Context is King #4 – Building AI Agents on Real Data

Context is King is back for a fourth edition. After sold-out events in San Francisco and in the Nordics, we're continuing what makes this series work: real implementation stories from engineers building at the AI frontier.
The focus is on context engineering for AI agents: the discipline of designing what information an agent has access to and how it uses it. Context windows, tool use, memory, retrieval, MCP, agent harnesses — the playbook is being written in real time.
We're bringing engineers from companies building at the frontier to break it down. Expect implementation stories and live demos.

🎤 Talks & demos
Itai Smith, Member of Technical Staff, Chroma: Context-1

Bernardo García del Río, Co-Founder & AI Lead, Flow AI: Harness is King: How we specialized our harness for data-heavy analytical agents

Romain Sestier, Founder & CEO, StackOne: The integration layer for AI agents

Otso Veisterä, Founder, The Token Company (YC W26): Context compression without quality compression

Nathan Burg, Co-Founder & CPO, GitHits: Source-grounded context for coding agents

📅 Agenda
Doors open at 17:15
17:15 – 18:00: Networking with food and drinks
18:00 – 20:00: Presentations + Q&A
20:00 – 21:00: Networking
Doors close at 21:00

👋 About the organizers
Aiven makes it simple to build on open source data infrastructure - Kafka, PostgreSQL, ClickHouse, OpenSearch, and more - in all clouds. Run your apps where your data lives with Aiven Apps, and give your teams and agents the context they need with Aiven DataHub.
Flow AI builds the infrastructure layer that lets data and analytics SaaS companies deploy AI agents directly on their production data — with structured query execution, semantic data layer, and multi-tenant isolation.