Course: Elite AI Assisted Coding

---

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 tools you use.

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 many more …

Companies Our Students Are From

• Amazon (AWS)

• Microsoft

• X

• Shopify

• Cisco

• DocuSign

• Monster

• TrustLayer

• and many more …

Weekly Session Breakdown

Week 1: Foundation & Personalization

1. 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.

2. 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

3. 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.

4. 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

5. 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.

6. Parallelization, Measuring Efficacy, & Continuous Improvement

   • Accelerating efficiency 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, Cursor, Copilot, Windsurf, Claude Code)

• 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

---