I Spent Two Years Building the Median — Hariprasad Sudharshan
Source
youtube.com
Author
AI Engineer
Date
Why it matters
Coding agents make it easy to rebuild what already exists. Naming the one distinctive element before starting, and asking who already solved the problem, helps you avoid shipping a median product.
Key takeaways · AI-distilled
Sudharshan describes a 'build first reflex': opening a coding AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → immediately instead of searching for existing solutions. After two years of solo work he found others had independently built calculators much like his.
He separates three layers often conflated in demos: the model's capability, the agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → around it, and the product a customer actually receives. A working demo, he argues, does not establish a durable advantage.
His three questions for leaders evaluating demos: Who has already solved this? What does this team have that a competitor does not? Where will the application reach users? The talk is a personal reflection, not a study of product outcomes.
Terms in this piece · Glossary
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
videoPaving the Road to Production: Governed Enterprise AI Agents — Harish Gaggar, Credit Karma
videoYour AI Isn’t the Problem. Your Infrastructure Is. — Jiachen Jiang, Coder
videoHow to Actually Tokenmaxx and Save Millions — Alvin Pane, OutRival
videoRebuilding CI for AI-Scale Commit Volume — Gautam Korlam, SonarSource
videoPrototyping as Leadership: How a CTO Ships with AI Agents — Hursh Agrawal, The Browser CompanyAI Engineer
videoThe Signal Layer: What to Build When Anything Can Be Built — Lena Hall, AkamaiAI Engineer
videoHarness Engineering is not Enough: Why Software Factories Fail — Dex Horthy, HumanLayerAI Engineer