Dhiren Mathur

We’re trending on GitHub again 🔥 Turn a single prompt into an agent that knows your entire codebase. @potpiedotai is open source, insanely powerful, and built for serious dev workflows. Check it out 👇 github.com/potpie-ai/potp… ⭐️

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.

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-onboa…

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.

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.

@aditikothari_ On point. System Understanding and Intent are the missing link to get meaningful outcomes from your agents!

Recently read an article that said "Many SWE-bench-Passing PRs Would Not Be Merged into Main" - and if you've used any coding tool, you get it. That's why it's become more and more important for you to steer the implementation - to build the constitution.

Absolutely loving how the future is moving towards spec driven development. 'whenwords' is such a beautiful example of a library with just spec and no code. Couple this with what we already saw in openclaw with pi agent self developing skills. Software is very much building itself!

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!

Codegen is not the hard part, making sense of large, messy systems is. We’re just getting started! 🚀

@potpiedotai @DSantra92 @deepesh_genani @yashkmkrishan Lol that spec looks like it needs some work

Spec-driven development, visualized! Left: “The agents handled it.” Right: “Cool. Show me the spec.”

👀👀

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!

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

@nischal Looks super cool, congratulations!

super stoked to launch bunny!! I feel there’s no higher mission than to be able to help nurture curiosity of kids ❤️

@conor_ai @ycombinator Lessgooo @conor_ai @maebert 🚀

🚨 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/sla…

Check it out here: github.com/potpie-ai/potp…

Your context is unique, your agent should be too. This is the exact ideology behind what we're building at potpie.

Potpie just crossed 4000 stars on GitHub! 🌟⚡ If you haven't checked out @potpiedotai yet --> We enable developers to create custom AI agents for your codebase with just a prompt. These agents are tailored to your code, your tools, and your usecase. github.com/potpie-ai/potp… The future of software development is personalised and agentic. Help us keep the momentum going by dropping a 🌟