Featured in
Lenny’s List
Building Agentic AI Applications with a Problem-First Approach
Aishwarya Naresh Reganti
AI Advisor & Founder to F500s | Ex AWS
Kiriti Badam
Applied AI @ OpenAI | Ex-Google
This course is popular
13 people enrolled last week.
Design and build impactful agentic AI systems to solve business problems.
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
Check out our student capstones here
We follow a flipped-classroom format. All lectures are pre-recorded so folks can go at their own pace, but we’ll still meet 3 times a week for office hours and live sessions. Check schedule below for more details
For questions or bulk requests, reach out to: problemfirst.ai@gmail.com
This course is an independent offering and is not affiliated with, endorsed by, or related to the instructors' current or past employers.
What you’ll learn
Learn to make decisions tailored to business constraints, understand when & how to apply AI effectively & build a multi-agent application
Identify where agentic AI can add value by reframing business challenges through a systems lens
Understand why traditional software assumptions fail in AI-driven environments
Evaluate tradeoffs between model choices, latency, performance and cost
Learn to frame AI problems through measurable outcomes rather than features or model choices
Understand how evaluation acts as the backbone of reliable agentic systems
Identify and quantify failure modes early using proxy metrics and iterative testing
Design smarter prompts using decomposition, meta-prompts, and algorithmic optimization
Compare reasoning and non-reasoning models for different business tasks
Implement evaluation and guardrail techniques using LLM judges and semantic scoring
Integrate retrieval, memory, and self-reflective behavior in agentic systems
Balance tradeoffs between accuracy, latency, and adaptability in agentic systems
Analyze multi-agent coordination patterns and challenges & learn about protocols like MCP/A2A
Work in small teams to design and implement an end-to-end agentic AI solution for a real business problem
Build an agentic search system across three iterations, integrating RAG, MCP, and multi-agent components
Present your final project to 2000+ attendees including enterprise leaders, investors, and hiring managers
Who this course is for
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 & lead AI initiative
Entrepreneurs looking to understand common generative AI use cases and learn how to develop and implement AI-powered solutions
Prerequisites
The only prerequisite
You should have coded at least once in your life. The course includes no-code assignments but some knowledge of code helps!
What's included
Live sessions
Learn directly from Aishwarya Naresh Reganti & Kiriti Badam in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
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.
Maven Guarantee
This course is backed by the Maven Guarantee. Students are eligible for a full refund up until the halfway point of the course.
Syllabus
14 live sessions • 81 lessons
Week 1
Week 2
Feb
7
Week 1 Content Office Hours
Feb
7
Week 1 Homework Office Hours
Feb
8
Chai & AI Session (Not Recorded)
Week 2: Prompt Engineering in 2025 & Building Workflow Agents For The Enterprise
[Build] Assignment 1: Build Your v0 Agentic Search System
Free lesson
.png&w=768&q=75)
Building Agentic AI Applications in 2025
What is Agentic AI, and how is it evolving in 2025?
Get up to speed on the latest updates—reasoning models, hybrid models, MCP, and more.
Using Agentic AI and Iterative Design in the Enterprise
Enterprise use cases need an iterative approach to autonomous agents. Learn design patterns and steps.
Best practices to follow and common pitfalls to avoid.
Learn how to build traceable, evaluable, and explainable agentic AI applications.
Schedule
Live sessions
3 hrs / week
Sat, Jan 31
5:00 PM—6:00 PM (UTC)
Sat, Feb 7
5:00 PM—6:00 PM (UTC)
Sat, Feb 7
6:00 PM—7:00 PM (UTC)
Projects
3 hrs / week
Async content
4 hrs / week
Success stories
- I'm loving the course. I considered myself an AI business expert, yet I'm learning so much and filling gaps I didn’t even realize I had!
Nadia V Gill
Senior Vice President of Strategy (AI), Hitachi Digital - Hands, down this is an excellent course - both in terms of pacing, coverage of the materials and technical depth. Aish has an extraordinary ability to take complex concepts and deliver it elegantly without oversimplifying. I teach gen AI for marketers and I know how hard this is so i appreciate the work put into this!
Karla Congson
CEO, Agentiiv.com - you are doing a great job with the course! Balancing the right level of pacing and content can be challenging, but Aish & Kiriti areable find that line.
Rick Somra
Senior Software Engineer, Clear Aspect Solutions - I can see the amount of effort that you have put into putting this together. It is well constructed love the depth at which things are being discussed. You have the perfect balance between gleaming at a surface level and explaining things at a ML level which might be hard for people to follow.
Govind Manoharan
Technical Architect, SapientRazorfish - I’m learning a lot, and what stands out the most for me is Aish’s ability to curate extensive material into concise, well-structured slides, along with Kiriti’s demos that bring those concepts to life. Given the six-week duration, the content is crisp, easy to grasp, and aligns well with the course objectives.
Ravi Nukala
Senior Director of Engineering, BlackLine - The course structure is thoughtfully designed, with bite-sized weekly lessons that are engaging and easy to absorb. It takes an enterprise and industry-specific approach to qualifying agentic AI solutions for real-world problems. I especially appreciated the flexibility to dive deep into technical aspects while still covering the basics
Milli Comstock
Gen AI Digital Strategy Leader, Hitachi Energy
What makes our course the most holistic Applied AI program out there?
.png&w=1536&q=75)
LinkedIn Shoutouts From Past Cohort Members!
.png&w=1536&q=75)
Other praise on assignments/lectures
.png&w=1536&q=75)
Our alumni come from
.png&w=1536&q=75)
Frequently asked questions
❌This course is not for:
Those who have already deployed GenAI systems in production and want advanced scaling or optimization content
Individuals looking for deep theoretical or research-heavy discussions (e.g., transformer internals, pretraining, or alignment math)
Participants who have never written or worked with code before, even at a basic level
Learners expecting detailed coverage of LLMOps, infrastructure, or large-scale deployment practices