 Agentic Code Engineering, SmartGenie

Sachin Mundra

Production-ready AI · Governed, Secure, Auditable · Ex-Microsoft 20+ yrs.

Is your AI lying to you?

The failure that sinks AI-built software the moment it leaves the demo, and why a bigger model will not fix it.

The flaw that breaks AI-built software in production

The practice we use so every fact your AI writes carries its source, turning guesswork into output you can check.

How we make AI prove every claim it writes

Build the guardrail that keeps unverified AI work out of your codebase, the core of Agentic Code Engineering.

The automatic check that makes AI code shippable

Go from a demo and a feeling to an evaluation practice you can run every week and defend to whoever controls the budget.

I build AI that has to survive an audit

Amazon Web Services

HashiCorp

VMware

NGINX

University of California

Thomas Underhill

Product & Eng Leader (AWS, VMware, HashiCorp, NGINX) · Adjunct Professor

Cohort 1

Your team put a model in production and it seems to be working. Then someone above you asked what the AI spend is returning, and the honest answer was a demo and a feeling.That is not a failure of rigor on your part. It is a structural problem with a name. On complex work, checking an answer costs about as much as producing it, so grading does not scale, so nobody grades. Ninety six percent of engineering teams use AI tools. Around twenty percent measure the result specifically.The gap is not laziness. It is that the standard advice does not work on the problems you have. Accuracy misleads on imbalanced data. Your eval set is probably contaminated and you cannot check. And for the most valuable work your system does there is no right answer to compare against, which is where most teams give up and let a model grade a model.There are ways out of all of that, and none is new. Metamorphic testing dates to 1998 and was never pointed at language models until recently.This course builds one evaluation practice, for one real system of yours, across five weeks. You leave able to say what working means, prove whether you have it, and defend the number to whoever holds the budget.

You shipped it. Now somebody wants a number, and you do not have one.

Define what working means for output that changes every run

Build an evaluation set you can actually trust

Choose a metric you can defend, and set the threshold from cost

Grade the work that has no right answer to compare against

Catch a regression before a customer does

Defend the whole thing to the person holding the budget

Every exercise runs against a real system of yours. Without one there is nothing to evaluate, and the coursework does not work in theory.

An AI system already in production, or about to be

The exercises run on my data, but the plan is for your system. You need to know what it does, what failure costs, and who cares about it.

A system you are accountable for, and enough context to describe it

Every exercise is a design decision rather than an implementation. You will read code. Your engineers build what you specify.

No machine learning background, and no code required

Engineering leader who shipped it and cannot measure it.

Product leader being asked what the AI spend returns

Anyone whose team grades model output with another model

A practical workshop on evaluating AI agents before launch

Founder & CEO | Ex-Adobe, WF, eBay | HBS

Adobe

Wells Fargo

eBay

Ganesan Anand

Founder, Formerly AI Product & Tech Leader (Adobe, Wells Fargo, eBay) · HBS alum

Next Cohort

<blockquote>Move your AI features from a vibe check to a value check. “Did the agent do the right thing? Would I catch it if it didn’t?” Every team shipping AI features is asking some version of these questions without a reliable way to answer them. An agent doesn’t just say the wrong thing. It does the wrong thing, and teams often find out from a user.Typical AI training falls into two traps: abstract theory that never leaves the slide deck, or disconnected techniques that stop short of a production-ready system. This workshop bridges that gap. I build enterprise infrastructure for AI evaluation every day, and I’ve seen that real adoption only happens when teams can trust their AI to perform consistently.You’ll learn a repeatable method for applying Responsible AI in practice, with a focus on reliability and safety. You’ll learn which metrics matter for your product, identify the edge cases that undermine trust, define how the product should respond, and prove it works before customers see a problem.</blockquote>

Learn a repeatable evaluation framework for building and releasing reliable AI features.

Know exactly what to measure

Find failures before your users do

Get a pass/fail read before release

Keep quality from slipping after launch

Access to leading commercial and open-source AI models is provided during the session for the eval exercises. Nothing to set up or pay for.

Model access is provided

Come ready to dig into how AI features fail and how to catch it. That mindset is all it takes.

Curiosity about AI quality

The session is live and remote, so a solid connection matters. Everything runs in-browser, and the no-code evaluation platform is provided.

Stable internet

AI engineers and product managers building, evaluating, or preparing to release AI features

Founders turning an AI prototype into a reliable product

Engineering and product leaders accountable for AI quality, safety, and release decisions

Defend a real decision on camera with AI removed, scored twice, and learn the practice that keeps your judgment sharp.

Exec Coach to Google, PayPal, the NFL

Google

Amazon

PayPal

U.S. Army

Joshua Miller

Master Certified Exec Coach to Google, PayPal, Amazon | LinkedIn Top Voice

Your output has never been faster. And somewhere in the last year, you noticed you could not fully explain a decision you had just made. Not the outcome. The reasoning underneath it.Most leaders respond by promising to read the output more carefully. That does not work, because you cannot detect this in yourself. People rate their own understanding highly right up until someone asks them to explain it out loud.That is Cognitive Atrophy. You did not lose intelligence. You stopped using the one capability your role rests on.AI can analyze, model, and recommend. It cannot sign its name. When the call goes wrong, nobody asks the model. They ask you. And the problem is not that your calls are wrong. It is that you have lost the ability to tell.Leaders who cannot explain their reasoning stop being handed the decisions that matter. Nobody says why. It just stops.In four weeks, you defend a real decision on camera with AI removed, scored in week one before any instruction and again in week four. You leave with proof, not notes.Every other course on decision-making is assessed using the tool. This one is assessed with it gone.

Every other course teaches deciding with AI. This proves you can without it.

Answer the follow-up you never prepared for because AI answered it first

Form your own position before the tool has framed it for you

Interrogate AI output that is persuasive and confidently wrong

Catch your own erosion while it is still reversible

Name the assumption your decision rests on, without notes

Defend a real decision with the tool removed, scored twice

Senior Executives and VPs<blockquote>The board will ask how you got there. "The analysis supported it" is not an answer anyone accepts twice. </blockquote><h3></h3>

Directors and Senior Managers<blockquote>AI made everyone's output look the same. Judgement is the only thing left that gets you promoted. </blockquote>

Founders and CXOs<blockquote>No one will ever ask you to explain a call. You find out you were wrong when the company does. </blockquote>

Your team adopted AI. Why hasn’t delivery improved?

Staff Software Engineer

Luis Vieira

Staff engineer

Agentic Engineering 1

<blockquote>AI coding tools make implementation faster. But typing code is only one part of getting software safely from idea to production.Teams still need to turn ambiguous requests into clear plans, give agents the right context, understand how changes affect existing systems, verify that the work is safe, and decide what should reach production.As agents become more capable, the bottleneck shifts. When code is cheap to produce, context, judgment, verification, and coordination become the limiting factors.This requires new agentic engineering practices: structuring work for delegation, giving agents clear constraints, running independent workstreams in parallel, and knowing where human judgment matters most.This workshop gives you a practical method for improving software delivery with agents. You’ll learn to identify SDLC bottlenecks, use multiple cloud agents in parallel, and build the context, guardrails, proof of work, feedback loops, and evals needed to improve them over time.</blockquote>

Learn how to find delivery constraints, design trustworthy agent workflows, and improve them through evidence, feedback, and evals.

Understand the AI coding plateau

The AI-Native Engineer

Agents across the SDLC

Implement a trustworthy agent harness

Improve agent workflows over time

Software engineers using AI coding tools looking to improve their team SDLC

Tech leads and engineering managers who want to understand how to increase engineering output using AI

Engineering leaders who adopted AI tools but aren't seeing it in delivery speed or business outcomes and want to understand why and fix it

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

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

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

Building autonomous AI agent systems that take actions, use tools, and orchestrate multi-step workflows.

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

Measuring and evaluating AI model performance, quality, and reliability for production use cases.

Is your AI lying to you?

What you'll learn

Why this topic matters

You'll learn from

Sachin Mundra