Anand S

Anand S

@sanand0

Mining Digital Exhaust

Submitted Oct 8, 2025

Every day, we leave behind a trail of digital exhaust — browser histories, search queries, command-line logs, chat messages, fitness data, and more. This workshop transforms that overlooked byproduct into a playground for insight. You’ll extract your own digital traces (or choose anonymized samples), explore them through data analysis, and use large language models to automatically generate meaningful stories and predictions.

Through a hands-on, “vibe-coding” experience, we’ll explore how to treat code as a byproduct rather than an artifact — letting LLMs generate, test, and narrate analyses in real time. You will compare results across peers, model scenarios, and uncover patterns in your own behavior or environment. The emphasis is on creativity, reflection, and understanding the power of personal data — not just in analytics, but in storytelling and self-awareness.

Key Takeaways:

  • Discover how everyday digital byproducts — from search logs to chat histories — can become valuable sources of insight and self-knowledge.
  • Learn innovative ways to use LLMs across the data value chain: preparation, analysis, visualization, and narrative generation — using “code on demand” as a creative medium.
  • (Optional extension) Build micro-stories or dashboards that compare your digital patterns with others’, revealing shared habits or unique quirks.

Ideal Audience:

  • Data enthusiasts, analysts, and storytellers who want to experiment with unconventional, personal data sources.
  • AI practitioners curious about using LLMs for analysis and creative data exploration.
  • Educators, designers, and researchers exploring personal informatics, digital well-being, or data ethics.
  • Programming knowledge helps but is not required — curiosity and openness to experimentation are the only prerequisites.

Anand is an LLM psychologist at Straive. He co-founded Gramener, a visual data company that Straive acquired. He is considered one of India’s top 10 data scientists and is a regular TEDx/PyCon speaker.

He has hand-transcribed every Calvin & Hobbes strip ever and dreams of watching every film on the IMDb Top 250.

He blogs at https://s-anand.net. His talks are at https://bit.ly/anandtalks

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Hosted by

Jump starting better data engineering and AI futures