DevFest Prayagraj 2025

A Day of Code & Connection: My Throwback to DevFest Prayagraj 2025

By Vaishnavi Mishra

As the year winds down, I’ve been reflecting on the moments that truly sparked my enthusiasm for technology. One day stands out vividly: November 29th at DevFest Prayagraj - My first time participating in a Devfest.

Events are often just about sitting in a dark room watching slides, but this felt different from the moment I arrived. Walking into the venue at the United Institute of Technology, the energy was palpable. With over so many participants, students, and experts under one roof, it felt less like a formal conference and more like a massive celebration of the developer ecosystem.


Beyond the Slides: Active Witnessing

What made this DevFest unique for me was the shift from passive listening to active witnessing.

I got to experience Parallel Hands-on Labs. Instead of just hearing about code, I watched it run. Seeing fellow developers build real-time solutions with the Gemini CLI and MCP Server bridged that frustrating gap between theoretical concepts and practical application. It was "builder energy" at its finest, and it was contagious.

The Learning Highlights

My notebook was full by the end of the day. A few key takeaways that stuck with me:

  • Open Source is for Everyone: Praveen Das (Wikimedia Foundation) demystified the world of open source. He reminded us that our code doesn't just sit in a repo; it has the power to empower communities.

  • The AI Revolution: The sessions by Nitin Tiwari and Jay Thakkar were absolute highlights. Watching Gemini 2.0 Flash and Veo 3 in action during the "Sketch to Runway" session gave me a real glimpse into how fast the ML landscape is evolving. It wasn't just technical; it was creative.

  • Developer Productivity: Pankaj Rai’s deep dive into Firebase tools felt like a masterclass in how to build smarter, not harder. I left that session with a list of tools I wanted to try immediately.



The Community & The "Hallway Track"

The best part of DevFest is always the "hallway track"—the conversations you have between sessions.

A massive shoutout to Ankit Kumar Verma and the entire GDG Prayagraj team. Organizing an event of this scale is no small feat, and they created a welcoming, inclusive, and genuinely inspiring environment.



The Cherry on Top: The Swags 🎁

And yes, we can’t wrap this up without mentioning the iconic DevFest goodie bag. Getting that super cool mouse pad, filling my laptop lid with fresh stickers, and grabbing those cool badges was the perfect ending to the day. It’s always fun to take home a physical reminder of the energy and the memories we made.


Final Thoughts

DevFest didn’t just give me stickers and swag; it gave me momentum.

It provided fresh ideas, a better understanding of the tech landscape, and a strong reminder of why I love being part of this community. Here’s to more coding, more building, and more connecting. 🚀

Tags: #DevFest #GDGPrayagraj #Technology #Community #YearEndReflection #AI #GoogleDevelopers


Comments

Post a Comment

Popular posts from this blog

Few-Shot Prompting, RAG and Agents

  Summary In this post, I explore my Kaggle notebook “Few‑Shot Prompting, RAG and Agents,” which demonstrates how to build a context‑aware conversational agent by combining three advanced AI techniques: few‑shot prompting to guide the LLM with in‑prompt examples, Retrieval‑Augmented Generation (RAG) to ground outputs in externally retrieved documents, and agent orchestration via LangGraph to manage a multi‑step workflow. The notebook ingests domain texts, embeds chunks with Google’s embeddings API, indexes them in a FAISS vector store, constructs dynamic prompts using LangChain’s ChatPromptTemplate and few‑shot templates, and finally wires everything together into a runnable graph that can decide when to retrieve context and when to generate answers. 1. Few‑Shot Prompting Few‑shot prompting involves providing a handful of example input–output pairs directly in the prompt to steer the model’s behavior on new queries. By conditioning the LLM with 3–7 demonstrations, you can...
Read more

HauntHub - A 19th-Century Butler with 21st-Century Tech

🧟‍♂️ Stitching the Spirit: Engineering a "Frankenstein" AI Agent with Kiro & MCP Most AI hackathon projects are just chatbots with a fancy wrapper. For Kiro-ween the theme was 'Frankenstein,' so I took that literally. I didn't want another polished, polite chatbot. I wanted to stitch together a bunch of messy, incompatible tech stacks into something that felt alive—and maybe a little dangerous. We are currently living in the era of "Chat." We ask an LLM a question, and it gives us text back. But the future of AI isn't just about retrieval; it's about agency . It's about agents that can reach out of the chat window and touch the operating system, the file structure, and the hardware. For the Kiro-ween Hackathon , I entered the "Frankenstein" category with a specific goal: To stitch together incompatible technologies—Local File Systems, IoT simulation, and Reactive Frontend Animations—into a single, cohesive entity. The result is...
Read more