University of Oxford

Amazon Web Services

Microsoft

Aishwarya & Kiriti

AI Founder & Advisor to F500s | Ex-AWS

Jan 2026

March 2025 Cohort

May 2025 Cohort

July 2025 Cohort

Self-paced Cohort

Oct 2025 Cohort

Hitachi Cohort

June Cohort

Cohort 1

April 2026 Cohort

Cohort 2

August 2026 Cohort

Our Free OpenClaw course + certification has been taken by 1000+ people! Check it out and attend our openhouse to build on top of those skills <ul><li><a href="https://maven.com/p/ddf4e5/open-claw-mastery-for-everyone-open-house" rel="noopener noreferrer" target="_blank">Session 1</a></li><li><a href="https://maven.com/p/da9448/open-claw-mastery-for-everyone-open-house" rel="noopener noreferrer" target="_blank">Session 2</a></li></ul>

Our Viral OpenClaw Certification

A comprehensive guide to evaluations and monitoring in AI systems. Learn systematic approaches that actually work in production.

AI Evals For Everyone Guidebook

An overview of the applied AI updates in 2025 and what to look forward to in 2026

State of Applied AI 2025 Report

Access our fully free and open-source AI evals course on Github, it'll give you a good high level overview of this course

AI Evals For Everyone Course

We put together a set of 90+ hand-curated FREE resources that cut through the noise. &nbsp;What you'll find: &nbsp;✅ 5 structured learning paths - from fundamentals to production deployment&nbsp;✅ 60+ project ideas categorized by difficulty (so you can build while learning)✅ 10 DeepLearning.AI short courses&nbsp;✅ Complete coding agents section - GitHub Copilot, Cursor, and moer!

Year End AI Resources Handbook

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

AI Founder | Lecturer | Advisor | Researcher 

Applied AI Lead  | Ex-Google

Kiriti Badam

Applied AI Lead | AI Advisor | Ex-Google

Building Agentic AI Applications with a Problem-First Approach

Sr Global Product Manager

Enterprise Software Deployment

AI Engineer

Head of Product

Distinguished Engineer, Solution Consulting

Data Engineer

Financial Analyst

Data manager

Sr Platform Engineer

Google

Samsung

Databricks

🚨 You can get our <a target="_blank" rel="noopener noreferrer nofollow" href="https://maven.com/aishwarya-kiriti/openclaw-bootcamp">Agent-Native Operator course</a> bundled with this course for 2700$ (3650$ value) only! Please use this checkout <a target="_blank" rel="noopener noreferrer nofollow" href="https://maven.com/aishwarya-kiriti/genai-system-design?promoCode=BUNDLE">link</a>!We teach all the the latest &amp; greatest skills, including context engineering, evals, agentic retrieval and RAG, multi agent systems, harness engineering, MCP, skills, fine tuning and more! but as part of a decision map for solving business problems, based on our experience building <a target="_blank" rel="noopener noreferrer nofollow" href="https://www.youtube.com/watch?v=z7T1pCxgvlA">50+ AI products</a>, not as a disconnected checklist.We focus on the why and the how, not just the what. If all you want is a checklist of topics, YouTube already has plenty of that.<ul><li>Check out out <a target="_blank" rel="noopener noreferrer nofollow" href="https://testimonial.to/building-agentic-ai-applications-with-a-problem-first-approach/all">wall of love</a> to see what our students think and to estimate the outcomes of the course, see our <a target="_blank" rel="noopener noreferrer nofollow" href="https://areganti.notion.site/Enterprise-AI-Projects-Showcase-25bc91fa3236804b8765e54dde771262">capstone showcase here</a>.</li><li>No hard prerequisites: We have hands on assignments for both, with no-code and code heavy options. Do check out our FAQs before signing up</li><li>If you're self-funding, Apply to our <a target="_blank" rel="noopener noreferrer nofollow" href="https://docs.google.com/forms/d/e/1FAIpQLSdcniF_jU5XA1jFR1PYt-2e6jGsdfjN44z8rkjayPBtirTDlA/viewform">scholarship program</a> (Reduced Price: $1750)</li><li>We follow a flipped classroom format with 35+ hours of live time</li></ul>This course is an independent offering and is not affiliated with the instructors' employers.Contact: problemfirst.ai@gmail.com

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

Develop a Problem-First AI Intuition For Enterprise Use Cases

Build an Evals Driven Mindset & Iterative Design

Master Practical Prompt and Context Engineering

Build and Optimize Agentic Pipelines

Apply Everything in a Real-World Capstone

A willingness to work with a few basic terminal commands. The course does include a no code assignment track, but does require a small setup

The only prerequisite

Software/AI Engineers, Strategists, Data/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

Evals aren't your product moat. A continuous improvement flywheel is.

Check out our free AI Evals Certification <a target="_blank" rel="noopener noreferrer nofollow" href="https://github.com/aishwaryanr/awesome-generative-ai-guide/blob/main/free_courses/ai_evals_for_everyone/README.md">here</a> (5000+) Learners!Most teams building AI products today know about evals and LLM judges, but they’re deeply confused about how to actually turn them into actionable improvement signals post production. Just throwing in LLM judges won’t magically fix your product. It won’t.<ul><li>This course shows how to use offline evals, online evals, and production monitoring to drive continuous improvement, based on real production experience.</li><li>We believe that going forward, a thoughtfully designed data flywheel will be the moat for AI applications. This course shows you how to build it.</li><li>This course is for people who’ve already built AI systems and are stuck with evals that are noisy, expensive, or uselessIf you need something more foundational, check out our top-rated flagship<a target="_blank" rel="noopener noreferrer nofollow" href="https://maven.com/aishwarya-kiriti/genai-system-design"> enterprise AI course</a> taken by over 1500+ builders and leaders.</li><li>For questions or bulk enrollments please email problemfirst.ai@gmail.com</li><li>We follow a flipped-classroom format with async lecture content and meet twice a week for office hour style sessions to optimize two-way/interactive live time.</li></ul>

Move beyond one-time evals to continuous improvement flywheels for AI products

Understand what evals actually mean and why it’s misunderstood

Build a pre-deployment evaluation foundation from scratch

Choose the right types of metrics for the system you’re building

Monitor in production and close the improvement loop

You should have built small AI applications before and be familiar with concepts like RAG, MCP, and tool use.

A good understanding of AI system design

The course includes optional Python assignments, you're free to use coding agents, but basic coding skills are recommended

Working knowledge of Python/Coding (Optional)

Software/AI Engineers, Strategists, Data Professionals, Solution Architects and Consultants looking for systematic evaluation practices

Business Leaders and Product Managers seeking to gain the technical understanding of AI Product Lifecycle and intentional iteration

Founders &amp; teams stuck at systematic evaluations and monitoring, unsure how to turn signals into real product improvements.

About This Resource

Fully free & open-source 10 -day OpenClaw course + Certification

Applied AI at OpenAI | Ex-Google

OpenClaw Mastery For Everyone (10-day  Course)

About

AI Product Architecture Audit

Build reliable workflows with agent harnesses like Codex, OpenClaw & Claude Code

Applied AI Lead | Ex-Google

Learn more in 1 day than what you'll usually spend MONTHS figuring out by yourself!!🚨Get this workshop with our <a target="_blank" rel="noopener noreferrer nofollow" href="https://maven.com/aishwarya-kiriti/genai-system-design?promoCode=BUNDLE">flagship course</a>!There are tons of tutorials online on how to build automations with agents, but almost none of them show what to automate for "your" use case. Most of them focus on the tooling, not the thinking needed to make it work for you.This bootcamp teaches the operating layer above the tools:• How to identify productivity and workflow use cases that are actually worth handing to agents • When and how to set up skills, MCPs, memory, scheduled triggers, and event driven workflows • How to build self healing eval loops so agents can check their own work before you ever see the output • How to design minimum exposure, guardrail first setups so you're less susceptible to prompt injection, data leaks, or security breaches • How to progressively increase autonomy, multiple agents, and design handoffs so the system scales.We've worked with tools like Claude Code, Codex &amp; OpenClaw for hundreds of hours. What we've distilled is tool-agnostic, role-agnostic, and designed to work regardless of which harness you use today or next month.

Opening files and directories, using websites to obtain API keys etc. No coding background needed

Basic Computer Usage Knowledge

The patience to make things work, the grit to deal with errors, and the willingness to keep learning and improving.

Patience & Grit

Product managers who use AI daily but get one-off outputs instead of repeatable systems.

Engineers and technical leads who want the evaluation and iteration mindset for scaling agent workflows

Founders and solo operators who need more output from fewer people

OpenClaw Mastery For Everyone (Open-house)!

Aishwarya Reganti

AI Advisor, Founder, Ex-AWS

Applied AI Lead | Ex-Google, Samsung

Learn how to host Openclaw at as less as 25$/month

Setup your claw in a security first manner to tackle your inbox

Setup up workflows to triage and send emails

Setup multi-agent systems on OpenClaw

github.com/aishwaryanr/awesome-generative-ai-guide/blob/main/free_courses/openclaw_mastery_for_everyone/README.md

Course link

Prototype to Production with v0 for PMs

Ary Khandelwal

1st Product Manager, v0 at Vercel

Turn a PRD into a deployed app in v0. Go from spec to live product with no handoffs or security gaps.

Ship a production feature without writing code

Import your team's repo, make changes, and submit pull requests yourself, all from v0.

Open PRs directly from your product spec

Those "quick fixes" deprioritized for months? Ship them to production yourself, no engineering queue.

Ship the features stuck in your backlog

Pull context from Notion, Granola, Linear, and more. Ship features informed by your actual specs and research.

Connect v0 to your PM stack with MCPs

#2 Designing Agentic AI Systems for Enterprise Use-Cases

Understand how to take an enterprise use-case, scope it and build solutions w

Watch 20+ 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 25% 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

#1 Designing Agentic AI Systems for Enterprise Use-Cases

Evals in Action With Arize

Laurie Voss

Head of DevRel at Arize, co-founder, npm Inc

Write an eval that detects hallucinations in <10 minutes using Arize Phoenix's templates and your own custom criteria.

Build your first LLM-as-a-Judge evaluator

Add observability to any LLM application so you can see exactly what's happening at every step, from input to output.

Trace your AI system end-to-end

Learn when to use code-based checks, LLM judges, or human annotations based on what you're trying to catch.

Aishwarya & Kiriti will make you a problem-first AI builder