AI Lab

AI Systems · Product Architecture · Evaluation

AI Lab

I design AI products and production systems around judgment, reliability, evaluation and human control — not just task automation.

01Featured AI System

OPERATIONAL AI AT SCALE

Company Enrichment Pipeline

A production AI pipeline that processed 173,517 company records end-to-end in 70 hours, combining concurrent processing, confidence scoring, deterministic validation and human-in-the-loop review.

The core challenge was not calling an LLM at scale. It was designing around quota limits, uncertainty, cost, failure recovery and the boundary between probabilistic judgment and deterministic control.

Read the full case study

173,517

Companies processed

99.996%

Processing success

70 hrs

End-to-end runtime

$216.50

Total API cost

02Other Flagship Builds

BEHAVIORAL MEMORY SYSTEM

Adaptive Agent Constitution

A behavioral memory system that learns durable user preferences without turning every correction into permanent behavior.

The dangerous memory error is inventing permanence the user never intended.

7/8

Machine end-to-end

8/8

Human-adjudicated

96.7%

Memory action accuracy

GENERATIVE AI SYSTEM

Personalized Content Writer

Collaboratively designed a production generative workflow that separates creative generation from deterministic controls, then turns human editorial feedback into governed context and reusable rules.

The harder problem was not generating drafts. It was keeping context, memory and human authority reliable as the system evolved.

31+

Live articles

8–12

Posts / week capacity

≤3

Writer–critic iterations

AI-ASSISTED 0→1 PRODUCT

SpeedLens

A Chrome productivity product built independently from idea to launch. The core product challenge was not the code — it was choosing a narrow user segment, designing around reading backlog, and finding a monetisation boundary that protected the core habit.

AI accelerated execution, but segmentation, monetisation and distribution remained product decisions.

140+

Chrome Web Store installs

0

Paid acquisition

v1.1.0

Current release

₹799/year

Pro Yearly pricing

03How I Build AI Systems

How I build AI systems

01 · Judgment

LLMs for judgment. Code for constraints.

Use language models where interpretation is needed. Use deterministic systems for rules, validation and schema enforcement.

Uncertainty is a design constraint.

Design for probabilistic output with confidence thresholds, fallback paths and graceful degradation.

02 · Reliability

Evaluation before optimization.

Define what 'good' means before tuning prompts, adding agents or scaling the workflow.

Failure modes should be observable.

Logging, tracing and confidence visibility turn silent failures into actionable product feedback.

03 · Control

Human review is part of the system.

Human-in-the-loop is a design decision, not a failure state. Build review and escalation into the workflow.

Every run should create better feedback.

Use evaluation results, human corrections and structured outputs to improve future decisions without implying autonomous self-learning.

04Current Research

Currently exploring

Responsibility

  • Responsible AI & deployment frameworks
  • AI ethics & deployment trade-offs
  • Red teaming & AI evals

Systems

  • LLM Wiki & persistent context systems
  • Agent orchestration & tool use

Economics

  • AI product pricing & unit economics

Active areas of exploration — not claims of expertise.

05 · Closing

AI products are still products. But increasing capability raises the bar for how deliberately they are evaluated, governed and deployed.

The goal is not just more capable systems — it is systems that are useful, observable and responsibly deployable.