WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 9, 2026 • Session details

3 Ways to Rebuild the Data Stack for Agents

Jordan Tigani

The modern data stack is obsolete for AI agents. Discover how ditching rigid UIs for token-optimized CLIs and programmatic pipelines fundamentally transforms autonomous data querying.

Pause
Mute Enter Fullscreen
#1 about 3 min

Transitioning from AI co-pilots to AI-native products

The shift from bolting AI onto human interfaces to building for LLMs as primary users.

#2 about 1 min

Overview of MotherDuck and serverless DuckDB infrastructure

MotherDuck runs faster, less expensive cloud queries built on DuckDB for applications.

#3 about 2 min

How LLMs imitate human data discovery behavior

Large language models can now explore datasets and write SQL through trial and error.

#4 about 2 min

Collapsing the modern data stack with AI models

The traditional segmented stack of ingestion and transformation merges into unified vibe-codable tasks.

#5 about 2 min

Replacing complex BI dashboards with live LLM queries

AI models can generate better live embedded visualizations than traditional business intelligence platforms.

#6 about 1 min

Leveraging scale-to-zero hypertenancy for AI agents

Running DuckDB allows every agent instance to independently scale while ensuring seamless cloud scaling.

#7 about 2 min

Why low-code interfaces hinder autonomous AI agents

LLMs perform better when allowed to write Python pipelines instead of using constrained graphical wizards.

#8 about 3 min

Integrating Model Context Protocol for non-technical users

MCP enables instant authentication and cloud application control directly from AI chat systems.

#9 about 3 min

Passing execution context using RAG and markdown guides

Passing exact product constraints and markdown skills reduces redundant parsing steps for inference engines.

#10 about 1 min

Minimizing token usage with the Tune data format

Replacing verbose JSON with Tune formatting drastically decreases parsing tokens and improves system accuracy.

#11 about 2 min

Balancing Model Context Protocol with direct CLI tools

Chaining local command line tools prevents expensive roundtrips and handles raw data better than MCP.

#12 about 2 min

Designing CLI command hierarchies for AI comprehension

Verbose and descriptive command structures allow LLMs to discover capabilities without polluting context windows.

#13 about 2 min

Enabling autonomous agent account signups and provisioning

Structuring deployment commands so agents can provision their own cloud accounts without human intervention.

#14 about 1 min

Constructing multi-step evaluations for agent reliability

Tracking token expenditure and multi-stage intent resolution requires custom built multi-step evaluation harnesses.

#15 about 5 min

End-to-end autonomous data workflow and dashboard demonstration

An LLM independently configures a warehouse, ingests S3 variables, and engineers an interactive dashboard.

#16 about 1 min

Lessons learned in token efficiency and backward compatibility

Redesigning products for agents requires focusing on resource efficiency and embedding changes directly into documentation.

#17 about 1 min

Comparing JSON and Tune formats during audience questions

Structure-agnostic models parse plain Tune format contents more accurately than strictly nested JSON structures.

Matching moments

1:22 min

Leveraging the comprehensive generative artificial intelligence stack

Duan Lightfoot Duan Lightfoot · World Congress 2024

1:30 min

Locating AI agents within the broader machine learning landscape

Jörg Neumann Jörg Neumann · World Congress 2025

2:04 min

Inspiration and challenges of scaling AI agent communication

diabhey diabhey · World Congress 2025

7:07 min

Exploring AI agent usage within the software engineering industry

Chris Heilmann +2 · LIVE

1:32 min

Building autonomous functions with conversational agent frameworks

Modood Alvi · World Congress 2025

2:38 min

The evolution toward agentic and literate software programming

Neel Sundaresan Neel Sundaresan +1 · World Congress 2026 Europe

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
3 months ago

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan, Sead Ahmetović

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41
3 months ago

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06
3 months ago

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13
3 months ago

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23
3 months ago

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26
3 months ago

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert, Karin Krobath

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 25, 2026 · 09:00–09:30

Stage 7

AI Agents are Only as Smart as their Context: Building a Real-Time Context Engine

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel
Open session

World Congress 2026 North America

September 24, 2026 · 14:50–15:20

Stage 7

When Agents Became Users: Rearchitecting Identity and Permissions for AI at Scale

Yoav Gal

Product Lead

Yoav Gal
Open session

World Congress 2026 North America

September 24, 2026 · 12:10–12:15

Outdoor Stage

Can AI Agents Actually Discover and Use Your Product? Agent-Led Growth and Agent Experience.

Jun Liang Lee

CEO at Lightsage

Jun Liang Lee
Open session

World Congress 2026 North America

September 24, 2026 · 17:30–18:00

Stage 6

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong
Open session

World Congress 2026 North America

September 24, 2026 · 11:00–11:30

Stage 5

The Missing Infrastructure for AI Agents

Chris Waterson

CTO of Guild.ai

Chris Waterson
Open session

World Congress 2026 North America

September 24, 2026 · 11:40–12:10

Tech Leaders Stage

Rethinking Developer Tools for the Agent Era

Han Wang, Sam Bhagwat, Ben Haefele, Ignacio Riesgo

Han Wang
Sam Bhagwat
Ben Haefele
Ignacio Riesgo

Related videos

When Should You Use an Agent? Architectural Trade-offs in Agentic Systems thumbnail
32:48
World Congress 2026 Europe • 3 months ago

When Should You Use an Agent? Architectural Trade-offs in Agentic Systems

Matheus Guimaraes

On a Secret Mission: Developing AI Agents thumbnail
29:03
World Congress 2025 • about 1 year ago

On a Secret Mission: Developing AI Agents

Jörg Neumann

Headless by Design: Building Enterprise Systems That Agents Can Actually Use thumbnail
23:52
World Congress 2026 Europe • 3 months ago

Headless by Design: Building Enterprise Systems That Agents Can Actually Use

Dirk Gronert

What 500+ Production Environments Taught Us About Shipping AI Agents thumbnail
23:05
World Congress 2026 Europe • 3 months ago

What 500+ Production Environments Taught Us About Shipping AI Agents

Liran Hason

Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP thumbnail
25:32
World Congress 2025 • about 1 year ago

Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP

Viktoria Semaan

AI Agents & Agentic AI thumbnail
26:53
Europe 2026 Virtual • 3 months ago

AI Agents & Agentic AI

Xavier Sala Presas

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.