Kentro

Cohort 1

Over 100 pages of answered questions, guides, and tips and tricks from Isaac Flath and Eleanor Berger!

Tips, Guides, and Answered Questions

A curated collection of LLM Context for building web applications efficiently with FastHTML. Includes `.ruler` formatted context, a Playwright MCP server example that works, and a small README tutorial to connect it all to Claude Code or other tools. This is the companion context to <a href="https://www.youtube.com/watch?v=CAxtf2nsnKE" rel="noopener noreferrer" target="_blank">this free talk</a> on Youtube

FastHTML LLM Context for AI Assisted Web Development

Are you making the most of AI-assisted development? Take this 5-part self-assessment to rate capabilities across foundational knowledge, interactive use, context &amp; environment, development process, and governance. Get a readiness score plus personalized priorities and learning resources.

Self Assessment: Are You Prepared for Making the Most of AI-Assisted Software Development?

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&amp;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 &amp; Wireless Communications・GitHub・Microsoft・Google・Canonical・Answer AI・and more ... Companies Our Students Are From ・Amazon (AWS)・Microsoft・Google・X・Shopify・Cisco・Red Hat・DocuSign・Qualcomm・Monster・Booz Allen Hamilton・TrustLayer・and more … Weekly Session Breakdown 🗓️ Week 1: Foundation &amp; 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 &amp; Frictionless Setup&nbsp;・Context stack: rules, docs, tools.&nbsp;・MCP in practice: context and action.&nbsp;・Supporting docs: importing key library/framework docs; updates; combining static imports with MCP.&nbsp;・Determinism &amp; validation: smoke prompts, golden answers, scripted checks. 🗓️ Week 2: Interactive Development &amp; Collaboration 📋 Interactive Agents &amp; Spec‑First Planning&nbsp;・Spec‑first flow: requirements → tasks → constraints → evaluation.&nbsp;・Mastering modern coding agents (in IDE and terminal).&nbsp;・De‑risking scope: narrow diffs, feature flags, rollback plans.&nbsp;・Custom MCPs, workflows, commands, and subagents. 📋 AI Code Review, PR Orchestration &amp; Security&nbsp;・Coding agent security: private data + untrusted context ⇒ risk.&nbsp;・Approvals &amp; execution modes and environments: fine-grained permissions, sandboxing, execution modes.&nbsp;・Auditability: structured logs and git history.&nbsp;・AI-powered DevOps: PRs, project management, deployment, observability. 🗓️ Week 3: Async Agents, CI/CD &amp; Advanced Techniques 📋 Async/Background Agents &amp; Dynamic Context&nbsp;・Background agent architectures: SaaS, GitHub Actions, scheduled tasks, job runners.&nbsp;・Effective delegation: specs and environments for end-to-end AI execution.&nbsp;・Automating software projects with continuous AI. 📋 Parallelization, Measuring Efficacy, &amp; Continuous Improvement&nbsp;・Accelerating productivity with parallel agents and workflows.&nbsp;・Measuring and reasoning about efficiency and quality in AI-powered software development.&nbsp;・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 &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

Course syllabus

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

Course schedule

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

Who is this course for

What you’ll get out of this course

<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.

Microsoft

Google

Canonical

Eleanor Berger

AI Leader, ex-Microsoft, ex-Google

Travel + Leisure

Cable & Wireless Communications

SpecStory

Answer AI

AnkiHub

Isaac Flath

Founder of Kentro Tech

OpenHands: AI software development agent platform

Ray Myers

Chief Architect at All Hands

OpenHands is a leading open-source and hosted software development agent platform - versatile and powerful.

Get to know OpenHands

Learn from Ray about the power of agentic AI coding and how it fits within the broader software development landscape.

Learn about agentic AI coding

Learn to build agents with the newly released OpenHands SDK to go beyond the basics

Open Hands SDK

Build Your Own AI Coding Agent from Scratch

Engineering & AI Leader; Elite AI-Assisted Coding co-instructor

Dev-efficiency and AI expert; Elite AI-Assisted Coding co-instructor

Hack together a tiny coding agent with us, end to end.

Build a simple AI coding agent

Understand how AI coding agents work so you can use them better.

Build a mental model of agents

Use context management, clear specs, small steps, interactive and structured flows.

Practice AI-assisted coding best practices

Agentic Code Search with GitHits

Olli-Pekka Heinisuo

Senior Applied AI Architect & Co-founder @ Softlandia

A clear mental model of how GitHits distils up-to-date, ready-to-use examples from public GitHub repos.

How Agentic Code Search Works

A live walk-through from a real task to a paste-ready snippet, including quick adaptation and verification.

From Problem to Working Code in Minutes

Practical tips for setup, privacy, limits, and when to trust results — plus how to pilot it with your team.

Adopting It in Your Workflow

You Can Just Do Things

Peter Steinberger

Full-Time Open Source Builder

AI is gonna change the world, and it's starting with software development.

Using AI agents to build

Explaining this incredible shift that's currently happening.

Inspirational thoughts and practical tips

AI-Powered Observability with Pydantic Logfire MCP

Samuel Colvin

Founder @ Pydantic

Pydantic Logfire is an observability platform designed to be easy to set up and understand.

Using Pydantic Logfire

How to use Logfire to observe complex systems and find needles in haystacks.

Logging, Tracing, and Debugging

Using Logfire MCP with your AI agent to integrate observability into your workflow.

Agentic debugging with Logfire MCP

Vibe Coding a Broadcasting Graphics Solution in 6 Hours

Stefanie Hetjens

CEO & Founder @ EVERYWOW

Solve an immediate problem perfectly, rather than over-engineering a permanent solution.

A new mindset: Learn when to build "throw-away" software.

How to establish a structured "vibe coding" process to move from a high-level idea to a functional, AI-created solution.

Structured "vibe coding" process

Practical techniques for managing an AI-driven workflow from a real-world example.

AI-driven Workflows

Agents that do the things Claude Can't

Vincent Warmerdam

Founding Engineer at Marimo, Creator of Calm Code

Learn to create taskmaster agents with specialized AI tools you can delegate repetitive tasks

Create customized Terminal Agents Customized for Tasks

A new approach to AI in notebooks, leveraging their dynamic nature to include more context about your code

Learn about the new dynamic AI context in Marimo Notebooks

Toad - a universal UI for agentic coding in the terminal

Will McGugan

Python Terminal UI Guru (creator of Rich and Textual)

Toad aims to raise the bar on TUI quality for coding agents, with jank-free, rich display

Learn about Toad, a new terminal coding agent in development

TUIs are exploding thanks to interest in coding agents and other tools. Modern Python can serve them well.

Learn about TUIs in Python

The Parallel Agent Multiplier

Charlie Holtz

Founder of Melty, Lead Developer of Conductor

AI Expert and Technology Leader (ex-Microsoft, ex-Google)

Get usage tips and information about conductor from the only source that has all the information

Inside look at Conductor from the team who built it

Learn to efficiently manage tasks across agents and coordinate their outputs for maximum efficiency

Learn Parallel Coding Agents Workflows

Learn to set up Conductor to manage multiple AI agents working on your codebase

Build Your First AI Dev Team

AI-assisted DevOps:
Driving Git and GitHub

Clelia Astra Bertelli

Open Sourceress @ LlamaIndex

Building a tool that focuses on a specific task or environment can help accelerate operations.

Building a task-focused AI tool

Learn about Gut, an open-source AI tool for driving operations with Git and GitHub

Gut: a Git and GitHub AI driver

AI tools can assist in all aspect of the software lifecycle, not just in writing code.

Kentro

Kentro

Courses

Lightning Lessons

Resources