Confidence is easy. Calibration is the work.
I’m Mayank — a solution architect working on AI and data systems. Making something work once is the straightforward half. Showing that it works, knowing where it breaks, and turning that into a number a decision can rest on is the harder half — and it’s the one that earns any trust the system gets.
- Focus
- Scalability, reliability & quality of AI
- Background
- Electronics → SWE → Architect → ML
Evaluation
Metrics whose assumptions match the problem, splits that don’t flatter the model, and trajectory-level evaluation for agents — numbers a person can actually act on.
Read 02Quality
Quality on two fronts — model quality (does it hold up, where does it break) and data quality (lineage, sensitivity, and governance over enterprise data estates).
Read 03Context engineering
Getting the right information in front of the model at the right moment — retrieval, grounding, and the context that decides whether an answer is any good.
Read 04Knowledge base
Knowledge graphs and RAG over enterprise data — turning scattered estates into a queryable, trustworthy source of truth.
Read 05Integration
Wiring AI into the systems around it — tools, APIs, MCP, and data pipelines — so a model becomes something a business can actually use.
Read 06Open-source & open-weight AI
Building on open models and open-source tooling — for control over cost, privacy, and how a system actually behaves.
Read