Skip to content
Director of Product, AI @ Sprouts.ai

Kartikay Dhar

I build AI products that scale. From launching the first native Agentforce app on Salesforce to architecting platforms serving 450M+ records — I turn complex AI into real business value.

View My WorkBook a Call
0X
ARR Growth in 12 Months
0X
Faster Account Intelligence
0%
AI Cost Reduction
0+
Professionals Coached
Kartikay Dhar

About

From QA to Director of Product — The Full Stack PM.

I've walked every step of the product journey — QA → Engineering → Solution Architecture → Product. This path gave me a 360° perspective on how to ship products the right way: with empathy for users, technical depth, and business impact.

Now I lead AI product strategy at Sprouts.ai, building industry-leading GenAI & ML solutions that help enterprises unlock the value of their data. From launching the first native Agentforce app on Salesforce to building MCP servers that connect AI agents to 450M+ records.

Generative AI & LLMProduct StrategyMCP & RAGPythonSalesforceEnterprise SaaS

Selected Work

Projects that define my journey.

The Era of Context-Aware Prototyping

Open Source

The Era of Context-Aware Prototyping

Stop recreating, start creating.

SkillsClaude codeReact
Sprouts Data Intelligence (MCP)

Platform

Sprouts Data Intelligence (MCP)

MCP access to 350M+ contacts and 35M+ accounts on Claude & OpenAI

TypeScriptOAuthMCP
AI powered Data Intelligence on Agentforce

0→1 Launch

AI powered Data Intelligence on Agentforce

AI powered Agentforce app on Salesforce enabling access to 350M+ contacts and 35M+ accounts

SalesforceApexLWCAI
AI Researcher

Enterprise

AI Researcher

Arguably, the most accurate, comprehensive, and affordable signal engine ever built.

PythonMulti-LLMRAGRedis
FastN8N

Open Source

FastN8N

Stop fixing AI-generated workflows. Start shipping them.

Node.jsTypeScriptMCPn8n

Latest Thoughts

From the blog.

View All Posts
The End of the Visual Web: Why AI Agents Need Contracts, Not Pixels
AI & LLM

The End of the Visual Web: Why AI Agents Need Contracts, Not Pixels

The Web Model Context Protocol (WebMCP) is a browser standard that enables websites to expose structured 'tool contracts' to AI agents. Instead of forcing agents to visually scrape screens to identify buttons and fields, WebMCP provides a logical API layer. This allows agents to interact with websites through defined functions and JSON schemas, resulting in faster, cheaper, and more reliable autonomous actions compared to traditional fragile screen-scraping methods.

Feb 1310 min
Why the 'Agent Stack' Is the Real Revolution
AI & LLM

Why the 'Agent Stack' Is the Real Revolution

Until 2025, the bottleneck wasn't model intelligence—it was isolation. GitHub Copilot saw your code but not your logs. ChatGPT wrote SQL but couldn't see your schema. Developers became glorified data routers, manually bridging the gap. This "interoperability gap" crippled even the smartest models. They lacked the sensory input to understand the system's state. The **Model Context Protocol (MCP)** and **Agent Skills** standard have solved this, creating a universal language for tools to expose their capabilities to AI without bespoke integration.

Feb 75 min
Beyond Vibe Coding: Master the Ralph Wigum Loop for Autonomous AI Apps
AI & LLM

Beyond Vibe Coding: Master the Ralph Wigum Loop for Autonomous AI Apps

How to make your vibe coded app work.

Jan 236 min

Get in Touch

Let's build something together.

Whether you have a project idea, want to collaborate, or just want to say hi, I'd love to hear from you.