Workshop

Responsible AI Agents: From Design to Production

Ganesan Anand

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

Hands-on AI evals for product and engineering teams (no coding required)

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.

What you’ll learn

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

  • Work from ten dimensions that cover responsible AI, from accuracy and safety to bias and privacy.

  • Prioritize the dimensions that matter most based on your product's actual failure modes.

  • Build a reusable failure map for an agent, chatbot, or RAG app, prioritizing each failure by impact and detectability.

  • Decide how the product responds to each failure, before a user hits it.

  • Analyze your AI’s trajectory to pinpoint failures, using a method applied live to a real agent and reusable on your own work.

  • Write the expected outcome that turns product intent into a testable target.

  • Build evals tied to real failures, with the pass/fail threshold set before your test data runs.

  • Use eval results to distinguish reliable performance from a lucky run and make the release call.

  • Re-run your evals on real production traffic, including multi-step agent traces.

  • Catch drift and feed new failures back into the failure map.

  • Detect quality changes caused by model updates or new user patterns before they affect customers.

Workshop agenda

  • Lesson 1: Map Failure Modes

    Identify where an agent, chatbot, or RAG app is most likely to fail, and prioritize those risks by impact.

  • Lesson 2: Define the Product Response

    Define how the product should handle each failure mode before it occurs in production.

  • Lesson 3: Build Reliable Evals

    An eval is a repeatable test of whether your AI did its job. You'll build evals tied to the failures you found, and learn to tell a result you can trust from one you can't.

  • Lesson 4: Make the Release Decision

    You'll decide whether your AI is ready to ship, using your eval results and clear release criteria.

  • Lesson 5: Monitor Quality After Launch

    Pull production traffic, re-run your evals, catch drift early, and feed new failures back into the failure map.

  • (Optional) Q&A with Ganesan

    A short share-out and open Q&A to help you take the method into your own work.

Learn directly from Ganesan

Ganesan Anand

Ganesan Anand

Contact

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

Adobe
Wells Fargo
eBay
HBS
See all products from Ganesan

Who this workshop is for

  • 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

Prerequisites

  • Model access is provided

    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.

  • Curiosity about AI quality

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

  • Stable internet

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

What's included

Ganesan Anand

Live sessions

Learn directly from Ganesan Anand in a real-time, interactive format.

What you'll leave with

Templates and frameworks for failure mapping, eval specs, pass/fail thresholds, release decisions, and production eval, built on a real example and ready to apply to your own work.

Community of peers

Stay accountable and share insights with like-minded professionals.

Certificate of completion

Share your new skills with your employer or on LinkedIn.

Access to monthly office hours (first 6 months)

Continuous learning: bring your evals and questions to live Q&A.

Maven Guarantee

Your purchase is backed by the Maven Guarantee.

Frequently asked questions

Maven for Teams

Reimbursement

Get your company to pay

Everything L&D needs: email template, receipts, and certificate of completion.

Get reimbursed

Team discount

Learn with your teammates

Save 20%+ when 2 or more teammates enroll in the same cohort.

Save 20%+ with a team

Private cohort

Run a cohort for your org

A dedicated cohort with a custom schedule and curriculum, tailored to your team.

Book a private cohort

$200

USD

Aug 5
·

12–3pm EDT

Enroll