Selected work

Products built where ambiguity meets execution.

Agentic workflows, product research, and enterprise implementations designed around real operational constraints.

Agentic AI / Enterprise Automation

Retail KPI Monitoring Agent

Problem

Teams manually reviewed dashboards every day to catch KPI misses, so risks were often spotted too late.

User

Retail operations teams and store managers.

Key decision

Instead of another dashboard, built an agent that compares daily actuals against targets, classifies risk, and pushes Slack alerts, with email reserved for high-risk cases.

Result

Risks are surfaced through daily checks and routed by severity, reducing reliance on manual dashboard review.

GPT-4.1Zoho AnalyticsSlackEmailTool Calling

GitHub

Agentic AI / Customer Experience

Apr – Aug 2026

Customer Support Agent

Problem

Support queries needed more consistent routing and resolution across different customer intents.

User

End customers and the support team.

Key decision

Designed intent detection, entity extraction, tool calling, and fallback logic, with clear rules for when to hand off instead of guessing.

Result

Improved agent accuracy by 35% through prompt evaluation, test-case creation, failure-pattern analysis, and root-cause analysis.

PythonPhronetic AI PlatformPostman (API Testing)

Product Management Case Study

Sept 2026

Where Is My Train — Product Case Study

Problem

How did Sigmoid Labs build and scale a consumer app, and what should it do after acquisition?

User

Product teams evaluating the app’s next phase of growth.

Key decision

Applied Atlassian’s Product Lifecycle framework to user segmentation, competitive positioning, business model, and key trade-offs.

Result

Produced product recommendations for the post-acquisition phase.

Notion

Case study

Agentic AI / Independent Project

Aug 2026

Ecommerce Retention Agent

Problem

At-risk customers were identified too late for teams to intervene with relevant win-back actions.

User

Ecommerce growth and CRM teams.

Key decision

Split the work into three agents—risk classification, strategy recommendation, and personalized re-engagement—so each step could be tested separately.

Result

Validated the full workflow across 50 synthetic customer profiles, including edge cases.

Lyzr