Vibe Analysis Workshop Recap

Who joined

On 16 September, 20+ participants — senior engineers, data scientists, analysts, and engineering leaders from companies such as Intenwise, Accenture, Google, Toast, Citi India, VideoVerse, Aftershoot, and PracticeNow — joined the workshop, both in-person and remotely.

What they learned

By live-prompting LLMs, participants got hands-on with the entire data workflow:

• Exploring datasets and generating hypotheses
• Writing and running code with Codex
• Building and comparing ML models
• Visualizing results as charts
• Exposing models as APIs
• Designing prompts, chaining tools and sub-agents, and even generating prompts from spoken language

In short: participants experienced how LLMs can supercharge data analysis and applied it directly to “vibe analysis.”

What participants said

“Anand, through his deep knowledge and lucid explanations, showed us how LLMs can transform data analysis—from hypothesis testing to building agents and minimizing hallucinations. The workshop was paced well, even for remote participants like me. My key takeaway was how BI and data analysis are evolving in the AI age, and how using multiple models can improve accuracy.”
— Ambarish

“Yesterday’s workshop was a first for me—it cut through the hype and showed how ‘vibe coding’ applies in analytics and data science. Anand walked us through the full lifecycle: raw data → hypotheses → AI testing with Codex → refined, business-ready insights. My biggest takeaway: start small, get your hands dirty, and the real learning will follow. Outstanding workshop!”
— Anindo Chakraborty

About the instructor

S Anand — self-styled LLM psychologist at Straive — co-founded Gramener, a data science company that narrates visual data stories, later acquired by Straive. He has also hand-transcribed every Calvin & Hobbes strip and dreams of watching every film on the IMDb Top 250.

Resources

📑 View the slides - https://sanand0.github.io/talks/2025-09-16-vibe-analysis/