What Aishwarya Naresh Reganti thinks about design
AI practitioner and researcher who has helped build more than 50 enterprise AI products at companies including OpenAI, Google, Amazon and Databricks; founder of LevelUp Labs and author of over 40 research papers.
Aishwarya Naresh Reganti did not write this page.
We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.
Filter design · Newest first
Only Aishwarya Naresh Reganti on design. See everyone on design
7 dated positions, 2026, in their own words. Our reading of what Aishwarya Naresh Reganti has said — not written or endorsed by them.
-
Their wordsAnd how well you build this harness layer itself can make a huge difference in the performance of your agentic AI systems. There's literally research showing that the exact same model performs up to six times better by simply building a better harness system around the agent.
↗2,000+ Hours of Learning Harness Engineering in 18 Minutesyoutube.com 3rd of 7 in this recording
-
Their wordsDifferent employees should have different access and some actions should require approval even before they happen. So all of that should be enforced in the harness.
↗2,000+ Hours of Learning Harness Engineering in 18 Minutesyoutube.com 4th of 7 in this recording
- 7 days earlier
-
Their wordsremember that you need to understand the scope of the problem very well before going into solutioning. A lot of people get confused in this, but a huge part of system design is simply scoping the problem and making your assumptions explicit.
↗2,000+ Hours of Learning Agentic AI System Design in 20 Minutesyoutube.com 2nd of 15 in this recording
-
Their wordsAnd if you're answering a system design interview question, this is where you want to ask your interviewer as many questions as possible, because the more assumptions you make up front, the better your system design or your architecture design will get.
↗2,000+ Hours of Learning Agentic AI System Design in 20 Minutesyoutube.com 3rd of 15 in this recording
-
Their wordsIf our evals later show that many questions actually need information across several documents, then we can revisit that decision, but do not overcomplicate your solution.
↗2,000+ Hours of Learning Agentic AI System Design in 20 Minutesyoutube.com 4th of 15 in this recording
-
Their wordsbecause that's where interviews are really looking for signal as to how well you can understand different design decisions and make architecture tradeoffs. Now, that layer is what separates your great candidates from good candidates.
↗2,000+ Hours of Learning Agentic AI System Design in 20 Minutesyoutube.com 12th of 15 in this recording
-
Their wordsAnd this is pretty much what interviewers are looking for, not someone who says at the first shot that they'll use a multi-agent system. Every complexity has to be earned, and you need to explain why you made those decisions.
↗2,000+ Hours of Learning Agentic AI System Design in 20 Minutesyoutube.com 15th of 15 in this recording