Agent Lab

How to use Claude Code to 10x your development workflow?

Meri Nova

Founder | Community Builder | 140k Linkedin

Hai Nghiem

Founder | Senior Full-Stack AI Engineer | Investor

Learn how senior engineers are upgrading their workflows with the latest AI tools.

Explore the landscape of coding agents

Discover the best way to use Claude Code. Craft Claude.md files to give optimal context and cut errors by half.

Plan, scaffold, and execute projects with Claude Code

Follow step-by-step integration with your GitHub, MCPs, Slack and more. Adopt core functionalities with ease.

Integrate Claude Code to your current workflows

The challenge in this new AI era: so much is changing, there's so much to learn, and there's so little time. Right? And the problem compounds as more time passes. You might be* using ChatGPT every day, but feel uncertain as to why certain OpenAI models or tools respond the way they do.* getting marginal utility out of AI, but struggling to use the tools in a way that doesn't feel burdensome and high effort.* feeling like everyone else is using techniques and tools that are leaving you behind (should you use Claude Code? hint: yes). Look, even power users who constantly talk to AI products every day aren't getting everything out of it that they should. But it's essential to become excellent at your foundational understanding and usage today, here, in 2025, because things are only getting crazier. The core thesis of this course is to move you beyond 'prompt engineering,' as you've heard described elsewhere. It's more fundamental than that. There are 3 pillars: 1. MODEL MECHANICSFoundational understanding of large language models, transformers, and attention mechanisms – whether you're a chef or lawyer or software engineer, you'll be able to get the why behind large language models, chain of thought, reasoning, tool use, vision, and prompt sensitivity. 2. MENTAL MODELSDurable tactics and frameworks for how to talk to AI across interfaces – move from copy-pasting the latest prompt templates to never using a prompt template again, because you'll know how to engage these models to get 10x better results than your peers. Seriously. 3. FUTURE FORWARDHow generative AI is evolving, from the models to the applications to the future of work – get a lens for what people are talking about inside the research labs, how jobs are definitely change &amp; how they might change, the latest applications, and trends to watch out for. What I seek to give you is not just tactics that work today but permanent understanding that will last as new models are released, new tools are built, and the world changes around us. It's a universal fluency that will keep you ahead. Just as language fluency isn't about memorizing phrases from a travel guidebook, AI fluency isn't about collecting prompts from Twitter. Most courses teach you what to say to an AI chatbot. This course teaches you how to think about AI foundationally. It's the difference between learning to order coffee in French versus understanding why French speakers structure their thoughts the way they do. We'll also cover:• How to consistently and easily judge new models as they're released for task-specific competence• Nuances between reasoning, agentic, task-based, and primitive models• Current power rankings based on real-world application (not biased evals) We'll play with advanced uses of:• Foundational SOTA models, like o3-pro, GPT 4.5, Deep Research, Gemini 2.5 Pro, Claude Sonnet 4• Agentic tools like Claude Code, Warp, Replit, Manus, GenSpark, and Devin• Wrapper tools like Gamma, Napkin, and Perplexity• My cheat code apps to 10x your workflow,&nbsp;both in ease and speed I'll share my theory on&nbsp;the future of work.And the&nbsp;OSD Framework&nbsp;I've developed to help people get ahead of the curve.You'll learn about the 3 core muscles I believe every job will distill down to:•&nbsp;Orchestration, the architect of AI-enabled systems•&nbsp;Supervision, the human-in-the-loop steering or polishing outputs•&nbsp;Delivery, the last-mile getting AI value to its end-user We'll go through CRITICAL concepts most people miss, including:* thinking in tokens* model training and fine-tunes* AI assistants v agents* diffusion and task-specific models* image and video model nuances* third party AI v foundational models* why I think you should NEVER use Perplexity At the end of this 10-day intensive, you'll...• be excellent at getting the outputs you want and need from AI models for any use case, from initial prompts to debugging to systems – seriously, a past student said: "I feel like I went from GPT-4 to GPT-7 after this course."• have seen how the latest models and tools work in their most unleashed format, with an understanding of agents as the future – and how to evaluate them, build them, and use them across use cases and interfaces.• future-proof your skills - because you're going to have a&nbsp;deep understanding&nbsp;of how these products work, you'll remain capable of using them as the models are continuously updated and evolved, even as the rapid pace of AI development continues. This course is for ANYONE who doesn't already consider themselves top 0.5% in both AI skill and ecosystem knowledge, and wants to grow their AI skillset with no-frills, no-BS intensity. No technical expertise required. Past students come from both inside and outside the tech industry, and have included:* product managers, startup founders, and early AI builders* software engineers, designers, marketers, operations leaders* analysts, bankers, and teachers* doctors, lawyers, and academics* chefs, frontline managers, students Want a taste of the course? Check out my video on why I think you're being lied to about AI agents: https://youtu.be/MoMxKF5duXI

Everything's changing. Become top 0.5% at using AI to future-proof yourself.

Course syllabus

6 days of live classes

Can't make it to the live classes or want to watch them again later? We'll make each day's content available same-day for all students.

Access recordings forever

There will be several projects and optional group workshops to turn the content into usable muscle - attend live for instructor feedback, or access projects, examples, and templates at your own pace - including permanent access after the course ends.

Daily projects (optional)

Course schedule

Non-technical, semi-technical, or technical professionals (throughout knowledge work) looking to gain an upper hand in this AI moment.

Anyone who has felt the gap between AI's potential, what they hear about what it can do, and their ability to access the upside.

NOT for people who already read arXiv papers and know who roon is. NOT for people looking for quick prompt templates.

Who is this course for

What you’ll get out of this course

You'll learn about the cognitive architecture that underpins not just LLMs, but the way that products and apps are built around them. These patterns will work across AI models and will continue working as systems evolve.

Instead of AI prompt templates, learn conversational design patterns

It's hard for even the most AI-passionate people to integrate and reliably, consistency use AI products. I'll give you systems, shortcuts, and methods for making it second nature -- we'll build your AI muscle.

Instead of treating ChatGPT like a magic answer box, you'll make it a constant companion

You'll know why even non-engineers should use Claude Code, how you should judge new tools, methods for integrating AI into your workflows, and feel in command of the future rather than chasing fake Zapier or n8n workflows that overpromise and underdeliver.

Instead of not knowing where to go next, you'll have an AI tech stack

You'll master the art of progressive refinement, building complex outputs and systems, and be able to leverage all of this to be top .5% in your field -- whether that's at work, with a hobby, with a side project, or with something personal.

Instead of being left behind, you'll get and stay ahead of the AI curve

Build permanent AI muscle: master the foundations of how AI actually works and future-proof tactics on making them work excellently for you.

Sherveen Mashayekhi

Founder & CEO @ Free Agency; Product Leader @ Stella (AI job matching), Toptal

Cohort 6

Cohort 7

The ChallengeYour days are filled with:🗓️ back-to-back meetings,🚀 sky-high customer or investor expectations,⏱️ wishes that your team could move faster sooner,🔥 wishes that you could move even faster and work on what really matters instead of fighting fires. You start each day with the best intentions, but somehow find yourself constantly reacting instead of leading.&nbsp;Sure, it would be nice to focus on your own goals, but you care about those other people (or at least some of them 😁). They’re colleagues and customers, family and friends... How can you collaborate with them responsively without forsaking your goals and becoming just a (re-)Actor in their story? 🎬 ✨ You wonder if AI can help, you wonder how other leaders are using AI to manage it all and manage their teams--but honestly, who's got the time to figure that out? ⏳ You have a constant, lurking anxiety about what’s falling through the cracks or not getting done, so you work faster. As you try to move faster, people fall short of your expectations and their potential. It causes friction and frustration (even if you hide it well). It's uncomfortable to call out, so you avoid giving feedback or mention it lightly, which makes the situation more uncomfortable. Eventually, you decide to give feedback. Sometimes it goes okay. Often, you try to move through and out of the conversation as quickly as possible because it feels so awkward. Growth and improvements rarely last. You take on more work yourself to get it done. The Solution (Evidence-based. Immediately applicable.)⏱️&nbsp;EVERYTHING YOU READ BELOW WILL BE ORIENTED TO IMMEDIATE APPLICATION DURING THE COURSE ⏱️What if you could shift from reacting to the constant inputs to creating what matters most and leading your team in that direction--everyday? This course will support you, step by step, in building your Operating System to make this shift. Fancy apps aren't enough. Nor are bursts of motivation. A sustainable Operating System has 3 features:🧰 Tools (simple enough to keep using, and amplified by AI)🔁&nbsp;Habits (the tools don't use themselves...except for some of the AI ones we'll build)🧠 Mindsets (you can "productively" spend your life responding to other people's messages and requests--or build something that matters) No, "perfection" isn't possible (or even desirable). But our days--and our results--completely shift when we focus our attention systematically instead of ad-hoc and reactively. And our conversations shift when we stop trying to fix people and start inspiring them to take action and grow. We teach you how to do this by using straightforward approaches that reliably transform defensiveness and friction into self-reflection, connection, and motivation to grow. You will start to look forward to feedback conversations because you will know how to use them as powerful tools for building trust and deepening connection. You will also explore your own mindsets and beliefs around feedback, identifying your own patterns around conflict avoidance, people-pleasing, and controlling behaviors. AI is woven throughout the course, including:1️⃣ building your own Custom GPTs2️⃣&nbsp;mastering your calendar3️⃣ using AI as a practice partner for difficult conversations and coaching skills4️⃣ helping your team use AI, and so much more! Once you've shifted the way you manage yourself and lead your team conversations, applying evidence-based approaches tested with 1000s of managers and amplified with AI, the whole game becomes fun again. Bonus:📝 You will also get 5 step-by-step facilitation guides for sharing and teaching your team members everything we cover in this course. This helps establish shared language and frameworks within your team/organization, and positions you as the leader of change. 📖&nbsp;You'll also get our 20-page Offsite Playbook with step-by-step guidance on how to design and facilitate unforgettable team and company gatherings. 🚀 And you'll get to do this while in a practice lab with other high-growth leaders.

Spend your days fighting fires or each other?

Sundays (+ 1 Thursday)

Weekly Office Hours

High-Growth ManagersReady to move out of IC mode, you want to be the inspiring leader people thank for the rest of their careers.

ExecutivesYou know there's a better way than back-to-back meetings everyday. To scale your impact, you know you must scale yourself first

Startup FoundersYou're expanding your focus from building a product to building a team. And to do so, you need the team to step up fast.

You'll have the Inner and Outer Game in place:<ul><li>A systematic set of habits, tools, and mindsets to define What Matters Most each day and week</li><li>You'll be using your emotions as signals for what needs to happen next</li><li>Your mind will be at ease</li></ul>

Clear Focus & Emotional Balance

Whether you're currently intimidated by AI, curious, or all-in, you will:<ul><li>know exactly how to leverage Claude and ChatGPT to improve your skills and help you prepare for key conversations</li><li>have your own CustomGPT to do a recurring management task FOR you</li></ul>

AI As Your Ally (including your own CustomGPT)

<ul><li>Next Actions template (simplest tool possible to stay organized)</li><li>Weekly Preview Checklist (define what matters most and who should do it)</li><li>Daily Defining Checklist</li></ul>

The Operating System (feel on top of your s***)

<ul><li>Know how to decide WHAT to delegate to increase your leverage</li><li>Know HOW to delegate (to a person or AI) in ways that build confidence and follow-through</li></ul>

The Leverage Framework

<ul><li>GAIN Template for how to structure feedback conversations that inspire response-ability, action, and growth</li><li>how to use AI to prepare and practice</li></ul>

GAIN Feedback Framework

<ul><li>GROW Template for coaching conversations</li><li>The key skill to coach effectively</li><li>Know the difference between a feedback and a coaching conversation</li><li>how to use AI to practice and get feedback on a coaching conversation</li></ul>

GROW Coaching Framework

What if you felt on top of everything and your team were aligning and growing through every conversation with you?

Jack Cohen

Cohort 1

Cohort 2

Like many software people, I started out as a developer before moving into product and executive leadership, but I never lost my love for the game. After years of barely coding, AI has given me the ability to build again, and it's also introduced a new concept -- agentic workflows -- which opens the door to truly intelligent software. I've been building AI workflows and writing AI code for almost 2 years now, and I can say two things with extreme confidence: 1) AI tools are going to completely change how we build software, both in terms of code and architecture, and 2) you can't learn how to do it from a book -- you need to get your hands dirty. This one-day, immersive workshop is designed for developers who want to quickly build competence with agentic coding and workflow tools. Former developers, engineering managers, technical PMs or designers, etc. are all welcome -- if you sorta know how to code or spend a lot of time close to code, you'll get a ton out of this course. I will show you how I use AI tools to code and build flows in the real world, we'll work through examples together in your own local environment, and you'll end the day having built real software with AI. No sales pitches, no bullshit -- just real stuff you can use that will get your creative juices flowing. WHAT YOU CAN EXPECT Hands-On ExamplesWe'll start with a few basic concepts around autonomy and then look at a variety of tools -- from Copilot to Claude Code to Cline, and everything in between -- and I'll share real client stories of using agentic AI to build and deploy software and agent workflows with LangGraph and LangSmith. We'll also look briefly at low-code builders like Lovable, Bolt and Tempo. Then we'll learn by doing, applying those tools and techniques to real codebases (we'll cover frontend React, backend Java, and LangGraph Python workflows) in your local dev env. Curated Tools and Techniques I'll demonstrate and help you get set up, answer any and all questions in real time, and share tips and techniques that have worked for me and help you adapt them to your process. You won't write a single line of code yourself, but you'll have several working software examples by the end of the day. I've done this with large teams (see Testimonials below) and it's amazing how much you can get done when AI is in play! Rapid Progress + Community and SupportYou may wonder why this isn't a multi-day (or multi-week) course -- but the goal of this workshop is to kickstart your ability to use AI in a software context. What you do with that ability is up to you -- you can build awesome prototypes, or become a model behavior architect designing and tuning workflows (much like I'm doing today), or be a superfast full stack app builder for hire. You'll be connected with the Not Safe for LinkedIn community (this is a side project of mine -- a place to discuss the changing landscape of life and work away from prying corporate eyes!) where you can reach me and other workshop folks as your journey unfolds. I'm always available for questions and advice -- and for coaching and private workshops if needed! Enhance Your ExpertiseVibe coders aside, most people who are winning with AI are leveraging existing expertise to move faster and make better choices. Lean into what you're already good at, use AI to make it even better, and you'll have a leg up on the competition. This applies to all software roles -- product, dev, design, project mgmt, etc. Immediate, Tangible ROIUsing AI can make you faster and better - which either frees up time to do more of what you love, or increases the value you deliver per unit of time, so you can deliver more value (and hopefully get paid for it!). At worst, you'll look awesome to your boss. --- Agentic coding and workflows are going to completely change how software is built. Don't miss out -- get in the game, get good at this stuff, and build a better future for you and your teams! Please note: Private cohorts are available for teams of 50+! ﻿Please reach out to me at d@jpsj.me if you're interested in a customized version of this workshop for your engineering and/or product delivery team. We can focus on technologies native to your stack and/or agentic tools that are available in your environment (Copilot, Cursor, Claude Code, Codex, etc.)

One-day hands-on AI coding workshop for developers -- from FOMO to FAFO, fast!

Make sure you have 8GB of RAM, admin mode and Homebrew or Chocolatey or similar to help you get going. Replit also works!

A development environment

Options include VSCode with GitHub Copilot, Cursor, Windsurf, Replit, Cline, Claude Code -- free Copilot may work, but be ready to subscribe

Access to an agentic coding tool

Lapsed coders will be fine, non-coders are still more than welcome, but if you don't know what code looks like, it may be tough to keep up

You need to be comfortable looking at/working with code

We'll introduce agentic coding and workflow concepts, and show-and-tell a variety of tools, examples and best practices.

Part 1: Concepts/Demos

Break

We'll do a live workshop, hands on keyboard, where we all use AI tools to modify and run sample code exercises. You'll leave with working software examples that you can continue to modify and enhance on your own.

Part 2: Hands on Keyboard Workshop

Engineers who are already coding with AI, or who could use a push to get started, and want to be thoughtful about best practices and tooling

Product managers or designers who want to level up technically and start building prototypes or workflows without developer help

Managers and executives who want to understand what's possible with state of the art tools, and maybe even get back into the game themselves

We'll work through real examples of frontend and backend code, and use AI tools to modify it. You won't write a single line of code yourself!

You'll use AI codegen tools to build and modify real software

We'll discuss opportunities and pitfalls when using AI to build software, and ensure that you can bring this knowledge back to your teams

You'll use and understand best practices for AI coding in production environments

We'll explore tools like Lovable, Tempo, GitHub Spark and more, and understand how they can be integrated into a larger build process if your prototype(s) get the green light

You'll explore AI rapid prototypers and how to shape their output

We'll use LangGraph (one of many agent frameworks) to create workflows, run them locally and observe chain of thought and tool use. Please note: this requires an API key -- Claude, OpenAI, Gemini, OpenRouter all fine

You'll build and run agentic workflows, from start to finish

One day, no gimmicks, no pitches, just building real code and workflows.  You'll walk away competent and confident in building with AI

Dan Mason

Principal, Head of AI @ Stride

Course Overview ・Duration: 2 weeks, 6 intensive sessions・Format: Cohort-based course・Goal: Transform generic AI assistants into personalized coding partners that understand your codebase, patterns, and needs Core Value Proposition Stop wasting time with generic AI suggestions. Learn to create a personalized AI coding partner that actually understands YOUR specific context and requirements, regardless of which AI tool you use (Cursor, Copilot, Amp, Claude Code, Windsurf, etc.). Instructors ・Eleanor Berger: Engineering and AI leader with experience in DevOps/SRE/Cloud, Applied AI, and Engineering Leadership.・Isaac Flath: Dev efficiency expert with experience at big tech, open source, and advising companies. Companies We've Helped ・SpecStory・Travel and Leisure・Cable &amp; Wireless Communications・GitHub・Microsoft・Google・Canonical・Answer AI・and more ... Companies Our Students Are From ・Amazon (AWS)・Microsoft・X・DocuSign・Monster・TrustLayer・and more … Curriculum 📚 Mise en Place: Preparing tools, environments, and context for working with AI・Rules and config setup・Documentation strategies・Tools &amp; environments configuration・LLM as assistant paradigm 📚 Good Vibrations: Interactive AI coding・AI coding IDEs and tools comparison・Interactive agents and workflows・Real-time collaboration patterns 📚 While You Were Gone: Delegating work to background agents and workflows・Background agents configuration・CI/CD workflows with AI・Autonomous task delegation Weekly Session Breakdown 🗓️ Week 1: Foundation &amp; Personalization 📋 The Context Progression JourneyMove from Generic → Curated → Personalized contextReal before/after examples showing 10x effectiveness improvementsMise en Place principles for AI setup 📋 AI Assisted Development ToolkitComprehensive tool comparison and selection guideHands-on evaluation of latest tools worth tryingInteractive AI coding patterns 📋 Personalizing Your Static ContextPractical examples and transformationsContext curation best practicesEfficient management techniquesRules and configuration management 🗓️ Week 2: Automation &amp; Advanced Techniques 📋 Automating Updates from Chat InteractionsTools for automatic context evolutionMining conversation history for improvementsPattern analysis to fix recurring AI failures 📋 Model Context Protocol (MCP) and Agent-Based ContextBuilding practical MCP serversReal-world examples used in daily developmentAutomated repetitive information gatheringBackground agent architectures 📋 Dynamic Context and ToolsTool calling and dynamic information accessBuilding useful integrations for daily workflowProduction-ready tools useful for immediate projectsCI/CD integration strategies Key Learning Outcomes 🛠️ Technical Skills・Universal AI Setup System: Build context systems that work across ALL major AI tools (no vendor lock-in)・Automated Context Evolution: Automate context updates based on actual coding patterns・Pattern Mining &amp; Analysis: Turn every AI mistake into a learning opportunity・MCP Server Development: Create practical automation tools for daily use 🏗️ Practical Applications・ Create and maintain context-independent rules across all major AI coding tools・ Efficiently manage and sync context for different formats (Amp, Copilot, Cursor, Copilot, Windsurf, Claude Code, etc...)・ Analyze conversation history to identify and fix AI pattern failures・Build real integrations that drastically enhance workflow 🔁 Workflows・Plan and task-based agentic processes・Targeted human augmentation approaches・Matching tasks to optimal AI assistance methods・Enterprise deployment strategies and processes 🏢 Enterprise Integration・ Implementing AI coding tools in enterprise settings・Security and compliance considerations・Team adoption strategies・Scaling personalized context across organizations・Integration with existing development workflows Target Audience Developers who:・Use AI coding assistants but feel limited by generic suggestions・Want to maximize productivity with personalized AI tools・Need a vendor-agnostic approach to AI coding assistance・Seek practical, production-ready solutions over theoretical concepts・Know AI should be better, but doesn't see how to get there Course Philosophy ・Focus on real-world applications・Vendor-agnostic approach ensures long-term value・Continuous improvement through automated pattern analysis・Practical tools you'll use daily in production environments

Transform generic AI assistants into personalized coding partners

While this is not a coding course, this content is to help people code

Coding Experience

If your events are recurring and at the same time, it might be easiest to use a single line item to communicate your course schedule to students

Tuesdays & Thursdays

Feel free to type out dates as your title as a way to communicate information about specific live sessions or other events.

May 7, 2022

Schedule items can also be used to convey commitments outside of specific time slots (like weekly projects or daily office hours).

Weekly projects

Developers who want to build technically solid solutions with confidence

Coders who want to move from copy-and-paste to consistent and reliable AI-assisted development skills

Engineers and leaders who need to adopt and grow dependable and repeatable AI-assisted software development processes

<ul><li>Universal AI Setup System: Build context systems that work across ALL major AI tools (no vendor lock-in)</li><li>Automated Context Evolution: Automate context updates based on actual coding patterns</li><li>Pattern Mining &amp; Analysis: Turn every AI mistake into a learning opportunity</li><li>MCP Server D</li></ul>

Technical Skills

<ul><li>Create and maintain context-independent rules across all major AI coding tools</li><li>Efficiently manage and sync context for different formats (Amp, Cursor, Copilot, Windsurf, Claude Code)</li><li>Analyze conversation history to identify and fix AI pattern failures</li><li>Build real integrations that</li></ul>

Practical Applications

<ul><li>Plan and task-based agentic processes</li><li>Targeted human augmentation approaches</li><li>Matching tasks to optimal AI assistance methods</li><li>Enterprise deployment strategies and processes</li></ul>

Workflows

<ul><li>Implementing AI coding tools in enterprise settings</li><li>Security and compliance considerations</li><li>Team adoption strategies</li><li>Scaling personalized context across organizations</li><li>Integration with existing development workflows</li></ul>

Enterprise Integration

Make it code like you do. Turn generic AI assistants into coding partners that actually get your style and have the right context.

Lightning Lessons

How to use Claude Code to 10x your development workflow?