End-to-End with Shape Up: A Real-World Case Study

Ryan Singer is one of the earliest employees and the former Head of Strategy at 37signals (the makers of Basecamp), where he spent nearly two decades refining a product development approach that helped the company build super-successful products with small teams. Based on these lessons, he wrote "Shape Up: Stop Running in Circles and Ship Work that Matters," and Ryan now works with companies of all sizes to help them escape the cycle of endless sprints, missed deadlines, and dragging projects. What you’ll learn: 1. Why traditional Agile and Scrum methods often lead teams into endless cycles of work without meaningful shipping milestones. 2. The “appetite-driven” approach to product development where teams set fixed timeboxes (usually six weeks maximum) and vary the scope instead of expanding timelines. 3. The exact process for running effective “shaping” sessions that collaboratively define projects before committing resources. 4. Why most teams struggle with too little detail in their planning, not too much. 5. Why a 30-to-50-person team size is the critical breaking point when growing startups need to adopt more structured processes. 6. Practical techniques for bridging the engineering-design divide by bringing technical and product perspectives together earlier in the process. 7. The powerful “breadboarding” and “fat marker sketching” techniques that help teams align on solutions without getting lost in high-fidelity details. 8. The clear warning signs that your current development process is failing before it’s too late to change course. 9. Proven strategies to implement Shape Up methods, whether you’re working in a startup or enterprise environment. 10. A step-by-step approach to transitioning from Scrum to Shape Up by piloting the methodology with a single team before broader implementation. 11. Why the PM role shifts upstream in Shape Up, focusing more on problem definition than project management. 12. How to adapt Shape Up principles to your company’s unique context, even if it’s nothing like Basecamp. — Brought to you by: • WorkOS—Modern identity platform for B2B SaaS, free up to 1 million MAUs: https://workos.com/lenny • Merge—A single API to add hundreds of integrations into your app: http://merge.dev/lenny • Airtable ProductCentral—Launch to new heights with a unified system for product development: https://www.airtable.com/lenny Find the transcript at: https://www.lennysnewsletter.com/p/shape-up-ryan-singer Where to find Ryan Singer: • X: https://x.com/rjs • LinkedIn: https://www.linkedin.com/in/feltpresence/ • Website: https://www.ryansinger.co/ • Course: https://www.ryansinger.co/srl/ Where to find Lenny: • Newsletter: https://www.lennysnewsletter.com • X: https://twitter.com/lennysan • LinkedIn: https://www.linkedin.com/in/lennyrachitsky/ In this episode, we cover: (00:00) Ryan’s background (04:38) The origins of Shape Up (07:40) Implementing Shape Up in different companies (09:56) How Shape Up is different (19:02) The core elements of Shape Up (26:29) Shaping sessions and timeboxing (37:23) Flexible sprint planning (38:56) The output of a shaping session (46:57) Balancing detail and flexibility (53:50) A deep dive into shaping sessions (01:01:32) Fat marker sketches (01:02:48) Getting started using Shape Up (01:13:20) Signs it's time to try the Shape Up method (01:18:25) Feature factories (01:25:59) The role of the PM in Shape Up (01:28:26) What makes Basecamp unique (01:35:55) The second edition of the book (01:38:30) Linking product strategy and shaping (01:41:53) Conclusion and final thoughts Referenced: • Basecamp: https://basecamp.com/ • David Heinemeier Hansson on LinkedIn: https://www.linkedin.com/in/david-heinemeier-hansson-374b18221/ • Jason Fried on LinkedIn: https://www.linkedin.com/in/jason-fried/ • Jason Fried challenges your thinking on fundraising, goals, growth, and more: https://www.lennysnewsletter.com/p/jason-fried-challenges-your-thinking • Des Traynor on LinkedIn: https://www.linkedin.com/in/destraynor/ • Intercom: https://www.intercom.com/ ...References continued at: https://www.lennysnewsletter.com/p/shape-up-ryan-singer Recommended books: • Shape Up: Stop Running in Circles and Ship Work That Matters: https://basecamp.com/shapeup • Demand-Side Sales 101: Stop Selling and Help Your Customers Make Progress: https://www.amazon.com/Demand-Side-Sales-101-Customers-Progress/dp/1544509987/ • Competing Against Luck: The Story of Innovation and Customer Choice: https://www.amazon.com/Competing-Against-Luck-Innovation-Customer/dp/0062435612/ • Job Moves: 9 Steps for Making Progress in Your Career: https://www.amazon.com/Job-Moves-Making-Progress-Career/dp/0063283581 Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email podcast@lennyrachitsky.com. Lenny may be an investor in the companies discussed.

This talk was recorded at Copenhagen Developers Festival in Copenhagen, Denmark. #cphdevfest #ndcconferences #developer #softwaredeveloper Attend the next NDC conference near you: https://ndcconferences.com https://cphdevfest.com/ Subscribe to our YouTube channel and learn every day: / @NDC Follow our Social Media! https://www.facebook.com/ndcconferences https://twitter.com/NDC_Conferences https://www.instagram.com/ndc_conferences/ #agile #softskills In this talk, we look at the Shape Up methodology, a project management approach, or more correctly, a risk management technique, developed by Basecamp. We'll be focusing on its application in a real-world startup environment, drawing from two years of experience in implementing Shape Up. You'll get an overview of how this method contrasts with traditional project management techniques, particularly in terms of team organization and project execution. We will talk about our transition away from the traditional backlog system to embracing six-week work cycles and a project 'betting table', which has brought notable changes in our approach to task prioritization and execution. Our journey with Shape Up has given us several advantages, especially in moving away from exhaustive and often overwhelming backlogs. Another key aspect of our experience has been the shift from using time estimates over to implementing time budgets. While the approach has helped with our focus and with managing the uncertainties inherent in product development, it has not been without trade-offs. The talk will provide attendees with real-life examples and actionable insights, aiming to show how the Shape Up methodology can be effectively adapted in various organizational contexts and what challenges you can face. Whether you are part of a startup or a larger company, the session will offer valuable perspectives on balancing structure with flexibility in project management.

Learn to use Anthropic's Claude Agent SDK (formerly Claude Code SDK) for AI-powered development workflows! https://platform.claude.com/docs/en/agent-sdk/overview https://x.com/trq212 **AI Summary** This workshop by Thariq Shihipar (Anthropic) details the architecture and implementation of the **Claude Agent SDK**. The session moves from high-level theory—defining "agents" as autonomous systems that manage their own context and trajectory—to a live-coding demonstration. Shihipar builds an agent "Harness" from scratch, implementing the core **Agent Loop** (Context Thought Action Observation), integrating the **Bash tool** for general computer use, and demonstrating **Context Engineering** via the file system to maintain state across long tasks. **Timestamps** 00:00 Introduction: Agenda and the "Agent" definition 05:15 The "Harness" concept: Tools, Prompts, and Skills 10:10 Live Coding Setup: Initializing the Agent class and environment 15:45 implementing the "Think" step: Getting the model to reason before acting 25:20 The Agent Loop: connecting `act`, `observe`, and `loop` 33:10 Tool Execution: Handling XML parsing and tool inputs 42:00 The "Bash" Tool: Giving the agent command line access 49:30 Safety & Permissions: "ReadOnly" vs "ReadWrite" file access 58:15 Context Engineering: Using `ls` and `cat` to build dynamic context 01:05:00 The "Monitor": Viewing the agent's thought process in real-time 01:12:45 Handling "Stuck" States: Feedback loops and error correction 01:21:20 Multi-turn Complex Tasks: Building a "Research Agent" demo 01:35:10 Refactoring patterns: "Hooks" and deterministic overrides 01:48:39 Q&A: Reproducibility, helper scripts, and non-determinism 01:50:31 Q&A: Strategies for massive codebases (50M+ lines) 01:52:00 Closing remarks and future SDK roadmap * **Evolution of AI Capabilities:** Shihipar argues we are shifting from **LLM Features** (categorization, single turn) to **Workflows** (structured, multi-step chains like RAG) to **Agents**. He defines agents as systems that *"build their own context, decide their own trajectories, and work very autonomously"* rather than following a rigid pipeline. * **The Claude Agent SDK Architecture:** The SDK is built directly on top of **Claude Code** because Anthropic found they were *"rebuilding the same parts over and over again"* for internal tools. * **The Harness:** A robust agent requires more than just a model; it needs a "Harness" containing Tools, Prompts, a **File System**, Skills, Sub-agents, and Memory. * **Opinionated Design:** The SDK bakes in lessons from deploying Claude Code, specifically the "opinion" that general computer use (Bash) is often superior to bespoke tools. * **The Power of the Bash Tool:** A key technical insight is that the **Bash tool** is often the most powerful tool for an agent. Instead of building custom tools for every action (e.g., a specific API wrapper for a file conversion), giving the agent access to the shell allows it to use existing software (like `ffmpeg`, `grep`, or `git`) to solve problems flexibly, similar to how a human developer works. * **Context Engineering:** Shihipar introduces the concept of **Context Engineering** via the file system. Instead of just "Prompt Engineering," the agent uses the file system to manage its state and context. * **Files as Memory:** The agent can write to files to "remember" things or create its own documentation (e.g., `CLAUDE.md`) to ground future actions. * **Verification:** The file system serves as a ground truth for the agent to verify its work (e.g., checking if a file was actually created). * **The Agent Loop & Intuition:** Building a successful agent loop is described as *"kind of an art or intuition"*. The loop generally follows a **Gather Context Take Action Verify Work** cycle. Shihipar emphasizes that this loop allows the agent to self-correct, a capability missing from rigid workflows. * **Strategies for Determinism (Hooks):** During the Q&A, a technique for controlling agent behavior is discussed: **Hooks**. * If an agent hallucinates or skips a step (e.g., guessing a Pokemon stat instead of checking a script), a hook can intercept the response and inject feedback: *"Please make sure you write a script, please make sure you read this data."* * This enforces rules like "read before you write" without retraining the model. * **Scaling to Large Codebases:** For massive codebases (50M+ lines), standard tools like `grep` or basic context window stuffing fail. * **Semantic Search Limitations:** Shihipar notes that while semantic search is a common solution, it is *"brittle"* because the model isn't trained on the specific semantic index. * **Solution:** He recommends good **"Claude MD"** files (context files) and starting the agent in a specific subdirectory to limit scope, rather than trying to index the entire 50M lines at once.

An LLM is an incredibly powerful brain that knows everything about humanity and nothing about you or the software you run. This video walks through the four buzzwords that turn that raw brain into a system you can trust: agent harness, loop engineering, LLM Ops, and eval. No jargon, step by step, technical or not. You can build anything. You can learn anything. 💪 Timeline 0:00 Intro: the 4 AI agent buzzwords 0:42 What an AI agent run actually is 1:52 The memory system: procedural, semantic, episodic 3:37 What "harness" really means (the horse) 5:07 Storing and updating memory (databases, skills, summarizer agent) 8:28 Retrieval: RAG, SQL vs semantic search 10:00 Tool calling and why agents loop 10:52 Loop engineering and end-loop guardrails 13:21 A Claude Code hooks example 14:18 Eval and LLM Ops: why you need them 15:55 Tracing every run (Langfuse, LangSmith) 16:43 Evaluation: LLM as a judge 17:20 Diagnosing what broke 18:16 The gate: ship the fix or fix the bug 18:57 Zoom out: the full system 19:53 Wrap up Launch Full-Stack App Template: https://github.com/ShenSeanChen/launch-mvp-stripe-nextjs-supabase My AI Agent Startup AutoManus.io is an AI sales lead manager for made-to-order product sales. We embed directly where conversations happen (WhatsApp, email, web chat) to capture inbound, automate follow‑ups, and kill CRM busywork; live with 4 pilots and 2 contracts in motion, pre‑seed backed by Character VC. Focused on US/UK/Germany, raising to expand engineering and scale deployments. ☕️ Buy me a coffee: https://buy.stripe.com/5kA176bA895ggog4gh - X: https://x.com/ShenSeanChen - Sean's Discord: https://discord.gg/tvECErKcFr - AutoManus Discord: https://discord.gg/5HhcNjCR - LinkedIn: https://linkedin.com/in/shen-sean-chen - Github Link: https://github.com/ShenSeanChen - Instagram: https://www.instagram.com/sean_ai_stories Sub Count when launched: 13,050 Top Github Repos - LaunchMVP NextJS,Supabase,Stripe (1015 stars): https://github.com/ShenSeanChen/launch-mvp-stripe-nextjs-supabase - ReactNextJSTips (114 stars): https://github.com/ShenSeanChen/yt-react-nextjs-tips - DeepResearchAgentBackend (70 stars): https://github.com/ShenSeanChen/yt-DeepResearch-Backend - SupabaseTipsKanban (64 stars): https://github.com/ShenSeanChen/yt-supabase-tips-kanban - RAGVectorDB (56 stars): https://github.com/ShenSeanChen/yt-rag - KimiK2Claude (37 stars): https://github.com/ShenSeanChen/yt-kimi-k2-claude - DeepResearchAgentFrontend (33 stars): https://github.com/ShenSeanChen/yt-DeepResearch-Frontend - AgenticRAG (13 stars): https://github.com/ShenSeanChen/yt-agentic-rag You Can Build Anything Playlist (Full-Stack Dev Without CS Degrees) - Core7: 95% React/NextJS Use Cases https://www.youtube.com/watch?v=vZzFlAjz4rA&list=PLE9hy4A7ZTmpGq7GHf5tgGFWh2277AeDR&index=16 - Core6: 95% Supabase Use Cases https://www.youtube.com/watch?v=Pnoq2tIif3s&list=PLE9hy4A7ZTmpGq7GHf5tgGFWh2277AeDR&index=15 - Core5: StripeNextJSSupabase https://www.youtube.com/watch?v=ad1BxZufer8&list=PLE9hy4A7ZTmpGq7GHf5tgGFWh2277AeDR&index=8 - Core4: AuthSupabaseGoogle https://www.youtube.com/watch?v=AZAU3ClAWWE&list=PLE9hy4A7ZTmpGq7GHf5tgGFWh2277AeDR&index=6 - Core3: FastapiGCPPro https://www.youtube.com/watch?v=u3sfqpzzo-U&list=PLE9hy4A7ZTmpGq7GHf5tgGFWh2277AeDR&index=5 - Core2: SupabaseHero https://www.youtube.com/watch?v=V0kmgkyPsVQ&list=PLE9hy4A7ZTmpGq7GHf5tgGFWh2277AeDR&index=4 - Core1: LaunchAnApp https://www.youtube.com/watch?v=iQ2izvGG4tQ&list=PLE9hy4A7ZTmpGq7GHf5tgGFWh2277AeDR&index=3 - Launch WhereToMeet w/ GoogleMaps, Calendar, Supabase, Cursor: https://www.youtube.com/watch?v=5xMjX1QxGUY&list=PLE9hy4A7ZTmpGq7GHf5tgGFWh2277AeDR&index=2 - Launch EncourageMe w/ Cursor, Supabase, Vercel https://www.youtube.com/watch?v=hnvL4xa2DHA&list=PLE9hy4A7ZTmpGq7GHf5tgGFWh2277AeDR

A hands-on workshop covering the full lifecycle of AI-assisted development, from turning ambiguous requirements into agent-ready plans to running autonomous coding agents that ship production features. You'll learn to stress-test vague briefs into structured PRDs, slice work into thin "tracer bullet" vertical slices, and run an AI agent with TDD. You'll watch it select tasks, write tests, implement code, and commit. You'll then refine your prompts based on where it struggles, graduate to fully autonomous (AFK) runs, and learn to design codebases that maximize agent effectiveness. You'll walk away knowing how to: - Turn ambiguous requirements into agent-ready issues - Slice work into vertical tracer bullets an agent can grab independently - Run AI agents human-in-the-loop and autonomously with TDD - Design codebase architectures that AI agents love to work in For: Engineers ready to move beyond chat-based AI assistance and build a real workflow for shipping features with autonomous coding agents. Speaker info: - https://x.com/mattpocockuk - https://www.linkedin.com/in/mapocock/ - https://youtube.com/@mattpocockuk Timestamps: 00:00:00 - Introduction 00:00:14 - The Thesis of AI Engineering 00:04:20 - Phase 1: Research & Prototyping 00:12:45 - Phase 2: The Grill Session 00:22:10 - Phase 3: Writing the PRD 00:35:50 - Phase 4: Slicing Work into Issues 00:48:15 - Phase 5: Implementation with AI Agents 01:05:30 - Phase 6: Human-in-the-Loop Review 01:18:45 - Phase 7: Deployment & Monitoring 01:28:10 - Designing Codebases for AI Effectiveness 01:34:06 - Final Takeaways & Summary --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/-QFHIoCo-Ko-ai-coding-workflow Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIE New York, October 12–14 — the first AI Engineer Finance mainstage summit - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney ---

🔥 Join Maker School & get customer #1 guaranteed: https://skool.com/makerschool/about 📁 Get all Claude course resources 100% free: https://skool.com/maker-zero/about ➡️ If this is your first video: I'm Nick Saraev. I run LeftClick, an AI growth agency. We've done work for large brands you're likely familiar with, like Mr. Beast, Anthropic, OpenAI, and a few others. In plain English: I help people build systems that generate leads, close deals, and scale businesses, mostly using new AI models like Claude. I also make videos about how to do all of that here on YouTube. It hasn't always been this way. My family immigrated from a Soviet bloc country (People's Republic of Bulgaria) in the 90s. They worked extremely hard, and we were broke for a very long time. I grew up wishing for more security, stability, and freedom over my own life. I don't have a programming degree, and never took formal education for IT or workflows. I learned it all myself from YouTube videos like you're watching now. As for my path: I started my first business at 19 in college. We threw events (mostly parties) at campus bars, and charged people for entry. That failed to provide me enough money to pay my bills, so at 21, I started another business, a door-to-door marketing agency. From there, every year, I would start several companies, over 10 in total. I did this in a variety of industries, like e-commerce, photography, videography, SaaS, credit repair, etc. Each grew slightly more profitable, until, at 25, I would start 1SecondCopy, a content writing company. A friend and I eventually scaled that to over $90,000/m. It was my first taste of financial independence, and the reason I'm here today. Since starting my journey, I've grown a fair bit of capital. To diversify my income, at 30, I began investing in other businesses and advising companies on how to grow in the AI era. These include SaaS businesses, like Clairvo, agencies like Dental Connect, and more. Collectively, the businesses that I own outright or are a part of generate over $10 million per year. This returns far more than the 5-10% you would get in the stock market, but also requires a lot of my active time. There's a tradeoff there, but I greatly prefer active investing, where I have control over the entities I'm a part of. It wasn't easy to get here. But I did in the end! For anyone on their own entrepreneurial journey: I wish you luck, happiness, and perseverance. You can make it! Summary ⤵️ The end-to-end, definitive course on Claude Code for beginners! I'll take you through a full four-hour masterclass where I start by teaching you how to set up and install Claude Code in a tutorial, how to configure your IDE or integrated development environment (we'll use Antigravity), how to utilize your CLAUDE.md file as your project brain, how to build your first project in Antigravity using Claude Code in under 15 minutes, advanced Claude Code functionality including hooks, slash commands, and more. I also teach you how to spin up multiple Claude Code instances and have them work on your behalf; how to parallelize work using sub-agents; how to use Git work trees to accomplish many hours of work in just a few minutes; how to conserve tokens and use context management to crush your coding and software projects; how to deploy things to the cloud using Modal and related services, and in general... how to be awesome at Claude Code! Hope you enjoy the tutorial. Chapters 00:00:00 Introduction to the Claude Code Tutorial 00:01:07 Learning the Basics of Claude Code 00:03:44 Setting Up Claude Code 00:08:05 Terminal vs. Graphical User Interface 00:12:23 Understanding IDEs 00:13:53 Exploring Visual Studio Code 00:19:11 Getting Started with Antigravity 00:24:01 Building Your First Web App with Claude Code 00:30:29 Utilizing the CLAUDE.md File (Project Brain) 00:34:40 Approaches to Website Design in CC +Antigravity 00:41:47 Importance of Verification in AI 00:54:42 Advanced Claude Code Functionality 00:55:13 Understanding the .claude Directory 02:01:24 Adjusting the Proposal Design 02:01:55 Testing Payment Functionality 02:05:20 Leveraging GitHub for Project Management 02:06:12 Setting Up the Project 02:07:50 The Power of Automation 02:13:53 Context Management Explained 02:19:56 Understanding MCP Tools 02:27:23 Strategies for Token Management 02:35:29 Creating Skills for Efficiency 02:41:15 The Structure of Skills 02:44:39 Building a New Skill 02:50:58 Introduction to Model Context Protocol 02:58:15 Evaluating Token Usage in MCPs 03:09:07 Exploring Claude Code Plugins 03:11:08 Introduction to Sub-Agents 03:12:15 Transforming Skills into Sub-Agents 03:14:14 Scaling Email Classification 03:18:54 Creating Useful Sub-Agents 03:26:27 Understanding Agent Teams 03:32:59 Enabling and Using Agent Teams 04:02:34 Utilizing Git Worktrees 04:03:08 Deploying APIs with Modal