Three projects, one platform: A developer's winning streak with Fireworks AI
By Fireworks AI|10/14/2024
Loading...
Qwen 3 models are now available with SOTA reasoning, coding and agentic tool use capabilities. Try Qwen 3 now
By Fireworks AI|10/14/2024
When it comes to building with Fireworks AI, few developers can match Nehil Jain's track record. His latest triumph – securing second place at the E2B x Fireworks AI hackathon alongside Selvam Palanimalai – marks his third consecutive success using the platform. From automating release notes with LazyPMs to matching hackathon teams with KinConnect, and now ensuring documentation reliability with ProoferX, Nehil has consistently demonstrated the power and versatility of Fireworks AI.
"The speed I get using Fireworks endpoints for Llama models is one of the key drivers for successful outcomes," explains Nehil, whose deep understanding of the platform has been crucial to his winning streak. "A combination of Llama for intelligence and Firefunction for tool calling, along with structured outputs, lets me build reliable AI pipelines."
His latest project, ProoferX, developed with technical architecture expert Selvam Palanimalai, tackles one of the most persistent challenges in the developer tools ecosystem: maintaining reliable technical documentation. You can see their solution in action in their demo on X or check out all the hackathon demos on YouTube.
"Good tech products need solid docs and examples. Developer experience and trust are essential for these products to grow," explains Nehil Jain, co-creator of ProoferX. "Out-of-date code examples in public technical documentation can really hurt the product builders."
The team uncovered several real-world examples that validated their concerns:
The challenge, Nehil points out, goes beyond simple maintenance: "It is unimaginable to expect a team to manually check that their guides work for all the versions of the libraries used in the examples for all the OSes for different versions of compilers the user is using. The only way to achieve this is through automation."
From E2B’s Tereza Tizkova LinkedIn post, “🏆 Who won our first hackathon?“
Drawing on his experience with Fireworks AI, Nehil worked with Selvam to architect a solution that could tackle this complex challenge.
ProoferX operates through three crucial steps:
At the heart of ProoferX lies a carefully orchestrated pipeline that begins with Firecrawl converting documentation URLs into markdown format.
Diagram from Nehil Jain’s blog post, “How we won Code Interpreter 2.0 with ProoferX”.
Code extraction pipeline
Analysis flow
URL → Markdown → Code Snippets → Success Criteria → Validation
Key components
Agentic approach
Check out Nehil’s blog for a full video demo of ProoferX and more details about his and Selvam’s personal perspective on their most recent hackathon.
The team's success wasn't just about technical innovation – it was built on methodical preparation and execution.
During the event, their process was equally structured.
Nehil brings deep expertise as:
"We have been building data platforms, infra, and engineering pipelines for various use cases for a long time in our careers," Nehil explains. "Using ML and now AI on top of it is a natural progression to unlock more value."
As co-founder at DemoDrive, Selvam (ex-Zomato, Rubikloud, and Kinaxis) contributed crucial expertise:
The team's complementary skills proved crucial for ProoferX's success, with Nehil handling LLMs and prompting while Selvam managed code sandboxes and app scaffolding.
Throughout his hackathon successes, Nehil has consistently leveraged Fireworks AI's capabilities:
"We used Llama 3.2 models to get excellent outputs for extracting essential information like goals, summaries, and steps from the markdown article," shares Nehil. "It was cheap so that we can iterate on the prompts freely."
ProoferX represents just the latest chapter in Nehil's journey with Fireworks AI. His previous hackathon victories demonstrate not only his technical versatility but also his deep understanding of how to leverage Fireworks AI's capabilities across different use cases.
Before tackling documentation challenges, Nehil turned his attention to a problem he knew firsthand: the challenge of forming effective hackathon teams. At the MongoDB GenAI Hackathon, he developed KinConnect, a sophisticated matching system that transformed the typically random team formation process into a data-driven solution. The project not only secured first place but also demonstrated the power of combining Fireworks AI with modern database technologies.
From Nehil Jain’s blog, “I built an AI app to Connect with Your Dream Team at a Hackathon”
The solution's architecture showcased Nehil's ability to build complex, integrated systems:
Frontend experience
Backend components
Data processing
Breaking new ground in search technology, KinConnect implemented MongoDB's Hybrid Search, combining:
AI integration
The project leveraged multiple Fireworks AI models, each chosen for specific tasks:
In another impressive showing at the Agents and Compound AI Systems Hackathon, Nehil and his team secured third place with LazyPMs Inc., a solution that redefined how teams handle release notes. This project showcased the potential of combining multiple AI agents to tackle complex documentation tasks.
From James Barney, LinkedIn post: “I had a ton of fun hacking with the best and brightest AI minds this weekend!“
The heart of LazyPMs Inc. was its sophisticated agent network, where each AI entity played a crucial role:
Agent network
With minimal oversight and only final approval needed, the coordinated agent system transformed brief release notes into rich, user-friendly documentation.
The team is actively working to launch ProoferX as a production-ready solution. Their roadmap includes several high-value use cases:
The team shares an unexpected insight: "Stay away from junk food if you want to boost your mental performance. Taking care of your physical and mental state is an underappreciated alpha for winning hackathons."
Nehil Jain and Selvam Palanimalai harnessed the power of Fireworks AI to tackle the persistent challenge of maintaining reliable technical documentation.
Inspired by ProoferX and want to build a similar solution? Here's how to get started:
Whether you're tackling documentation challenges, building AI agents, or creating the next game-changing developer tool, Fireworks provides the performance and reliability you need to succeed.
