ISHANT.OS — Agentic AI · Generative AI · Backend Engineering · Data Science
I BUILDINTELLIGENTSYSTEMSTHAT SHIP.
I build AI-powered products and the backend systems that make them reliable, usable, and production-ready.
PROFILE GRAPH
AI & backend engineer building agentic systems, developer tools, and production software.
I'm Ishant Yadav, a computer science student and builder focused on Agentic AI, Generative AI, backend engineering, and production systems. I work at the intersection of intelligence and infrastructure—designing AI workflows, connecting models to tools and data, building retrieval systems, exposing capabilities through APIs, and developing the backend foundations required to turn prototypes into usable software. My work spans Python, FastAPI, Django, Next.js, TypeScript, PostgreSQL, Redis, LangChain, LangGraph, Firebase, Docker, and cloud infrastructure. I've built developer tools, productivity platforms, business software, retrieval-driven systems, and AI products with teams. I care about the complete system: architecture, data flow, APIs, AI behavior, persistence, deployment, debugging, and iteration. I'm currently focused on building deeper expertise in Agentic AI and Generative AI while expanding into MLOps, DevOps, system design, evaluation, and scalable backend architecture. I don't want to build demos that only work on my machine. I want to build software that can be deployed, operated, improved, and used.
Agentic AI
Orchestrated multi-step agents with explicit state, tool boundaries and streamed reasoning.
Generative AI
Retrieval-grounded generation, structured model output, and interfaces the model composes.
Backend Engineering
Typed APIs, relational modelling, caching strategy and the operational edges around them.
Data Science
Analysis and modelling in Python, with the pipeline work that makes results reproducible.
SKILL NETWORK
The edges matter more than the nodes.
Skills are stored with the relationships between them, so the graph shows what is actually used together — not a list of logos.
Agentic AI
Generative AI
Backend Engineering
Data Science
PROJECT MEMORY
Featured systems.
IN DEVELOPMENT
FOCALISHANT.OS
A portfolio that an agent uses as its interface.
LIVE
QUEUEDVIS ERP
Production backend for an operations platform.
INSPECTING SYSTEM
ISHANT.OS
A generative interface where the agent composes the page itself — validated UI specifications instead of generated code, streamed alongside a grounded answer.
- Agent output is a validated specification, never executable code
- Interface events are contract-typed and shared by mock and real backends
- UI planning and answer generation run as separate stages
RESEARCH VAULT
Notes on making generated systems trustworthy.
RESEARCH
Generative interfaces without generated code
Provisional entry — replace from the admin dashboard. On treating model output as a validated presentation specification rather than executable code.
RESEARCH
Grounding answers in a versioned knowledge base
Provisional entry — replace from the admin dashboard. On keeping retrieval, cache and index in step so answers never outlive their sources.
AGENT RUNTIME
Query the system directly.
Commands resolve against portfolio content locally. `ask` hands off to the agent.
END OF SEQUENCE
Ask the system anything else.
OPEN TO ENGINEERING OPPORTUNITIES
Open to internships, engineering collaborations, hackathons, and opportunities to build real AI and backend systems.
KNOWLEDGE VERSION
v2026-09-23T17-38-26-085Z