Anil Prasad

28 years building production AI/ML at Fortune 100 scale. Founder @AmbhariiLabs. Head of Engineering & Product @DukeEnergy. I write about what actually breaks in regulated AI deployments.

Closter, NJ · New York Metro Joined on Mar 25, 2026 https://ambharii.com

Education

Stanford University · BITS Pilani

Pronouns

He/Him

Work

Head of Engineering & Product · Duke Energy

Cover image for The week the agent capability inflection arrived. And what to do about the 86% that still fail.

Anil Prasad

May 2

The week the agent capability inflection arrived. And what to do about the 86% that still fail.

#ai #agents #machinelearning #aiops

6 min read

Cover image for The week AI capability outpaced readiness. Again. Here is what it means in production.

Anil Prasad

Apr 24

The week AI capability outpaced readiness. Again. Here is what it means in production.

#ai #argus #genomixiq #ariarcm

5 min read

Cover image for I Built the First Agentic AI Platform for Clinical Genomics. Here Is the Full Architecture

Anil Prasad

Apr 18

I Built the First Agentic AI Platform for Clinical Genomics. Here Is the Full Architecture

#agentaichallenge #genomics #healthtech #ai

7 min read

Cover image for I Built 11 Autonomous Agents for Healthcare Revenue Cycle. Here Is the Full Architecture.

Anil Prasad

Apr 10

I Built 11 Autonomous Agents for Healthcare Revenue Cycle. Here Is the Full Architecture.

#ai #python #machinelearning #healthcare

9 min read

Cover image for Building Multi-Agent Systems That Don't Collapse in Production

Anil Prasad

Apr 8

Building Multi-Agent Systems That Don't Collapse in Production

#ai #agentaichallenge #machinelearning #powerplatform

5 min read

Cover image for How I Built a Self-Correcting Multi-Agent System for Healthcare - and Why Standard ML Metrics Failed Me

Anil Prasad

Apr 7

How I Built a Self-Correcting Multi-Agent System for Healthcare - and Why Standard ML Metrics Failed Me

#ai #python #machinelearning #healthcare

9 min read

Cover image for 78% of PyTorch Models Never Reach Production. I Built the Fix.

Anil Prasad

Apr 4

78% of PyTorch Models Never Reach Production. I Built the Fix.

#pytorch #mlops #opensource #python

6 min read

Cover image for I open sourced a production MLOps pipeline. Here is what it took to get it to PyPI and Hugging Face in one day.

Anil Prasad

Apr 2

I open sourced a production MLOps pipeline. Here is what it took to get it to PyPI and Hugging Face in one day.

#mlops #python #opensource #machinelearning

4 min read

Cover image for argus-llm is now on PyPI — production LLM observability in one pip install

Anil Prasad

Mar 28

argus-llm is now on PyPI — production LLM observability in one pip install

#llm #ai #machinelearning #aiobservability

1 min read

Anil Prasad

Mar 25

OpenTelemetry Traces Your LLM. It Does Not Fix It.

#llm #observability #opensource #ai

3 min read

Forem

Anil Prasad

Badges

Writing Debut

Skills/Languages

Currently learning

Currently hacking on

Available for

The week the agent capability inflection arrived. And what to do about the 86% that still fail.

The week AI capability outpaced readiness. Again. Here is what it means in production.

I Built the First Agentic AI Platform for Clinical Genomics. Here Is the Full Architecture

I Built 11 Autonomous Agents for Healthcare Revenue Cycle. Here Is the Full Architecture.

Building Multi-Agent Systems That Don't Collapse in Production

How I Built a Self-Correcting Multi-Agent System for Healthcare - and Why Standard ML Metrics Failed Me

78% of PyTorch Models Never Reach Production. I Built the Fix.

I open sourced a production MLOps pipeline. Here is what it took to get it to PyPI and Hugging Face in one day.

argus-llm is now on PyPI — production LLM observability in one pip install

OpenTelemetry Traces Your LLM. It Does Not Fix It.