Gokul Suresh

@ManaevLab Thanks for the suggestion, @ManaevLab. I will surely do so. I'm happy for you to guide me. Thank you. If you have any tool or best practices recommendations, or anything I should study and try, please let me know.

@GokulSures39968 Good project for upskilling. One suggestion from running these: wire eval into the graph from day one, not at the end. The Dev agent's output needs a judge before the QA agent sees it, otherwise QA spends cycles on hallucinated code that should have been failed at gen time.

After months of research into Agentic AI, I am building Codegram: A Multi-Agent Software Incubator. 10+ agents (Architects, Devs, QA) build professional repos in parallel using LangGraph, Groq, and Gemini. Huge undertaking, but the upskilling is the goal. #AI #LangGraph

I haven't opened Stack Overflow in months. Traffic dropped 75% since ChatGPT launched. We're gaining speed but losing community knowledge. Who documents new problems if we all just ask AI privately? Not sure if this shift is better or just faster. @gokulofficial18602/the-moment-i-realized-something-had-fundamentally-changed-in-how-i-code-0b40ca0a9dab" target="_blank" rel="nofollow noopener">medium.com/@gokulofficial…

I've been using n8n for a year. Everything works great. So why am I considering Make.com? Tried Zapier—too limiting. But Make keeps coming up for complex Switching means rebuilding everything. Is it worth it? @gokulofficial18602/when-do-you-know-its-time-to-switch-automation-platforms-2909b2719601" target="_blank" rel="nofollow noopener">medium.com/@gokulofficial…

I saw a YouTube Short this morning about Google Labs and realized something embarrassing: I've been ignoring it for months. Not because it's obscure. Because I kept filing it away as " check later." So I finally explored it. Here's what I found. @gokulofficial18602/google-labs-the-experimental-playground-ive-been-ignoring-for-way-too-long-3324eff763e0" target="_blank" rel="nofollow noopener">medium.com/@gokulofficial…

The AI "bigger is better" era just hit a wall. 🛑 Samsung’s 7M Tiny Recursive Model is 100,000x smaller than giants but beats them on reasoning. How? It drafts & self-corrects up to 16x. 🧠 Accuracy over scale. Full deep dive: @gokulofficial18602/the-death-of-the-bigger-is-better-era-how-samsungs-7m-parameter-model-is-redefining-ai-e26dbce43c72" target="_blank" rel="nofollow noopener">medium.com/@gokulofficial…

Is the "bigger is better" AI era hitting a wall? Samsung’s new Tiny Recursive Model (7M params) just out-reasoned trillion-parameter giants on the ARC Prize 2025. It works like a dev: it doesn't just guess—it loops,checks its logic, and refines up to 16x Efficiency > Brute Force

@gokulofficial18602/the-2-billion-signal-why-metas-manus-ai-acquisition-marks-the-end-of-the-chatbot-era-4d3b86eab5ac" target="_blank" rel="nofollow noopener">medium.com/@gokulofficial…

Meta acquired Manus AI for $2B yesterday. Not because it's a better chatbot—because it's an autonomous agent that actually completes tasks. Wrote about why this is the biggest signal yet that AI is shifting from "thinking" to "doing." Curious what others are seeing

I gave my AI 1,000 docs and asked one question. It gave me a confident, detailed, and 100% wrong answer. The model wasn't dumb; it was just lost. No filing system. LlamaIndex fixed it. It’s the librarian that organizes the chaos. LlamaIndex or LangChain? What's your pick?

leetcode.com/problems/shuff… #newhabit

Great experience at Edition 24, UST Trivandrum (6 Dec 2025). Learned about cloud, edge & scalable workflows, met amazing developers, MNC pros & startup founders — and won 2 prizes 🎉 Thanks GDG Trivandrum & the organizers!#gdg #devfest2025 #ust #gdgcloud

#DevFest2025 #GDGTrivandrum #DevFestTrivandrum #gdg

Happening at UST Global #GDGTrivandrum #DevFestTrivandrum #gdg #devfest2025

Speakers are great #GDGTrivandrum #DevFestTrivandrum #gdg

@gdg #DevFest2025 #GDGTrivandrum #DevFestTrivandrum #gdg

What an amazing day at #GCCD2025 Trivandrum! 🧠 Learned from brilliant GDEs 🤝 Connected with startup founders 💻 Loved the Chrome DevTools AI session Huge thanks to @gdgcloudtvpm & @gdgindia for the experience. #GoogleCloud #DevTools #CloudCommunity #AI #Trivandrum

Want to dive deeper into everything I learned? Check out the full write-up here: 👉 @gokulofficial18602/mastering-ai-prompting-lessons-from-googles-start-writing-prompts-like-a-pro-7b187cf7cb0a" target="_blank" rel="nofollow noopener">medium.com/@gokulofficial… #PromptEngineering #AI #GenerativeAI #LLM #Coursera #GoogleAI

Prompt Types ✅ Zero-shot ✅ Few-shot ✅ Chain-of-thought ✅ Multimodal Each has a place — especially in real-world applications like chatbots, data analysis, and content creation.

Mastering AI Prompting – Lessons from Google's Coursera Course Prompt engineering isn’t just hype — it's the backbone of using AI effectively. I just completed Google’s “Start Writing Prompts Like a Pro.” Here’s what stood out 👇 (Full read ➡️ @gokulofficial18602/mastering-ai-prompting-lessons-from-googles-start-writing-prompts-like-a-pro-7b187cf7cb0a" target="_blank" rel="nofollow noopener">medium.com/@gokulofficial…)