Multi Modal AI Forum
An exclusive meetup connecting AI experts across Vision, Voice, and Text.
Join TechSee for an evening of hands-on discussion with practitioners building multimodal AI. We'll talk about how to benchmark, audit, and validate multimodal models and agentic workflows, then split into small groups to work through real-world challenges.
AGENDA
19:30–20:00 | Gathering
20:00–20:05 | Opening Remarks Renan Schilman, VP R&D & Product, Home Business Unit, TechSee
20:05–20:15 | The Right Questions for AI Answers Restoring methodology to modern AI: How to benchmark, audit, and validate multimodal models and agentic workflows.
20:15–21:15 | Interactive Workshop: Multimodal Challenges Small groups tackling real-world challenges: designing multimodal AI workflows to fit your use case and your data.
🧩 Bring your own challenge
The workshop is built around YOUR use cases. When you register, you’ll be invited to submit a real-world challenge for us to tackle together in small groups.
What makes a great case:
• It combines more than one modality, e.g., vision + voice, images + text, video + audio
• It solves an everyday, real-life pain point
• In 2–3 sentences: what you’re trying to solve, what data you have, and where it breaks
Example: Traffic jams. Combining live road cameras with drivers’ voice reports to predict congestion and reroute in real time.
Selected cases will be tackled at the workshop. Optional, but highly encouraged!
SPEAKERS
Dr. Irit Opher, Research and Innovation Leader
Omer Lerinman, CEO, Agentiqu
Seats are limited. Registration is subject to approval.
Hosted by TechSee