Staging environment

How Product Teams Should Think About Multi-Agent Systems

Hosted by Aki Wijesundara, PhD and Manu Jayawardana

Share this lesson

Go deeper with a course

Designing Multi-Agent AI Systems
Aki Wijesundara, PhD and Manu Jayawardana
View syllabus

What you'll learn

What multi-agent systems actually are (in product terms)

Move beyond hype and understand agents as coordinated roles, not magic autonomy.

When multi-agent systems make sense and when they don’t

Identify product scenarios where multiple agents add real value versus unnecessary complexity.

Common product failures with multi-agent setups

Learn why many agent demos break in production (handoffs, loops, cost, and evaluation gaps).

How to design agent roles and boundaries

Define responsibilities, inputs, and outputs so agents stay predictable and testable.

How to evaluate multi-agent behavior as a product team

Think in terms of outcomes, reliability, and UX - not model internals.

Why this topic matters

Multi-agent systems are rapidly becoming a default pattern in AI demos, but most product teams adopt them without clear ownership, evaluation criteria, or user impact in mind. This session helps product teams reason about multi-agent design at the product level, focusing on user experience, reliability, and cost, before committing engineering resources.

You'll learn from

Aki Wijesundara, PhD

AI Founder | Educator | Google AI Accelerator Alum

Aki Wijesundara is an AI leader with a PhD in Machine Learning and extensive experience mentoring startups at Google’s AI Accelerator. With a career spanning both research and applied AI, Aki has taught 5,000+ students worldwide how to design and deploy production-ready AI systems.

He has worked across cutting-edge areas of applied AI, from LangChain and RAG pipelines to observability and large-scale deployment. As a researcher and educator, Aki bridges the gap between theory and practice, making complex systems approachable and actionable for engineers, founders, and product leaders.

Aki is also a frequent speaker and advisor to organizations adopting AI, helping them transition from experimentation to production at scale.

Career highlights

  • Ex–Google AI Accelerator researcher focused on responsible AI and applied ML.
  • PhD in AI & Cognitive Systems with published research across top universities.
  • Former researcher with teams affiliated with MIT, University of Oxford, & King’s College London.
  • Co-founder of Snapdrum — delivered AI systems for finance, education, and healthcare.
  • Built and deployed AI product pipelines used by PMs, startups, and enterprise teams.
  • Instructor for multiple AI builder programs, helping 500+ professionals ship AI features fast.


Manu Jayawardana

Exited AI Founder (Rise AI: 35k Users) | Co-Founder of Krybe and Snapdrum.com

Manu Jayawardana is a serial entrepreneur with multiple AI startup successes. He exited Rise AI, a fintech app with over 35,000 users, to a private investor, demonstrating his ability to build and scale impactful products.

He is also the Co-Founder of Snapdrum, an AI consultancy helping companies integrate and automate their businesses using AI. Through Snapdrum, Manu has worked with top startups and enterprises across the U.S., Europe, and Asia, advising on automation, product development, and AI strategy.

Currently, Manu is the Co-Founder & CEO of Krybe, an AI voice agent startup in London transforming how businesses automate customer interactions. His experience spans fundraising, scaling products, and leading teams to deliver production-grade AI solutions adopted globally.

Career highlights

  • Co-Founder of Snapdrum — builds production-ready AI systems for Fortune 500s, YC startups, and global Series A–C companies.
  • Exited Founder of Rise AI — created an AI investment copilot used by 35,000+ users worldwide.
  • Co-Founder of Krybe — ultra-realistic voice AI platform with 1000+ users and part of the NVIDIA Inception Program.
  • Creator of the #1 ranked Investment GPT on the OpenAI Store with 30,000+ users.
  • Built and scaled 10+ companies across AI, SaaS, analytics, and EdTech, including a B2B analytics product that grew 10× in one year.
  • Former Entrepreneur First Unlock Fellow, selected for high-potential AI founders.


Previous Students from

Google
Meta
Boston Consulting Group (BCG)
NVIDIA
OpenAI

Watch this lesson for free

By continuing, you agree to Maven's Terms and Privacy Policy.