Speak at The Fifth Elephant 2026 Annual Conference

Who will be consuming your data - humans or agents? When it’s agents, do you structure it differently? Optimize for token budgets instead of disk or query cost?

From what I see, we might not need clean, joined data (agents can do that), but descriptions of relationships. Functions become checklists. Tools beat tables. Logs beat docs. Ambiguity + context might work better than a single-source of truth.

In this workshop, we’ll (together) explore:

• How data engineering for agents is different than for humans
• How agents themselves can help engineer the data for agents

This session is for data/AI engineers who are using agents or whose work agents will be using.

Anand is an LLM psychologist at Straive and co-founder of Gramener, a data stories company. He’s listed among India’s top 10 data scientists and AI influencers and is a regular TEDx/Pycon speaker. More importantly, he hand-transcribed every Calvin & Hobbes strip ever, is addicted to Minecraft & Anime (thanks to his daughter), and dreams of watching every film on the IMDb Top 250 (except The Shining). He blogs at s-anand.net.

{Add the link to draft slides - PDF/PPT - with comments access - TODO: at least a TOC or blog series}

{Add the link to 2-min elevator pitch video - Um... will skip, please? Or... wait -- I’ll have an AI generate it?}