All Things Claude: From Coding to Cowork to Security

What You Will Learn

NOTE: This is a hands-on workshop - bring a personal laptop (corporate ones may not allow the labs to work).

84% of developers now use or plan to use AI tools — but only about 3% highly trust what those tools produce (Stack Overflow 2025). Meanwhile, Claude has quietly stopped being a chat window. Over the past year it has grown into a platform: Claude Code for agentic development (now behind roughly 4% of public GitHub commits), Cowork for delegating everyday knowledge work, Claude Design for visual work, built-in security review and deep scanning, and integrations that put Claude inside Excel, PowerPoint, Chrome, and Slack. The gap between using AI and working with AI — knowing which surface to reach for, how to hand work over, and how much to trust it with — is the skill this workshop builds.

This half-day workshop is a guided tour of the whole platform with your hands on the controls the entire way. We make five main stops — Claude Code, Cowork, Claude Design, security, and integrations — and at each one you'll do a short hands-on lab (seven labs in all, 8–12 minutes each) from a companion GitHub repo with realistic sample projects, made-up data, and a reset script so you can make a mess and try again. You'll fix a bug start to finish in Claude Code and make it prove the fix with a test, package a routine into a reusable skill, delegate a messy-folder job to Cowork and approve its plan, turn a brand folder into an editable flyer in Claude Design, watch a deny rule hold and run a deep security scan on a deliberately vulnerable app, and carry one conversation across Excel and PowerPoint.

Prerequisite: Basic familiarity with AI assistants (you've used Claude, ChatGPT, or similar) and comfort running commands in a terminal. No prior Claude or Claude Code experience is required.

Covers: the Claude model family and the agent loop; Claude Code (permission modes and the trust dial, CLAUDE.md and context, skills, subagents and delegation, /goal and /loop, the AI-native SDLC); Cowork and the “One Claude” merger (task lifecycle, projects and memory, scheduled tasks, connectors); Claude Design (inputs, refinement modes, design systems, /design-sync with code); security (the permission gates, the guardrail stack, Claude Code Security, the claude-security plugin); integrations (Claude in Excel and PowerPoint, Chrome, Claude in Slack, MCP); plus a tips-and-tricks grab bag of terminal power moves, context and cost controls, and automation sleepers. Approximately 55% presentation, 45% hands-on labs.

Outcome: Participants leave with a working mental map of the Claude platform, seven labs they can rerun and extend on their own (the repo is theirs to keep), and a Monday-morning playbook: one concrete action for each stop on the tour.

About Brent Laster

Hi, I'm Brent Laster - a global trainer and book author, experienced corporate technology developer and leader, and founder and president of Tech Skills Transformations LLC. I've been working with and presenting at NFJS events for many years now and it is always exciting and interesting.

Through my decades in programming and management,I've always tried to make time to learn and develop both technical and leadership skills and share them with others Regardless of the topic or technology, my belief is that there is no substitute for the excitement and sense of potential that come from providing others with the knowledge they need to help them accomplish their goals.

In my spare time, I hang out with my wife Anne-Marie, 4 children and 2 small dogs in Cary, North Carolina where I design and conduct trainings and write books. You can find me on LinkedIn (linkedin.com/in/brentlaster), Twitter (@brentclaster) or through my company's website at www.getskillsnow.com.

More About Brent »