Skip to content
View agstya's full-sized avatar
4 followers · 9 following

Achievements

Achievement: Pull SharkAchievement: YOLO

Achievements

Achievement: Pull SharkAchievement: YOLO

Highlights

  • Pro

Block or report agstya

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
agstya/README.md

Agastya Kommanamanchi — Forward-Deployed AI Engineering Leader. AI, Data, Cloud.

Building AI systems that move from ambition to adoption.

Forward-Deployed AI Engineer at Deloitte · Enterprise Solutions Architect · Builder
10+ years turning complex AI, data, and cloud opportunities into secure production platforms.

Enter the portfolio Connect on LinkedIn

↑ The cover and portfolio button both open the complete interactive experience.

Where strategy meets the build

I lead production AI, data, and cloud initiatives from opportunity shaping and executive alignment through architecture, engineering, and adoption. My work spans agentic systems, identity-aware retrieval, enterprise copilots, cloud data platforms, and responsible AI delivery—especially in regulated environments where reliability matters.

I enjoy the hard middle: balancing value, scalability, security, and delivery risk while keeping teams focused on measurable outcomes.

Impact in production

95%+ 40% 25% $1.2M
AI task success lower latency lower inference cost annual cloud savings
$4.5M 50M+ 10TB 200+
recovery supported users served telemetry processed daily engineers enabled

Selected systems

System What shipped Measured outcome
Enterprise underwriting intelligence Secure agentic assistants with identity-aware retrieval, evaluation, and production controls 95%+ task success · 40% lower latency · 25% lower inference cost
Customer 360 intelligence platform Real-time and batch customer, meter, and operational data on AWS with embedded predictive outputs 12% better retention · $4.5M recovery supported
Multi-cloud FinOps platform Cost visibility, anomaly detection, and automated infrastructure controls across AWS and Google Cloud 200+ engineers enabled · $1.2M annual savings
Behavioral intelligence at scale Recommendation, telemetry, and experimentation systems processing more than 10TB daily 50M+ users · 25% longer sessions · 14% higher CTR

Explore the full case studies →

Systems-level toolkit

AI engineering

RAG AI Agents Context Engineering Evaluation Guardrails MCP

Platforms & data

AWS Google Cloud Databricks Snowflake Apache Spark Kubernetes Terraform

Architecture & delivery

Microservices · Event-driven systems · APIs · MLOps / LLMOps · Security & governance · Solution shaping · Executive alignment

Granted patent

US 12,518,057 B2 — System and method for a generative artificial intelligence model gateway
A secure enterprise AI gateway for sensitive-data evaluation, governed access to approved language models, and managed interaction with model outputs. Granted January 6, 2026.

Credentials  ·  Writing & visualizations  ·  Open source lab  ·  Contact

Have an ambitious AI problem?

Let's turn it into a system that ships.

Explore agstya.github.io Start a conversation by email

LinkedIn  ·  DEV  ·  Tableau  ·  Credly

Designed for clarity. Engineered for impact.

Popular repositories Loading

  1. ag2 ag2 Public

    Forked from ag2ai/ag2

    AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/pAbnFJrkgZ

    Python 1

  2. Lambda-MCP-Server Lambda-MCP-Server Public

    Forked from mikegc-aws/Lambda-MCP-Server

    Creates a simple MCP tool server with "streaming" HTTP.

    Python 1

  3. agstya agstya Public

    Config files for my GitHub profile.

    HTML

  4. get-started-with-ai-chat get-started-with-ai-chat Public

    Forked from Azure-Samples/get-started-with-ai-chat

    Basic sample for deploying chat web apps with Azure AI Foundry and SDKs

    Bicep

  5. contoso-chat contoso-chat Public

    Forked from Azure-Samples/contoso-chat

    This sample has the full End2End process of creating RAG application with Prompty and Azure AI Foundry. It includes GPT 3.5 Turbo LLM application code, evaluations, deployment automation with AZD C…

    Bicep

  6. contoso-creative-writer contoso-creative-writer Public

    Forked from Azure-Samples/contoso-creative-writer

    A creative writing multi-agent solution to help users write articles.

    Bicep