
Prev: co-founder at @potpiedotai 🥧
India
Joined April 2020
- Tweets242
- Following959
- Followers224
- Likes2.3K
Dhiren Mathur retweeted
A few weeks after announcing our round, what stands out is not the number, but the fact that people chose to back us early, before it was obvious. That kind of thoughtful and quiet trust stays with you far longer than any headline.
We are building Potpie for engineering teams who have grown tired of AI tools that perform well in controlled settings but fall apart when they meet real systems. This is not glamorous work, but it is the kind of work that, when done properly, changes how people spend their days, and that has always felt worth doing to us.
What has been equally meaningful is the response from customers and early users. Teams that have spent time with the product have come back with a level of conviction that is difficult to ignore.
Their response does not feel like curiosity, but like recognition, and that strengthens our own belief in what we are building. We are grateful for the support we have received, and we are focused on continuing to build.
Thank you to everyone who has supported us along the way. There is more coming soon.
Dhiren Mathur retweeted
The standard onboarding story for AI coding tools is deceptively simple: connect your repo and start getting value immediately. For small teams with straightforward codebases, this actually helps. But inside a real enterprise engineering org, the experience is different. The outputs feel generic, the agent misses things that are obvious to anyone on the team. And over time, engineers quietly stop using the tool, not because it is bad, but because it was never given the context it needed to be useful.
At Potpie, we learned early that onboarding isn't a one-click step. It's the part that actually decides whether the tool actually works or not. In this article we talk about the 8 things we do during every enterprise onboarding to make sure the agentic coding workflow is contextual and consistent from day zero. If you're evaluating AI tools for your team, or just trying to understand why some tools feel powerful in demos but fall flat in real systems, this is worth a read.
👉 potpie.ai/blog/how-onboardin…
Dhiren Mathur retweeted
MCP was launched in late 2024 as a complete, open standard, meant to give all AI agents one universal way to link up with outside apps. Some compared it to the USB-C, because it was designed as a single connection for every model and every service. People started adopting it very fast, major AI companies, software tools, and infrastructure providers quickly got on board. Thousands of MCP servers went online, and it truly seemed like the AI world had found its necessary standard.
But when developers began to build serious AI agents with it, the cracks started to show. The protocol looked great in demonstrations but failed under actual work because of several key issues:
Context Overload: Every time an agent connect to an MCP server, the server dumped its full tool description into the agent's prompt. Connecting just 5-6 servers meant that between 30% and 70% of the AI's brain space was taken up by this technical data, leaving less room for the model to think and reason.
Performance Hit: Because of the context overload, the agents started performing noticeably worse.
Reliability Problems: The MCP systems had issues with unstable authentication, servers that crashed easily, and incomplete documentation.
Chaining Complex Tasks: The simple way MCP handled tool calls didn't work well for complex agent tasks that needed to link multiple operations together.
The AI community eventually came up with various workarounds to handle these limitations of MCPs. One of the most trivial workarounds being lazy loading of MCPs whenever required. But it still had it's own demerits of context and tool overload. Soon, people noticed that using a CLI interface makes it easier for the agent to access the app without compromising on context: one of the biggest example being GitHub cli. For more complex tasks, agents could use the python/typescript interpreter to write code using the MCP apis directly. This not only saves a ton of context but also makes the tools very composable.
MCP is still useful for some big company tasks, but for most everyday work like coding, it can be more harmful than being useful. Context is limited, and most of the time, simple tools are better.
Dhiren Mathur retweeted
Always a hard decision for a founder to know what to build and, more importantly, what not to. Love this from
@rauchg chat with a16z.
One early decision we made was to commit to spec-driven development across all our agentic systems, instead of optimizing for skills.md.
Skills can raise the bar in isolated cases, but they don’t create consistency. There is no single right way to define or optimize a “skill.” Every engineer, every agent, interprets it differently. Over time, this leads to fragmentation, not improvement.
You end up with a collection of behaviors rather than a coherent system.
Specs force alignment and define intent, constraints, and expected outcomes upfront. They give every agent and every engineer a shared contract to operate against. That’s what creates system-level reliability and team-level cohesion, and also a decision point for an enterprise to choose @potpiedotai
Internally, we think about this as local vs global context.
Dhiren Mathur retweeted
A meaningful moment for us at @potpiedotai 🚀
We’ve been featured in Forbes after an in-depth interview with David Prosser on what is truly holding enterprise engineering teams back from adopting AI at scale.
The piece captures a shift we are seeing firsthand:
• AI has made code generation easier, but the real challenge is reasoning across massive, interconnected legacy systems and in non-trivial tasks like debugging.
• “Context” is the missing layer. Decades of decisions across code, tickets, logs, and documentation cannot live in people’s heads anymore.
• Most enterprises are experimenting with AI, but very few have embedded it deeply into production workflows.
• Potpie builds a structured knowledge graph across the codebase so AI agents can operate with the same clarity and safety as a senior engineer to practice spec-driven development.
• Early results are already tangible, including reducing debugging time from nearly a week to 30 minutes for one enterprise customer.
We are already working with large enterprises across healthcare, consumer and fintech, supporting systems with millions and sometimes hundreds of millions of lines of code. The opportunity in front of us is immense. Not incremental productivity gains, but fundamentally changing how complex software systems evolve.
We’re grateful for this recognition. But it is not an individual milestone.
While the story mentions me and @runtimeHorror, Potpie has been built by a much larger circle of belief. Our early investors who leaned in when this was just a sharp point of view. The mentors who pushed us to think bigger. The design partners who trusted us in production. The team that shows up every day to solve hard problems with care.
To everyone who backed us early, advised us, challenged us, introduced us, and believed in this problem before it was obvious. Thank you!
@anupamr, @kushalbhagia, @RTinkslinger, Ravish, @colinevans , Rachel, @rksunchained, @anshpsingh, @DavidTwizer , @ashpreetbedi , @rabi_guha , @GanatraSoham , @xdebstep , @richexplorer_ , @SameerGoyal91, @PuriSid , @maanavsagar, @prasunjain, @nikalank, @hipreetam93, @TsainGra , @vedantm_, @Mandybuoy.
The space is moving fast. Enterprises are ready. The need is real. And we are building with strong conviction. This is just the beginning!
Dhiren Mathur retweeted
Spec-driven development, visualized!
Left: “The agents handled it.”
Right: “Cool. Show me the spec.”
Dhiren Mathur retweeted
Today, we are launching the All In Golden Ticket program. Because the best founders building in AI deserve to build with the best customers and the best talent.
The quality of companies, talent and capital in AI that has concentrated in SF over the last three years is unprecedented. We consistently see that the founders that move there build much faster and bigger companies.
The US is very unique because it aggressively pays for software and automation. The U.S. spends more on software than the EU and China combined—multiplied by two.
We are very clear - if you want to build a global AI company, don't waste your time by starting with the domestic market and think about moving later, you will be too late.
Indian founders have the hustle and grit to win in this race and we want to back those who are willing to take the leap and build from the US from Day 0.
We will be your first investors, fly you to SF and help you soft land into the ecosystem with our network. You will also get enough credits to build an almost free MVP that can help you get revenue and investors.
Only one condition - one cofounder has to be technically strong -either prestigious college or strong work experience.
Fresh grads are also encouraged to apply. You will have fewer things to unlearn than grown ups and will adapt to the SF mindset quickly!
Accepting applications till Feb 15. Link in comments - go and apply!
Dhiren Mathur retweeted
AI Tinkerers Bengaluru #11 is a wrap.
No panels. No pitch decks. Just builders shipping code.
This weekend, the signal-to-noise ratio was high. We saw live demos on DFD automation with LLMs, agentic alert-to-PR debugging, and GraphRAG multi-hop retrieval. Real systems, not theory.
Huge thanks to Cashfree Payments for backing the builders and hosting us at The Bay.
Props to Dhiren Mathur @runtimeHorror for leading the chapter. You help us keep the bar high.
To the founders and engineers who showed up: you’re the reason this is the room that matters.
We build. We ship. See you at the next one.
Want to get involved? Search for the AI Tinkerers chapter in your city and join the community: Welcome aitinkerers.org
#AITinkerers #Bengaluru #GenerativeAI #LLM #Builders
Dhiren Mathur retweeted
🚨 Potpie is now on Slack!
Ask your AI agent anything about your codebase, right from your team’s daily workflow.
Like this:
🧠 “What browsers does @browser_use support?”
⚡ Instant answer, straight from the source code.
→ Install now: docs.potpie.ai/extensions/sl…
Dhiren Mathur retweeted
Auto-fill any online form based on your documents with BrowserAgent x Hyperspell
Excited to announce the launch of BrowserAgent Actions and our collab with @browserai_dev
Dhiren Mathur retweeted
Some of the best engineers I’ve met share one thing in common. They don’t just learn how a system works. They understand why it was built that way.
That kind of understanding doesn’t come from scrolling past summaries or skimming neatly labeled diagrams. But that’s how a lot of modern writing is. Short, simplified, and optimized for quick consumption.
There’s nothing wrong with that, but it rarely helps you think like an engineer.
Real understanding comes from seeing how a system was designed from the ground up, what tradeoffs were made, and what problems it was trying to solve. That’s also how I like to learn, and how I like to write.
It takes longer to read, because you’re not just absorbing facts. You’re tracing the decisions that shaped the system. But once you get it, you rarely need to revisit the topic. You can think your way through it again from first principles.
And more importantly, you start applying that mindset to new problems.
That, to me, is real engineering.
Dhiren Mathur retweeted
Create AI agents for your codebase using just one prompt.
This is pretty incredible! (This repo hit #2 on GitHub trending).
Potpie is an open-source platform that lets you build custom agents that understand your codebase and can automate any development task.
These are not "white-labeled", out-of-the-box, one-size-fits-all agents. These are *your* agents. They know *your* codebase. They are tailored to *your* use cases — anything from software architecture to root cause analysis.
For example, here is a prompt to create an agent:
"You are a custom agent specialized in generating detailed integration tests for this Python repo using Pytest. Refer to existing tests in the /test directory and generate new integration tests using the same format."
That's all it takes!
These custom agents ingest your codebase and build a knowledge graph—a mental model of your system that lets them:
• Understand your code
• Navigate your project's structure
• Reason about relationships & dependencies
• Focus on the right context, every time
I've been talking about knowledge graphs forever, and this is a great use case for them.
Here is the GitHub repository: github.com/potpie-ai/potpie
Dhiren Mathur retweeted
The Global Agent Hackathon is live!
Win up to $25K in cash, credits for your favorite AI tools, and ultimate bragging rights for building the coolest AI Agents! 🤖✨
Check out prizes, guidelines, and how to win 👇
Dhiren Mathur retweeted
We just launched Potpie on Product Hunt! 🚀
Potpie is an open-source platform to build custom AI agents for your codebase — think debugging, testing, system design, integration, and more.
You can create agents from a single prompt, connect them to your tools (GitHub, Jira, etc.), and let them automate the heavy lifting across the SDLC.
If you've ever felt limited by generic copilots — Potpie is for you.
Would love your support ❤️
🔗 producthunt.com/posts/potpie…
#AI #DevTools #ProductHunt #AIAgents #OpenSource
Dhiren Mathur retweeted
🎉 We just hit 3,000 stars on GitHub! 🌟
Potpie AI is reimagining software development with powerful & custom AI agents designed for engineers. From system design, debugging and testing to implementation and deployment, Potpie automates every stage of the software development lifecycle—helping developers build faster!
Thanks to all our users and contributors who’ve helped us reach this exciting milestone 🙌
Check us out and star our repo if you haven’t already! 🚀
👉 github.com/potpie-ai/potpie
Dhiren Mathur retweeted
You know what's common between Hugging Face, Stability AI, Mistral, LangChain, and CrewAI?
They're all open-source AI companies driving massive breakthroughs!
The next big wave isn't just AI Agents—it's COSS AI Agents.
So at Potpie AI we decided to actively support all Agentic COSS companies and started by identify them all across categories
Dhiren Mathur retweeted
We've been cooking a new version of Potpie AI!
💥 Today we're open-sourcing our most powerful feature yet — Custom AI Agents that understand your entire codebase!
⭐️One prompt creates an AI Agent that thinks like a developer, navigates code like a pro, and adapts to your workflow
🔥Dive into our latest release: potpie.ai/blog/open-source-c…
Dhiren Mathur retweeted
Potpie now has web access which means now along with having specific context from your repo , our AI agents can also reference the internet whenever needed.
Check out this example where I just paste a Github issue link and our LLD agent starts by explaining how to work on it.
Thanks to @firecrawl using which we enabled internet access for our AI agents 🔥
@potpiedotai
Dhiren Mathur retweeted
Github 👨🔧: Prompt-To-Agent : Create custom engineering agents for your codebase
Helps you build custom AI agents specialized in your codebase for automated code analysis, testing, and development.
It constructs a knowledge graph from your code, enabling agents to understand code relationships for tasks like debugging, code Q&A, change analysis, and test generation. It offers pre-built agents and tools for integration into development workflows, handling codebases of any size or language.
-------------
What it offers:
🤖 Pre-built agents for debugging, codebase Q&A, code changes analysis, integration and unit test generation, low-level design, and code generation.
🧠 Deep code understanding via a built-in knowledge graph that captures relationships between code components.
🛠️ Tooling system including functions to retrieve code snippets and graph information, execute knowledge graph queries, and detect code changes.
🚀 Easy setup with Docker, supporting local and production modes, including API access for integration into CI/CD pipelines.
🎨 Custom agent creation to personalize tools by defining system instructions, agent information, tasks, and tools.
🔄 Flexible customization options to modify system prompts, add new agents, customize agent behavior, and integrate custom tools.




























