Course Overview

・Duration: 3 weeks, 12 live sessions

・Format: Cohort-based course

・Goal: Transform generic AI assistants into personalized coding partners that understand your codebase, patterns, and needs

Learning Structure

Each part (week) of the course includes:

・2 live lessons

・Office hours session (Q&A and discussion)

・Live practice session

・Homework assignment (with both begginner-friendly and stretch exercises)

・Pre-reads and lesson materials

・Deep-dive collections (optional) for exploring topics in depth

In addition, learning continues with:

・Questions and discussions in the course Discord server

・Guest lectures

・Student exchange and collaboration

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 & Wireless Communications

・GitHub

・Microsoft

・Google

・Canonical

・Answer AI

・and more ...

Companies Our Students Are From

・Amazon (AWS)

・Microsoft

・X

・Shopify

・Cisco

・DocuSign

・Monster

・TrustLayer

・and more …

Weekly Session Breakdown

🗓️ Week 1: Foundation & Personalization

📋 Introduction to AI-Assisted Software Development

・Course orientaion.

・Tools and human in the loop - Claude, Copilot, Cursor, Codex … and you.

・Recognize capabilities, limits, pitfalls, safety, and coding pattern basics.

・Start with any modern IDE, terminal, or browser-based agent with near-zero setup.

📋 Context Engineering & Frictionless Setup

 ・Context stack: rules, docs, tools.

 ・MCP in practice: context and action.

 ・Supporting docs: importing key library/framework docs; updates; combining static imports with MCP.

 ・Determinism & validation: smoke prompts, golden answers, scripted checks.

🗓️ Week 2: Interactive Development & Collaboration

📋 Interactive Agents & Spec‑First Planning

 ・Spec‑first flow: requirements → tasks → constraints → evaluation.

 ・Mastering modern coding agents (in IDE and terminal).

 ・De‑risking scope: narrow diffs, feature flags, rollback plans.

 ・Custom MCPs, workflows, commands, and subagents.

📋 AI Code Review, PR Orchestration & Security

 ・Coding agent security: private data + untrusted context ⇒ risk.

 ・Approvals & execution modes and environments: fine-grained permissions, sandboxing, execution modes.

 ・Auditability: structured logs and git history.

 ・AI-powered DevOps: PRs, project management, deployment, observability.

🗓️ Week 3: Async Agents, CI/CD & Advanced Techniques

📋 Async/Background Agents & Dynamic Context

 ・Background agent architectures: SaaS, GitHub Actions, scheduled tasks, job runners.

 ・Effective delegation: specs and environments for end-to-end AI execution.

 ・Automating software projects with continuous AI.

📋 Parallelization, Measuring Efficacy, & Continuous Improvement

 ・Accelerating productivity with parallel agents and workflows.

 ・Measuring and reasoning about efficiency and quality in AI-powered software development.

 ・Mining projects for evidence-based decision making and continuous improvement.

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 & 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