# Kartikay Dhar > Director of Product, AI at Sprouts.ai in Bengaluru. This file lists public pages only. Unpublished drafts are omitted. Kartikay writes about AI agents, product strategy, and enterprise systems, and publishes notes on work shipped at Sprouts.ai. ## Pages - [Home](https://www.kartikaydhar.com/): Kartikay Dhar is Director of Product, AI at Sprouts.ai in Bengaluru. He ships live enterprise AI products across agents, data platforms, and Salesforce. - [Blog](https://www.kartikaydhar.com/blog): Essays and notes from Kartikay Dhar on AI agents, product strategy, and enterprise systems, drawn from shipping GenAI products at Sprouts.ai in Bengaluru. - [Projects](https://www.kartikaydhar.com/projects): Selected AI product work by Kartikay Dhar, including Agentforce, an MCP server, signal research, and context-aware prototyping shipped with Sprouts.ai. - [Resume](https://www.kartikaydhar.com/resume): Resume of Kartikay Dhar, Director of Product, AI at Sprouts.ai. Twelve-plus years across QA, engineering, solution architecture, and product leadership. - [WebMCP demo](https://www.kartikaydhar.com/webmcp): A public WebMCP demo by Kartikay Dhar. The page exposes tools, prompts, and resources that browser agents can discover and call without a separate server. - [About](https://www.kartikaydhar.com/about): About Kartikay Dhar, Director of Product, AI at Sprouts.ai in Bengaluru. He ships enterprise AI products, writes in public, and publishes the work on this site. - [Contact](https://www.kartikaydhar.com/contact): Contact Kartikay Dhar, Director of Product, AI at Sprouts.ai in Bengaluru. Email, LinkedIn, or a call are open for AI product work, writing, and collaboration. - [Privacy](https://www.kartikaydhar.com/privacy): Privacy notes for kartikaydhar.com, the site of Kartikay Dhar in Bengaluru. It explains what public pages store, what they do not sell, and how to reach him. - [Terms](https://www.kartikaydhar.com/terms): Terms for using kartikaydhar.com, the personal site of Kartikay Dhar. The writing, projects, and resume here are his, and you may share links with attribution. - [Search](https://www.kartikaydhar.com/search): Search the published blog, case studies, and resume of Kartikay Dhar, Director of Product, AI at Sprouts.ai in Bengaluru. Drafts stay out of the results. ## Blog - [What Amazon Kiro Crew Means for Async Agents](https://www.kartikaydhar.com/blog/kiro-crew-async-agent-workspace): Kiro Crew is AWS Kiro's open-source async agent workspace: schedules, memory, approvals, and audit logs so coding agents keep working after you leave. - [Microsoft Scope: Test Whether AI Agents Use Your APIs Correctly](https://www.kartikaydhar.com/blog/microsoft-scope-evaluate-ai-coding-agents): Set up Microsoft's open-source Scope platform, run a coding-agent evaluation, define criteria, and inspect failures in API integration tasks. - [Cloudflare Clairic: Typed Data Extraction With Confidence](https://www.kartikaydhar.com/blog/cloudflare-clairic-structured-data-extraction-tutorial): Cloudflare Clairic is a Workers AI model that pulls typed values, estimates and forecasts from messy text, with confidence scores, for $0.10 per million tokens. - [VoiceStudio: Run Local Transcription and Review GTM Signals](https://www.kartikaydhar.com/blog/voicestudio-local-transcription-gtm-signals): Set up VoiceStudio speech-to-text and MCP, then turn a sample sales-call transcript into reviewable GTM signals. - [Skill Cauldron: Brew a Claude Skill That Works Like You Do](https://www.kartikaydhar.com/blog/skill-cauldron-brew-personal-claude-skills): I built Skill Cauldron to turn your work habits, installed skills, and skills.sh discoveries into one focused Claude skill—with a blind taste test and a reusable recipe card. - [Hallmark: A Design Skill That Checks Whether Your AI-Built Website Actually Works](https://www.kartikaydhar.com/blog/hallmark-ai-website-design-skill-tutorial): Install Hallmark for Claude Code or Codex, review a realistic frontend demo, and learn which AI-built website checks still need browser verification. - [What NVIDIA OpenShell Adds to Agent Sandboxes](https://www.kartikaydhar.com/blog/nvidia-openshell-agent-sandbox): NVIDIA OpenShell is an open-source Rust runtime that sandboxes AI agents and enforces YAML policy at the kernel. Here is how it works and what it locks down. - [Decisions API vs Jev vs Laya vs Cloudflare Clef](https://www.kartikaydhar.com/blog/decisions-api-vs-jev-laya-cloudflare-clef): OpenAI's Decisions API, TypeSafe's Jev, open-source Laya and Cloudflare's Clef all return typed decisions. Here's how they compare on price, inputs and hosting. - [Agent Skills Joins the Agentic AI Foundation: What Changes](https://www.kartikaydhar.com/blog/agent-skills-agentic-ai-foundation): Anthropic donated Agent Skills to the Linux Foundation's Agentic AI Foundation. What the SKILL.md standard is, who maintains it now, and what changes for teams. - [What Claude Duet Gets Right About Proactive AI Agents](https://www.kartikaydhar.com/blog/claude-duet-proactive-ai-agent): Claude Duet is Anthropic's proactive agent: morning briefs, background work and approval before it acts. What it gets right, and what revenue agents still need. - [What YC's QM Teaches About Rolling Out AI Agents](https://www.kartikaydhar.com/blog/yc-qm-multiplayer-agent-harness): YC open-sourced QM, the agent harness it uses internally. Here's how scoped memory, sandboxes and approval modes let one agent setup serve a whole company. - [I built typwrtr, and my dictation got better(and free)](https://www.kartikaydhar.com/blog/typwrtr): A new category of voice dictation is emerging: local-first, GPU-accelerated, and actually learns from your edits. typwrtr runs entirely on your machine, improves after every correction, and never sends your audio or... - [The End of the Visual Web: Why AI Agents Need Contracts, Not Pixels](https://www.kartikaydhar.com/blog/webmcp): 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... - [Why the 'Agent Stack' Is the Real Revolution](https://www.kartikaydhar.com/blog/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,... - [Beyond Vibe Coding: Master the Ralph Wigum Loop for Autonomous AI Apps](https://www.kartikaydhar.com/blog/beyond-vibe-coding-master-the-ralph-wigum-loop-for-autonomous-ai-apps): How to make your vibe coded app work. - [Recursive Language Models vs. RAG](https://www.kartikaydhar.com/blog/rlm-vs-rag-solving-infinite-context): A New Paradigm for Scaling LLM Context Without RAG ## Projects - [The Era of Context-Aware Prototyping](https://www.kartikaydhar.com/projects/the-era-of-context-aware-prototyping): Stop recreating, start creating. - [Sprouts Data Intelligence (MCP)](https://www.kartikaydhar.com/projects/mcp-server): MCP access to 350M+ contacts and 35M+ accounts on Claude & OpenAI - [AI powered Data Intelligence on Agentforce](https://www.kartikaydhar.com/projects/agentforce-salesforce): AI powered Agentforce app on Salesforce enabling access to 350M+ contacts and 35M+ accounts - [AI Researcher](https://www.kartikaydhar.com/projects/ai-signals-platform): Arguably, the most accurate, comprehensive, and affordable signal engine ever built. - [FastN8N](https://www.kartikaydhar.com/projects/icp-engine): Stop fixing AI-generated workflows. Start shipping them. ## Optional - [Full text for published posts and projects](https://www.kartikaydhar.com/llms-full.txt) - [RSS feed](https://www.kartikaydhar.com/feed.xml) - [Sitemap](https://www.kartikaydhar.com/sitemap.xml)