Madan Mohan
You are hereApron · Project evidencePlain briefAirfield

Four projects. Four product decisions.

Explore AI evaluation, requirements drafting, experimentation, and fraud-risk decisions.

Sentinel Eval Harness

Completed portfolio build

An evaluation harness for AI systems with repeatable datasets, deterministic and quality scorers, mutation testing, statistical comparison, persisted runs, an API, dashboard, and CI release gate.

Open evidence pack

Briefly PRD AI

Live portfolio application

Transforms rough product concepts into decision-ready PRDs with guided intake, user stories, acceptance criteria, success metrics, and Markdown export.

Open evidence pack

AB Advisor

Completed portfolio build

A Bayesian experimentation workspace that turns posterior probability, expected lift, credible intervals, and expected loss into an evidence-based ship decision.

Open evidence pack

FraudShield

Live portfolio application

A live rules-based e-commerce risk prototype showing transaction-level risk factors.

Open evidence pack
Other experiments

Browse the full collection

9 of 9 projects in Product & Strategy. 25 across the four categories.

  • Autonomous Product Analyst

    Complete

    Investigates why product metrics changed through governed definitions, safe SQL, eight diagnostic dimensions, contributor ranking, statistical evidence, and release context.

    Problem, approach, and evidence
    Problem
    A changed metric needs an explanation before a team can choose a response.
    Approach
    Connect governed definitions and safe SQL to diagnostic dimensions, statistical evidence, and release context.
    Evidence
    Inspect the repository for the diagnostic workflow and implementation; no business-impact percentage is claimed here.

    Python · FastAPI · SQLite · Statistics

    Evidence and walkthrough GitHub

  • AI Product Discovery Engine

    Complete

    Unifies interviews, support tickets, reviews, surveys, and analytics to detect customer problems, rank opportunities, and preserve the evidence behind every recommendation.

    Problem, approach, and evidence
    Problem
    Customer evidence is scattered across interviews, tickets, reviews, surveys, and analytics.
    Approach
    Unify inputs, detect customer problems, rank opportunities, and preserve the evidence behind recommendations.
    Evidence
    Inspect how the implementation links recommendations back to customer evidence.

    JavaScript · NLP · Product Discovery

    Evidence and walkthrough GitHub

  • AB Advisor

    Complete

    A Bayesian experimentation workspace that turns posterior probability, expected lift, credible intervals, and expected loss into an evidence-based ship decision.

    Problem, approach, and evidence
    Problem
    An experiment needs a decision that accounts for uncertainty and downside.
    Approach
    Use posterior probability, expected lift, credible intervals, and expected loss to frame a ship decision.
    Evidence
    Explore the Bayesian workspace and tests in the repository.

    Python · Streamlit · Bayesian Models · Pytest

    Evidence and walkthrough GitHub

  • AI Experimentation Platform

    Complete

    A working local experiment workspace with saved hypotheses, sample planning, entered conversion counts, calculated readouts, guardrail checks, review decisions, and JSON backup; rollout controls are planning state.

    Next.js · TypeScript · DeepSeek

    Evidence and walkthrough GitHub

  • Feedback Prioritizer

    Complete

    Converts customer feedback into deduplicated themes and ranked product opportunities so teams can prioritize work with traceable evidence.

    NLP · RICE · Product Analytics

    Evidence and walkthrough GitHub

  • SprintForge

    Complete

    Runs the delivery cycle from backlog prioritization and sprint planning through Kanban execution, burndown tracking, retrospectives, and dependency visibility.

    React · Vite · Recharts

    Evidence and walkthrough GitHub

  • Briefly PRD AI

    Live

    Transforms rough product concepts into decision-ready PRDs with guided intake, user stories, acceptance criteria, success metrics, and Markdown export.

    Problem, approach, and evidence
    Problem
    Early product concepts need a structured requirements draft before cross-functional review.
    Approach
    Guide contextual intake, generate an editable draft, and export Markdown.
    Evidence
    Review the live workflow and the generation route; assess drafts against actual customer evidence.

    Next.js · React · DeepSeek · Cloudflare

    Evidence and walkthrough GitHub Live app

  • AI Project Manager Assistant

    Complete

    Turns an early brief and team roster into a work breakdown structure, milestones, effort estimates, resource assignments, and a RAID register.

    TypeScript · Workers AI · Delivery Planning

    Evidence and walkthrough GitHub

  • ProdMind

    In progress

    An experimental workspace connecting customer evidence, prioritization, and release decisions.

    TypeScript · Python · D1 · Cloudflare

    Evidence and walkthrough GitHub