Tejas Kumar
Tejas Kumar is an AI Engineer at IBM in Berlin whose public work focuses on AI engineering, including large language models, retrieval-augmented generation, and multi-agent systems. He is also a conference speaker and author of Fluent React.
AI Evaluations Need Human Calibration Before They Can Gate Deployments
Tejas Kumar of IBM argues that AI evaluations should be treated as calibrated reliability checks, not as proof that a system works. In a customer-support example, a test passes an answer that wrongly approves a return because it contains the word “cannot”; an LLM judge can also mislead unless its verdicts are checked against human-labeled cases and the relevant policy. Kumar’s approach is to examine disagreements, refine the judge and dataset, and use measured agreement as a deployment gate.
A Harness Made GPT-3.5 Turbo’s Browser Agent Reliable Without Rewriting the Prompt
Tejas Kumar, an IBM engineer, argues that unreliable AI agents are often not suffering from bad prompts so much as missing harnesses: the deterministic software around a model that bounds its behavior, manages context, verifies outcomes, and handles known failure states. In his Hacker News browser-agent demo, GPT-3.5 Turbo falsely claimed it had upvoted a post after hitting a login wall; without changing the prompt, Kumar added guardrails, trace-based verification, and a programmatic login handler until the same model completed the task reliably.