Problem-First AI

March 2025 Cohort

May 2025 Cohort

July 2025 Cohort

Self-paced Cohort

Oct 2025 Cohort

Download a list of over 50 capstone projects from our course with full end-to-end architecture designs, demo video, iterations, evaluations, guardrails, and more across enterprise verticals like healthcare, finance, education, real estate, retail, and legal.

Capstone Projects Showcase

Access our curated collection of top reading materials, roadmaps, research papers, and more!

Our Curated Generative AI Free-Resource Bundle

Learn to make decisions tailored to business constraints, understand when & how to apply AI effectively & build a multi-agent application

Aishwarya Naresh Reganti

Tech Lead | Lecturer | Advisor | Researcher | Speaker | Investor

Kiriti Badam

Member of Technical Staff @ OpenAI | AI Advisor | Ex-Google

Building Agentic AI Applications with a Problem-First Approach

Assistant Vice President 

Partner

Principal Architect

Senior Manager, Software Engineering

Senior Software Engineer

Senior Software Engineer in Search

Senior Product Manager

Yes, we teach RAG, evals, agents, MCP, multi-agents, context engineering, and all that jazz. But always as tools to solve a business problem. If you want a checklist of hype items without knowing when or why to use them, please don’t join our course. :) 🚨🚨Notes:- For current offers/promotions check out the FAQs section below-We follow a flipped-classroom format. All lectures are pre-recorded so folks can go at their own pace, but we’ll still meet 5 times a week for office hours and live sessions. The course includes 35+ hours of live time. Check schedule below- For questions or bulk requests, reach out to: problemfirst.ai@gmail.com- October will be our final cohort. We don’t plan to run this course in 2026, it’s simply gotten too hectic. As much as we love teaching AI, we love building enterprise AI systems a bit more. So if you’ve been considering it, this is your last chance to join.- This course is an independent offering and is not affiliated with, endorsed by, or related to the instructors' current or past employers. ⛳&nbsp;The only prerequisite: you should have coded at least once in your life. The course includes low-code assignments, and even folks who hadn’t touched code in over 15 years have found it approachable and rewarding. That said, a basic understanding of coding really helps you get the most out of it — and of course, there’s AI to assist you along the way. The course is built for everyone, whether you’re a Product Manager, Architect, Director, C-suite leader, or someone seriously exploring agentic AI. Agentic AI or AI systems capable of operating with some degree of autonomy, is transforming how we interact with technology. In the coming years, most software systems will integrate AI agents to enhance their capabilities. This shift will drive a growing demand for professionals who can move beyond surface-level understanding and apply AI effectively to solve real business challenges while navigating practical constraints. This course focuses on practical AI agent development, covering key agentic design and usage paradigms. Instead of just explaining what these techniques are, we focus on when and how to use them, so you're equipped to make informed, business-driven AI decisions. What You'll Learn All core content is pre-recorded so students can focus on two-way interaction. Lectures are watched asynchronously, and we host four office hours each week for questions and brainstorming Week 1 (Let’s get you to understand what problem-first means)Decode why agentic AI breaks traditional software assumptionsFrame hallucinations, latency, and prompt brittleness through the determinism spectrumOpen vs. closed models: tradeoffs across compliance, latency, and costProblem-first, evaluation-driven design using early datasets and proxy metricsDeconstruct a production-grade use case and redesign it across progressive system versions Week 2 (Prompt engineering is still the core part of agents, do it smarter with right evals)Break down the evolution from zero-shot prompts to self-optimizing modelsMaster context engineering: Decomposition, meta-prompts, algorithmic optimizationAnalyze when to use prompting-only systems based on task, cost, and latencyCompare model-level strategies: reasoning vs. regular, and when each makes senseAdd guardrails and evaluation layers using LLM judges, semantic scoring, and offline tests Week 3 (RAG is not dead, it’s in fact the basis of self-improving agents)Address statelessness via dynamic retrieval and memory-backed context injectionBuild robust RAG pipelines with advanced chunking, embedding selection, and retrieval methodsExplore GraphRAG, Agentic RAG and multimodal RAG and other advanced methods and learn tradeoffsArchitect episodic, semantic, procedural, and working memory layers for self-reflective agent behavior Week 4 (MCP from an enterprise lens and multi-agents + Fine-Tuning)Understand planning autonomy in agents and how dynamic tool use and multi-turn reasoning go beyond static workflowsCompare agent levels and their control dimensions: action, planning, evolution, and physical autonomyExplore MCP (Model Context Protocol) and A2A as emerging agent-tool communication standardsInvestigate critical security challenges in MCP and A2A. Understand how guardrails, tool signing, audit trails improve reliabilityAnalyze coordination patterns in multi-agent systems, including shared memory governance, state sync, AI collusion risks, evaluation, logging, and observabilityExplore fine-tuning levers (SFT, RLHF, PEFT etc.), compare with RAG, and determine when to shift from context injection to model adaptation Week 5–6 (Put it all together in a capstone)Work in groups of 6Take a business problem and design/implement a solutionDemo to 4000+ public attendees including leaders, VCs, and hiring managers Homeworks: You'll supplement your learning by building an agentic search system (Perplexity like) in 3 iterations with the final iteration using agentic RAG, MCP and multi-agents. You can choose between low-code/code routes to complete assignments. ---- ❌ Who This Course Is Not For For Those Who Have Already Deployed Gen AI in Enterprise: This course is designed as an applied foundations course for enterprise AI with only basic Python as a prerequisite and no ML background required. If you’re already familiar with deploying AI systems, you won’t gain much from the core content. However, if you're looking to network and refine best practices, you're welcome to join. Those Seeking Heavy Theoretical Knowledge: This course emphasizes applied learning and practical problem-solving, not deep dives into theoretical topics like transformer architecture, pre/post-training optimization, inference techniques, or alignment. Those Who Have Never Coded Before: While we provide low-code options, this course assumes you have some coding experience. It’s not suitable for those who have never written or worked with even basic code. Individuals Expecting Deep AI Research Focus: While we’ll cover cutting-edge techniques, this course is centered on applying AI to business problems, not research-heavy exploration. Scaling and Ops Enthusiasts: This course does not focus heavily on scaling or operational aspects (i.e., LLMOps). Deployment will be covered at a high level, but not in-depth.

Design and build impactful agentic AI systems to solve business problems.

Course syllabus

You should have coded at least once in your life. The course includes low-code assignments, and even folks who hadn

The only prerequisite

We offer generous office hours to support you throughout the course, along with 24-hour help on Slack. Typical weekly schedule:<ul><li>Wednesdays at 10 am PT and Saturdays at 9 am PT: Assignment Support</li><li>Thursdays at 5 pm PT and Saturdays at 8 am PT: Content/Use-case discussions</li></ul>

Live Office Hours

Our weekly community discussion channel covers the latest trends in AI, industry updates, and all the unfiltered tea, open, casual, and freeform.

Chai & AI Sessions

We bring in industry experts to share proven insights and discuss real enterprise challenges

Guest Lectures

Course schedule

Software/AI Engineers, Strategists, Data Professionals, Solution Architects and Consultants who want to master AI system design

Business Leaders and Product Managers seeking to gain the technical understanding needed to make informed decisions &amp; lead AI initiatives

Entrepreneurs looking to understand common generative AI use cases and learn how to develop and implement AI-powered solutions

Who is this course for

What you’ll get out of this course

While most courses stop at teaching tools and frameworks, this course goes further by focusing on solving real-world business problems. You’ll tackle practical constraints like cost, scalability, latency, and performance, learning to design AI solutions tailored to real use cases

Solving Real Enterprise Challenges, Not Just Concepts 

While learning applied AI concepts, we’ll put them into action by building a Perplexity-like AI-powered search system through detailed, hands-on tutorials that demonstrate their practical application (Low code options will be provided)

Apply Concepts to Build an Agentic Search System

Learn how to connect cutting-edge research with real-world applications. For the capstone, you’ll use our curated list of the latest research papers to design and implement solutions for practical business use cases. Some of our capstones have received VC funding too. <a href="https://areganti.notion.site/Capstone-Projects-Problem-First-AI-1e0c91fa32368011b935e00a35d9bceb" rel="noopener noreferrer" target="_blank">Examples</a>

Capstone Project

Gain a deep understanding of key challenges in building AI systems, including handling hallucinations, adversarial attacks, security, privacy issues etc., and learn best practices to evaluate AI solutions comprehensively

Understand Challenges and Effective Evaluation
 

The course includes guest lectures from industry experts, AMA sessions, and our Chai &amp; AI discussions, culminating in a final in-person meetup in the Bay Area. You'll have plenty of opportunities to network and become part of our community.

Access to the Problem-First AI Community

#2 Designing Agentic AI Systems for Enterprise Use-Cases

AI Advisor, Founder, Ex-AWS

Applied AI Engineer, OpenAI, Ex-Google

Understand how to take an enterprise use-case, scope it and build solutions with state-of-the-art techniques

Watch 15+ Agentic AI Application Solutions

Use-cases include verticals like finance, real-estate, manufacturing, retail and more!

See Live Solutions For a Wide Range of Enterprise Verticals

What sets a good AI practitioner apart is their ability to work within business constraints. Watch it in real time!

Learn About Our Problem-First Framework

A 15% off coupon will be shared during the session and will be valid only until the session ends.

Get An Exclusive Discount On Our Next Cohort

Sign up for #1: https://maven.com/p/545da1/1-designing-agentic-ai-systems-for-enterprise-use-cases

🔔 Note: Projects are spread across 2 sessions

#1 Designing Agentic AI Systems for Enterprise Use-Cases

Aishwarya Reganti

Applied AI Engineer @ OpenAI, Ex-Google

Sign up for #2: https://maven.com/p/69f3e6/2-designing-agentic-ai-systems-for-enterprise-use-cases?utm_medium=ll_share_l

Don't Build AI Products Like Traditional Software

Founder @ LevelUp Labs | AI Advisor | Ex-AWS

Applied AI @ OpenAI | AI Advisor | Ex-Google

Traditional software behaves predictably. AI doesn’t. Learn how to build around the non-determinism

AI Products & Non-Determinism

Most enterprise teams rush into building autonomous agents, and fail. Learn how to think through the tradeoffs first.

Understanding the Agency/Control Tradeoff

CI/CD doesn't quite make the cut for AI products, learn about our new CC/CD framework!

CI/CD for AI Products

#3 Single vs. Multi-Agent AI Systems

AI Tech Lead | Advisor

Member of Technical Staff @ OpenAI | AI Advisor

We’ll break down what qualifies as multi-agent, common misconceptions, and the core coordination patterns they use.

What Multi-Agent Systems Are (And Aren’t)

Understand when multi-agent systems are helpful and when they can lead to unnecessary debugging overhead

When to Use One Agent vs Many

We’ll cover the real-world challenges: context sharing, memory, handoffs, failure handling etc.

Hidden Complexities in Multi-Agent Setups

#2 AI Protocols 101: What You Should Know About MCP, A2A etc

Tech Lead | AI Advisor

Get a clear picture of the protocol ecosystem (MCP, A2A, and others) and how they fit into the agentic AI stack.

The AI Protocol Landscape Today

See how enterprises are using these protocols today, and what to keep in mind around security, modularity & more

What Practitioners Need to Watch For

Know about current gaps that exist in the space and best enterprise practices while building

Best Practices w/ AI Protocols

#1 Building Agentic AI Applications 2025 (Q2 Updates)

Understand how the agentic AI landscape evolved this quarter across both cutting-edge research and real enterprise use.

2025 Q1 → Q2: What Shifted in Research and Enterprise

Get a quick overview of agent protocols, reasoning models, and self-improvement methods worth paying attention to.

New Trends to Watch

Get a forward-looking view of where agentic AI is headed next and what matters most if you’re building or deploying in t

What AI Practitioners Should Focus On Next

Integrating Agentic AI into Enterprise Architecture

Tech Lead @ AWS

Helen Yu

CEO @Tigon Advisory Corp

We’ll talk about what actually happens when agentic AI meets enterprise systems and why tech isn’t always the blocker

AI Integration Isn’t the Hard Part, It's the Alignment

You’ll walk away with a clearer lens on the real tradeoffs (cost, latency, control) and how to ask the right questions

The Build vs. Buy Debate

Most teams stall after the demo. We’ll cover what it takes to break out of PoC mode and start solving real problems with

From PoC to Production

Note: This lesson is hosted on LinkedIn Live

AI Advisor | Tech Lead

Applied AI Engineer @ Open AI | Advisor

Link to #1: https://maven.com/p/466e22/1-designing-agentic-ai-systems-for-enterprise-use-cases

Link to session 2: https://maven.com/p/a0cdf1/2-designing-agentic-ai-systems-for-enterprise-use-cases

AI Native Products: What Every PM Needs to Know (and Do)

Jyothi Nookula

Product Director @ Netflix

Vikash Rungta

Instructor @ Stanford Continuing Studies, Ex-Lead PM @ Meta

AI Tech Lead @ AWS

Applied AI Engineer @ OpenAI

How AI-native products differ from traditional ones, and why this distinction matters for product strategy

What makes a product AI-native

From prompting and evaluation to dealing with model unpredictability and setting up feedback loops.

New responsibilities for PMs in AI-first teams

How the PM role shifts and what it takes to bridge product and AI development effectively.

Problem-First AI

Problem-First AI

Courses

Lightning Lessons

Resources

Reviews