using Ollama to pull, serve, and query models such as llama3.2 via CLI, API, and Python integration.
2.Creating Agents: Building a reasoning agent that uses the Thought → Action → Observation loop to call weather APIs.
3.Exploring MCP (Model Context Protocol): Implementing standardized tool discovery and invocation through a FastMCP server-client setup.
4.Vector Databases: Indexing and searching local data with ChromaDB to enable semantic search and similarity matching.
5.RAG with Agents: Combining retrieval and reasoning so agents can access relevant context from external data sources.

    6.    Streamlit Web Application – Wrap the RAG agent in a modern web UI using Streamlit, complete with a memory dashboard, real-time status, and visual feedback.

1. Deploying to Hugging Face Spaces – Publish the Streamlit app to a live, shareable web environment, learning how to authenticate, push, and auto-deploy projects for public access.

Each lab reinforces the previous one, culminating in a fully functional, classification-driven RAG agent that demonstrates multi-domain reasoning, semantic search, and modular design.

This full-day, hands-on workshop equips developers, architects, and technical leaders with the knowledge and skills to secure AI systems end-to-end — from model interaction to production deployment. Participants learn how to recognize and mitigate AI-specific threats such as prompt injection, data leakage, model exfiltration, and unsafe tool execution.

Through a series of focused labs, attendees build, test, and harden AI agents and Model Context Protocol (MCP) services using modern defensive strategies, including guardrails, policy enforcement, authentication, auditing, and adversarial testing.

The training emphasizes real-world implementation over theory, using preconfigured environments in GitHub Codespaces for instant, reproducible results. By the end of the day, participants will have created a working secure AI pipeline that demonstrates best practices for trustworthy AI operations and resilient agent architectures.

The course blends short conceptual discussions with deep, hands-on practice across eight structured labs, each focusing on a key area of AI security. Labs can be completed in sequence within GitHub Codespaces, requiring no local setup.
1.Lab 1 – Mapping AI Security Risks
Identify the unique attack surfaces of AI systems, including LLMs, RAG pipelines, and agents. Learn how to perform a structured threat model and pinpoint where vulnerabilities typically occur.
2.Lab 2 – Securing Prompts and Contexts
Implement defensive prompting, context isolation, and sanitization to mitigate prompt injection, hidden instructions, and data leakage risks.
3.Lab 3 – Implementing Guardrails
Use open-source frameworks (e.g., Guardrails.ai, LlamaGuard) to validate LLM outputs, enforce content policies, and intercept unsafe completions before delivery.
4.Lab 4 – Hardening MCP Servers and Tools
Configure FastMCP servers with authentication, scoped tokens, and restricted tool manifests. Examine how to isolate and monitor server–client interactions to prevent privilege escalation.
5.Lab 5 – Auditing and Observability for Agents
Integrate structured logging, trace identifiers, and telemetry into AI pipelines. Learn how to monitor for suspicious tool calls and enforce explainability through audit trails.
6.Lab 6 – Adversarial Testing and Red-Teaming
Simulate common AI attacks—prompt injection, model hijacking, and context poisoning—and apply mitigation patterns using controlled experiments.
7.Lab 7 – Policy-Driven Governance
Introduce a “security-as-code” approach using policy files that define allowed tools, query types, and data scopes. Enforce runtime governance directly within your agent’s workflow.
8.Lab 8 – Secure Deployment and Lifecycle Management
Apply DevSecOps practices to containerize, sign, and deploy AI systems safely. Incorporate secrets management, vulnerability scanning, and compliance checks before release.

Outcome:
Participants finish the day with a secure, auditable, and policy-controlled AI system built from the ground up. They leave with practical experience defending agents, MCP servers, and model workflows—plus learning for integrating security-by-design principles into future projects.

This 1/2 day workshop introduces participants to Claude Code, Anthropic’s AI-powered coding assistant. In three hours, attendees will learn how to integrate Claude Code into their development workflow, leverage its capabilities for productivity, and avoid common pitfalls. The workshop also introduces the concept of subagents (specialized roles like Planner, Tester, Coder, Refactorer, DocWriter) to show how structured interactions can improve accuracy and collaboration.

Format: 3-hour interactive workshop (2 × 90-minute sessions + 30-minute break).

Audience: Developers and technical professionals with basic programming knowledge.

Focus Areas:

Core capabilities and limitations of Claude Code.

Effective prompting and iteration techniques.

Applying Claude Code for code generation, debugging, refactoring, and documentation.

Using subagents for structured workflows as an optional advanced technique.

Deliverables:

5 hands-on labs (10–12 minutes each).

Experience with everyday Claude Code workflows plus a brief introduction to subagents.

In this presentation, we'll cover the options, tips, and tricks for using GitHub Copilot to help us identify how to test code, generate tests for existing code, and generate tests before the code.

Join global trainer, speaker, and author of the upcoming book, Learning GitHub Copilot, Brent Laster as he presents material on multiple ways to leverage Copilot for testing your code on any platform and framework.

Have you wondered what options GitHub Copilot can provide for helping to not only write your code, but test your code? In this session, we'll examine some key ways that Copilot can support you in ensuring you have the basic testing needs covered. In particular, we'll cover:

• A quick overview of GitHub Copilot
• Letting Copilot tell you how to get started testing for a new language
• Creating tests for existing code through one-step commands
• Creating tests for existing code with comments
• Creating tests for existing code with explicit prompts
• Validating inputs to functions using Copilot
• Using Copilot to build out tests for edge cases
• Leveraging testing frameworks
• Building tests before the code - TDD with Copilot

In this workshop, we'll cover the options, tips, and tricks for using GitHub Copilot to help us identify how to test code, generate tests for existing code, and generate tests before the code.

Join global trainer, speaker, and author of the upcoming book, Learning GitHub Copilot, Brent Laster as he presents material on multiple ways to leverage Copilot for testing your code on any platform and framework.

Have you wondered what options GitHub Copilot can provide for helping to not only write your code, but test your code? In this session, we'll examine some key ways that Copilot can support you in ensuring you have the basic testing needs covered. In particular, we'll cover:

• A quick overview of GitHub Copilot
• Letting Copilot tell you how to get started testing for a new language
• Creating tests for existing code through one-step commands
• Creating tests for existing code with comments
• Creating tests for existing code with explicit prompts
• Validating inputs to functions using Copilot
• Using Copilot to build out tests for edge cases
• Leveraging testing frameworks
• Building tests before the code - TDD with Copilot

Get handson learning to understand and utilize Generative AI from the ground. Work with key AI techniques and implement simple neural nets, vector databases, large language models, retrieval augmented generation and more all in one single day session!

Generative AI is everywhere these days. But there are so many parts of it and so much to understand that it can be overwhelming and confusing for anyone not already immersed in it. In this fullday workshop, opensource author, trainer, and technologist Brent Laster will explain the concepts and working of Generative AI from the ground up. You’ll learn about core concepts like neural networks all the way through to working with Large Language Models (LLM), Retrieval Augmented Generation (RAG) and AI Agents. Along the way we’ll explain integrated concepts like embeddings, vector databases and the current ecosystem around LLMs including sites like HuggingFace and frameworks like LangChain. And, for the key concepts, you’ll be doing handson labs using Python and a preconfigured environment to internalize the learning.

Just as CI/CD and other revolutions in DevOps have changed the landscape of the software development lifecycle (SDLC), so Generative AI is now changing it again. Gen AI has the potential to simplify, clarify, and lessen the cycles required across multiple phases of the SDLC.

In this session with author, trainer, and experienced DevOps director Brent Laster, we'll survey the ways that today's AI assistants and tools can be incorporated across your SDLC phases including planning, development, testing, documentation, maintaining, etc. There are multiple ways the existing tools can help us beyond just the standard day-to-day coding and, like other changes that have happened over the years, teams need to be aware of, and thinking about how to incorporate AI into their processes to stay relevant and up-to-date.

Just as CI/CD and other revolutions in DevOps have changed the landscape of the software development lifecycle (SDLC), so Generative AI is now changing it again. Gen AI has the potential to simplify, clarify, and lessen the cycles required across multiple phases of the SDLC.

In this session with author, trainer, and experienced DevOps director Brent Laster, we'll survey the ways that today's AI assistants and tools can be incorporated across your SDLC phases including planning, development, testing, documentation, maintaining, etc. There are multiple ways the existing tools can help us beyond just the standard day-to-day coding and, like other changes that have happened over the years, teams need to be aware of, and thinking about how to incorporate AI into their processes to stay relevant and up-to-date.

MCP, or Model Context Protocol, is a standardized framework that allows AI agents to seamlessly connect with external data sources, APIs, and tools. Its main purpose is to make AI agents more intelligent and context-aware by giving them real-time access to live information and actionable capabilities beyond their built-in knowledge.

Join AI technologist, author, and trainer Brent Laster as we learn what MCP is, how it works, and how it can be used to create AI agents that can work with any process that implements MCP. You'll work with MCP concepts, coding, servers, etc. through hands-on labs that teach you how to use it with AI agents.

With MCP, developers can easily integrate AI agents with a wide variety of systems, from internal business databases to third-party services, without having to build custom integrations for each use case. MCP servers act as gateways, exposing specific actions and knowledge to the AI agent, which can then dynamically discover and use these capabilities as needed. This approach streamlines the process of adding new functionalities to AI agents and reduces ongoing maintenance.

MCP is particularly useful for scenarios where AI agents need up-to-date information or need to perform actions in external systems-such as customer support bots fetching live ticket data, enterprise assistants accessing knowledge bases, or automation agents processing transactions. By leveraging MCP, organizations can create more adaptable, powerful, and enterprise-ready AI solutions that respond to real-world business needs in real time

In this presentation, we'll cover some of the latest developments and feature additions in GitHub Copilot as rolled out in recent months and at GitHub Universe. Join author, trainer, technologist, and author of the upcoming book “Learning GitHub Copilot” from O'Reilly, Brent Laster to learn what's new and exciting with this popular generative AI tool!

GitHub Copilot continues to evolve as a popular AI coding assistant, adding features and functionality regularly. But there are more significant changes that have been rolled out recently, including wider Copilot integration in the individual GitHub plan for things like indexing repos, pull request and issue summaries. Also, there's new functionality for reviewing code, agent edits, vision features, giving Copilot custom instructions that will apply to every chat, and more!