Chimera

Learning to Speak Code

Sean Thielen-Esparza

Building AI-powered storytelling tools as a creative technologist at Complex.

Language to precisely control AI coding agents.

Ship alongside other developers with confidence.

Personalized toolkit for AI programming.

Path towards understanding & writing code yourself.

Ship better software, faster. A comprehensive course from first principles to autonomous AI-powered development – precision, not vibes.

AI & Software Engineering Leader

Google

Microsoft

Canonical

Eleanor Berger

Cohort 3

Cohort 4

AI is transforming software engineering. Mastering AI-powered coding is now core to every developer, engineering leader, and product professional.Go beyond the hype – build deep understanding of the fundamentals and best practices that will serve you and your team for years to come.Learn complete frameworks for Context Management and Specification-driven Development, and master the integration of AI across the full Software Development Lifecycle – from individual practice to enterprise-scale autonomous operation.

Adopt AI-powered Software Development with Confidence

Context Engineering

Spec-Driven Development & Precision

Agentic Software Engineering

AI Across the Software Development Lifecycle

Security, Quality, Product & Enterprise Readiness

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

Coding Experience

Developers &amp; Engineers who want to build technically solid solutions and adopt AI-powered software engineering with confidence.

Engineering Leaders who need to adopt and grow dependable and repeatable AI-forward software development processes.

Software Professionals – PMs, Analysts, Managers – growing from clients &amp; planners to contributors &amp; operators with the power of AI coding.

Students will learn the AI literacy to evaluate AI ideas, surface risk, and make sound judgments without becoming technical specialists.

Modernizing Business Analysis

Angela Wick

25+ years practicing, shaping, and teaching analysis, product, and requirements.

AI Literacy for Business Analysts

AI usage, productivity, and implementation risk often come from poor assumptions about what AI can and cannot do. It also stems from poor analysis and organizational dynamics in which stakeholders ask for solutions that are either too specific or too generic, and pressure teams to deliver them, rather than solving real problems.Analysis professionals have a huge role in this dynamic that can change everything!Analysts are increasingly expected to participate in AI decisions, yet most training focuses on tools or stays abstract. This course fills the gap in understanding AI capabilities: Not from a technical point of view, but from a capability point of view; business uses and patterns of functional usage.You will build a grounded understanding of AI capabilities, limits, and failure modes, and learn how requirements shift toward hypotheses, experiments, and continuous outcomes in AI-enabled work.This course explores the skills of:🎯 Identifying the right AI use cases for specific business scenarios🎯 Distinguishing between deterministic and probabilistic systems and deciding where each should be applied in a workflow🎯 Questioning and communicating AI use case fit and risks

Giving BAs AI Fluency & Literacy to Use, Analyze, and Recommend AI Solutions

Major AI capability types and their appropriate uses

GenerativeAI is just one piece of AI, and much more than "chat".

What AI is good at and where it fails

Generative AI and its Data Sources (Public vs. Private)

How requirements shift to hypotheses and experiments

Where humans must remain accountable in AI-enabled systems

Business Analysts, Product Owners, Business Systems Analysts, Systems Analysts, Business Process Analysts, and similar roles.

BA Leaders redefining roles for AI-enabled teams

Business Leaders, Project and Product Professionals pulled into AI initiatives without clear accountability

Become a real Claude Cowork builder and ship a custom skill in 1 day.

Cohort 2

Sr Dir @Salesforce | ex-Microsoft AI

Salesforce

Goldman Sachs

McAfee

Shankha Dey

Sr Director PM @ Salesforce | ex-Microsoft Bing & Copilot | Columbia CS

Co-Founder & COO at Level Up | ex-Amazon

Amazon

Dentsu

IPG Mediabrands

Harvard Business Review

Techstars

Jason P. Yoong

Co-Founder & COO at Level Up (fmr Amazon, VP at Dentsu, Startup - $8M seed)

Cohort 1

If you're a realtor, marketer, consultant, or any other non-technical professional who's tried Claude but it doesn't feel like it's saving you real time, this is the course for you.The gap between output that looks right and output that is right is where most AI tools fail people. Your email drafter runs. It looks professional. But is it surfacing the right emails? Do the drafts sound like how you would reply to that person?AI Evals is the fastest growing skill in the world. This course applies that methodology (developed and refined since 2018 by Shankha) to your automations, in plain English.You will build 3-4 automations and apply a simple evaluation framework to each one. You define what good looks like before you build. You run it. You find the gap. You fix it. That's the loop that makes AI tools useful.This is a hands-on build something real workshop, with instructors live (not a passive webinar). Spots are limited to keep cohorts small.

You will leave with real working automations that save you time.

Three automations running on your real data

Skills connected to your real tools via MCP

An evaluation framework you can apply to any AI output

(Optional) custom Skill for your job

Direct instructor time that no larger future cohort will get

Intel Mac and Windows ARM64 are not supported by Claude. Instructors will use Mac

MacOS with Apple Silicon (M1 or later) or Windows 11 Pro x64

Visit claude.com/download. Not claude.ai (need the desktop app).

Prework setup (20min): Step-by-step guide provided.

Claude Desktop installed & Prework Setup (20min)

Advanced features (e.g. Cowork, Skills, Projects) require a paid plan.

Claude paid subscription (Pro or Max)

Non-technical operators and leads who want to use AI to automate workflows (to save time) and learn fast with a one-day hands-on workshop.

Non-tech professionals who know AI is critical to their business and want a hands-on 101 level (no jargon) workshop to get started.

AI-aware leaders who want to move from “Claude dabbling” to building a real Claude Cowork skill that saves time.

Working with code as the raw material of software will change how you see design and what you can do with it.

Design Teacher

General Assembly

Ironhack

Edenspiekermann

BuzzFeed

Cantilever Web Design & Development

Nevan Scott

Designer/developer since before it was uncool

Making software is supposed to be fun! And this six weeks is packed with the most fun I’ve had in my 15-year teaching career.LLM-assisted coding tools can put you in the driver’s seat, working with the real materials of your craft. I’m seeing designers do things I didn’t think I’d ever get to see designers do.For as long as I can remember, product designers have been pushed away from code. Most designers settled this question for themselves long ago—code is not for me. Now is a great time to reconsider that decision. You can have a relationship with what feels like real work without spending years mastering syntactical minutiae.Working on a design with code is an act of shaping: you’re shaping something out of the raw materials yourself. And as you shape it, you can actually interact with it, get the feel of it. This means you can work on a user interface the way it really works.As designers, we enjoy making things. Working with code is a fantastic opportunity to feel connected to the thing you’re making.Read on to find out more about the course, but keep in mind that the most important things that happen in my classroom <a target="_blank" rel="noopener noreferrer nofollow" href="https://buttonschool.com/classroom/">have nothing to do with the syllabus</a>.

Learn how to use AI coding tools to build your own designs

Take the driver’s seat when working with LLM coding tools

Read code to understand the shape of what you’re making

Form a strong mental model of the architecture of what you’re building

Any amount of knowledge will work in your favor, but the course is made for designers with little-to-no coding skills.

No previous coding experience is required

The course leans into understanding—not just generating—so a desire to go beyond surface-level outputs will help you get the most out of it.

Curiosity about how things work under the hood

You should be comfortable making product decisions and thinking beyond individual screens.

Experience designing real-world products

Product designers with solid design experience but little (or zero) coding knowledge who want to build working apps of their own creation.

Product designers comfortable in tools like Figma who want to understand how web apps work and are ready to learn new tools and thinking.

Product designers who want to cut through the noise by learning how to use AI coding tools with structure, intention and control.

Velocity Coding

Agentic AI

Coding with AI

AI Workflows

Claude Code

OpenClaw

Vibe Coding

AI Evals

AI Transformation

RAG & Search

AI for PMs

AI for Engineers

AI for Designers

AI for Marketers

AI for Founders

Product Sense

Product Discovery

User Research

Prototyping

Growth

Analytics

Tech Foundations

Strategy

Influence

Leadership

Career Growth

Machine Learning

LLM Ops

Context Eng

Security

System Design

Figma

Design Systems

Visual Design

Design Strategy

Automation

Content Marketing

Demand Gen

Go-to-Market

Product Marketing

Positioning

Social Media

Brand

B2B Marketing

SEO & AEO

AI for Leaders

AI Governance

Communication

Management

People Operations

Exec Presence

Storytelling

Goal-setting

Personal Brand

Fundraising

Everyone

Operators

Data Scientists

Business Analysts

User Researchers

Customer Success

Project Managers

HR Professionals

Sales People

Lawyers

Finance

Investors

Real Estate

Educators

Creators

Late start, waiting for participants, session kickoff

Lightning session goals: demystify AI coding and make shipping accessible for non-engineers

Speaker background and why “Learning to Speak Code” matters beyond one-shot prompting

The SLOP problem: AI-generated code that works but is hard to reason about and debug

Framework overview and shared GitHub repo of Cloud Code strategies

Non-engineer bottlenecks: Git/GitHub basics, branch management, and PR review culture

Framework 1 — Comprehensive code: explainability rule, heritage-speaker analogy, and the “2AM test”

Framework 2 — Context engineering & atomic features: plan mode, distill plans into GitHub issues, keep PRs small and reversible

Framework 3 — Build for simplicity: avoid premature clever abstractions

Using multiple models as a “phalanx”: planning vs execution vs review models

End-to-end daily workflow: voice planning, issues, branch-per-issue, reset chat context, and PR review with Greptile

Git/PR essentials: branches, commits, pull requests, etiquette, and PR review checklist (including CI and secret handling)

Model recommendations and key takeaways: you’re the product judge, manage context, ship small PRs frequently

Q&A: applying the approach to large monorepos, tool costs, and preferred models

Q&A: GitHub Copilot for CI log debugging, moving context between tools, and multi-model agent interfaces

Wrap-up: more questions, resources follow-up, Greptile reviewer tool, using Google’s Anti-gravity IDE, and how he runs Cloud Code in Cursor

Product managers who drive strategy, development, and launch of products.

Engineers and engineering leaders who build, deploy, and scale software systems.

Broad professional audience — content relevant across many roles and functions.

Applying AI tools and techniques to professional workflows — assign alongside more specific AI topics.

Using AI coding assistants and tools to write, review, and ship code faster.

Building technical literacy — understanding APIs, databases, system architecture, and engineering tradeoffs.

Learning to Speak Code

What you'll learn

Why this topic matters

You'll learn from

Sean Thielen-Esparza