Kiriti & Aish

Kiriti & Aish

40.7K Subscribers

AI Founder & Advisor to F500s | Ex-AWS

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

Contact

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

Aish Reganti is the founder and CEO of LevelUp Labs, a human-first AI startup that helps develop and deploy production-ready generative AI solutions for mid to large enterprise clients. With over 10 years of experience in machine learning, she has published more than 40 research papers at top-tier AI conferences, including NeurIPS, AAAI, and CVPR.

Kiriti Badam is a member of the technical staff at OpenAI Codex, with over a decade of experience designing high-impact enterprise AI systems. He specializes in AI-centric infrastructure, with deep expertise in large-scale compute, data engineering, and storage systems.

Worked/Taught At
MIT
University of Oxford
Amazon Web Services
Microsoft

Alumni reviews

Ryan

Live cohort
Directory, Software Engineering · BrainCorp

Harness Engineering: Designing the Operating Layer for Reliable Agents

This course is jam-packed with content, all extremely relevant for building a harness today. With all the hype around harnesses, this class adds structure, depth, and clarity to each of the components in a harness. Aish and Kitiri provide homework, allowing you to get your hands dirty and apply what you've learned. Great course all-around.

Edgar

Live cohort
Associate Director - Digital Transformation · Cogent IBS

Harness Engineering: Designing the Operating Layer for Reliable Agents

Overall the course was a fantastic experience. Understanding when and how we gain value at working at the harness level helped me gain a lot of confidence while working with more advanced agents. As other courses from Aish and Kiriti, would recommend 100% :)

Abhi K

Live cohort
VP Agentic AI solutioning · Persistent

Harness Engineering: Designing the Operating Layer for Reliable Agents

This course provided a practical and structured view of what it takes to build enterprise-grade AI systems. Beyond the models themselves, the focus on agent loops, context management, subagent orchestration, memory, and governance highlighted the key engineering decisions that drive successful AI implementations. I particularly appreciated the balance between technical concepts and real-world applicability. The content has strengthened my understanding of agentic architectures and will help me better evaluate, position, and design AI solutions that can scale within complex business environments. Thank you Kiriti & Aish !

Sahana

Live cohort
Software engineer · Wayve

Harness Engineering: Designing the Operating Layer for Reliable Agents

I honestly walked into the course hoping to get better at using Codex, Claude Code, and other coding agents. Thanks to Kirti and Aish's first-principles approach to harness engineering, I walked away with real knowledge and curiosity about how Codex and Claude Code are actually built, and how I can build the features I want myself. Even the smaller things stuck, reinforced through the assignments: playing to a tool's strengths, like having coding agents write code directly instead of reasoning its way to the output, reinforces the first-principles thinking rather than just being a tip. It's rare to make state-of-the-art tools feel this accessible, replacing that overwhelmed feeling with genuine curiosity. It's consistently surprising how Level Labs keeps delivering that.

Akash

Live cohort
Senior Solutions Architect · Gulf Business Machines

Harness Engineering: Designing the Operating Layer for Reliable Agents

Harness engineering is a rare skill. This course teaches it while giving you a durable way to think about harnesses. Not just tools, but the system around the model. Kiriti is very responsive and teaches in the most simplified, effective way I’ve seen. Totally recommend this intense two-week course.