Python
Becoming more fluent in the language and tooling underneath practical AI development.
A technology career
still in motion.
I’m Srikanth. My background spans enterprise technology, data, analytics, delivery, and decision systems. VonticAI is where I’m extending that foundation into AI engineering by learning, building, testing, and documenting the work.
Learn
→
Build
→
Understand
→
Share
↺
01
Where I’m Coming From
Systems first.
Systems first.
Then data.
Then decisions.
Much of my career has been spent around enterprise systems: building them, operating them, scaling them, integrating them, and helping organizations depend on them.
Over time, the work moved increasingly toward data and analytics— not just reporting what happened, but understanding what the information could help people decide.
01
Enterprise Technology
Systems, platforms, delivery, reliability, and scale.
→
02
Data & Analytics
Models, reporting, platforms, and information architecture.
→
03
Decision Intelligence
Connecting information to better operational decisions.
→
04
AI Engineering
Learning how intelligent systems are actually built.
02
Why VonticAI Exists
I wanted somewhere to document the transition.
It’s easy to consume courses, demos, articles, and AI news. It’s much harder to turn that information into understanding.
VonticAI gives me a place to make that process visible: build something, test it, explain it, and preserve the lesson.
01
Learn
→
Study the concept and identify what I don’t understand.
02
Build
→
Turn the concept into something concrete enough to test.
03
Understand
→
Find the assumptions, tradeoffs, failures, and real mechanics.
04
Share
Document the result clearly enough that I can explain it.
03
What I’m Focused On Now
Moving from AI concepts to engineering practice.
My current focus is building enough technical depth to understand how modern AI systems behave beyond the demo layer.
RAG & Retrieval
Chunking, embeddings, vector search, grounding, and evaluation.
Agents & Tool Use
Understanding workflows, tool calling, state, orchestration, and MCP.
Evaluation
Measuring whether an AI system is actually useful rather than merely convincing.
04
What Carries Forward
AI changes the tools. It doesn’t erase the foundation.
The deeper I go into AI, the more familiar some of the hard problems look: architecture, integration, reliability, observability, governance, data quality, security, and knowing what failure means in production.
Systems
Architecture & integration
Delivery
Turning ideas into operating systems
Data
Models, quality, context & governance
Operations
Reliability, monitoring & failure modes
Decision Making
Connecting technology to useful outcomes
Learning
Understanding systems by building them
05
Keep Exploring
The work is the portfolio.
Projects show what I built. The AI Lab shows what I’m testing. Insights show what I learned along the way.