Edition 03 · 2026

Talks 2026.

The programme unfolds talk by talk, grouped by theme. Announcements continue week after week.

Schedules and rooms will be announced soon.

01

Data Foundations for Humans & AI

Data platforms now serve two kinds of consumers: people and machines. Analysts and business teams still need trusted, well-modeled data, and a fast-growing population of LLMs and agents needs it too, with even less tolerance for ambiguity. This theme covers the foundational work that makes data consumable, trustworthy, and affordable for both.

  1. (Re)Building an AI-Ready data universe
    EN
  2. Data Quality at Scale: Building a Robust Framework for Complex data Models
    FR · EN
  3. DuckDB, dbt, and the Death of Pipeline Glue
    EN · FR
  4. From the Gold layer to a federated knowledge graph: Decathlon's journey
    FR
  5. How a Small Data Platform Team Serves 2,000 People — with Self-Service and AI
    FR · EN
  6. Towards self-serve analytics: a year of data transformation at leboncoin
    FR
02

Agentic Systems Engineering

Models stopped being the hard part. The engineering around them, context, memory, evaluation, orchestration, security, cost, is where AI systems succeed or fail in production. This theme is for the builders of those systems.

  1. Context engineering for analytics agents that actually work
    EN
  2. Context Engineering for Large-Scale Product Search
    EN
  3. How to build a context factory for analytical agents
    EN
  4. LLM inference : What actually happens in the 2 seconds after you hit enter on Claude
    Lightning EN
  5. Malt field report: from experimentation to production, adapting your observability infrastructure for generative AI
    Long Talk FR
  6. One Agent Is a Feature. Three Agents Are a Platform.
    EN
  7. The AI FinOps levers that actually move your LLM bill
    FR
03

Engineering Shifts

AI is transforming engineering work itself. Whatever you build, pipelines, analytics, software, or product features, your craft is changing. This theme gives each engineering practice its own stage, with one requirement: tell us what changed for real, in a real team.

  1. Analytics that builds the platform: say goodbye to Ticketing 2.0 with agents in the git repo
    FR
  2. How we use agents to 10x our data team
    EN
  3. The Agent OS: a harness to survive a $100M to $400M year
    EN
  4. The Next Data Stack Has No UI: Building End-to-End Analytics with Agents and Ducks
    EN
04

Leading the AI Shift

Most Data & AI transformations stall on organizational questions: enablement, accountability, operating model. This theme is for the leaders working through them, with real numbers to share.

  1. AI will make your organization obsolete. If you have one
    EN · FR
  2. Building the AI factory: the operating-model shifts behind Doctolib's AI products
    FR · EN
  3. The future of data governance in the age of AI agents
    FR
  4. What do Job Descriptions tell us about Analytics Engineering in 2026?
    Lightning EN