# Operationalizing Agents with speakers from Google DeepMind, Snowflake, and Google Research co-hosted by Prolific and AI Circle
**Date de l'événement :** 27/05/2026
* Publié le 27/05/2026

### Date
27/05/2026

### Galerie d'image
![1.png](https://firebasestorage.googleapis.com/v0/b/memory-ai.appspot.com/o/prod%2FrKxsdSTpqCfzIFY8Y2hg%2FprojectsMedias%2Ffnd28Vj2PEusUbVionaH%2Fthumbs%2F1_1600x900.png?alt=media&token=b1e37728-8360-477a-8c9b-8024eb92ad37) 

### Ville
`#San Francisco` 

## Description
As foundation models begin to plateau in raw capability, the frontier is shifting toward building reliable systems: how agents are designed, deployed, evaluated, and improved in real-world environments.  
Agents introduce new layers of complexity: orchestration, memory, tool use, and multi-step reasoning. But without robust evaluation, feedback loops, and human-in-the-loop systems, even the most promising agents fail in production.  
The next wave of progress won’t come from better models alone, but from how we operationalize them.  
Join us for a closed-door conversation with leaders building and deploying agentic systems across research, startups, and enterprise.  
Speakers:  
  
Jaidev Shah - Senior Research Engineer at Google DeepMind working on Personalization and Memory. Connect with Jaidev.  
Aman Mehta - Senior Researcher at Snowflake. Connect with Aman  
Ivy Si - Multimodal Agents for Empirical Research at Google Research. Connect with Ivy.  
Moderator:  
Viviana Márquez - DevRel Engineer, Prolific. Connect with Viviana.  
  
Together, we’ll explore what it takes to move from demos to durable systems: how agents are evaluated, where they break, and how feedback, data, and infrastructure come together to make them reliable at scale.  
Topics will include:  
Designing agentic workflows and orchestration systems  
Evaluating multi-step reasoning and tool use  
Human-in-the-loop feedback and reward design  
Failure modes in production and how to mitigate them  
Building scalable evaluation pipelines for agents  
  
Agenda:  
5:30 – 6:00 — Arrival, networking, and refreshments  
6:00 – 6:10 — Welcome and introductions  
6:10 – 7:00 — Panel  
7:00 – 8:30 — Networking  
  
Attendance is limited and curated. Requests will be reviewed.  
  
About the hosts:  
Prolific powers high-quality human data for model evaluation and training. Learn more about Prolific.  
AI Circle curates high-agency operators across research, startups, and enterprise. Learn more about AI Circle.  
  
Our event will be hosted at the SignalFire office in SF. They raised a $1B fund last year focused on AI and data. Learn more about SignalFire.  
  
Limited capacity.  
Apply to attend.  
  
Marketing Disclaimer  
By submitting this form, you agree to receive marketing communications from SignalFire. You can unsubscribe at any time by clicking on the unsubscribe link at the bottom of our emails. See our privacy policy available on our website.

**Lien de l'évènement :** [https://luma.com/event/evt-ESC4WJiHSikNlT1](https://luma.com/event/evt-ESC4WJiHSikNlT1)

### Pays
`#United States` 

### Continent
`#North America` 

**Médias associés :**
[Média 1](https://80954c1d.sibforms.com/serve/MUIFABojU8UBbDiX_TdcGa7Wv5VMoVB_nBZ92mkLkGlS1pJLpP7s-pVJusyN-7cG9KPrSuv3fv7TmXwuw_AoyNUShR8jZhmNDgUbZPJO2V5xYXlNz4YXOTjSb8X7Lj7PRIPzgzEWlLbA4f4uw_F8RM51EUsjSfQQko0qaby98GHMdYJVWLIXd5JzzaXBGmqN2CcYOFuqnbnaYEnw) 

## event_id
evt-ESC4WJiHSikNlT1@events.lu.ma

### Outils
`#Snowflake` 

### Selection
`#Agents` 



---
### Navigation pour IA
- [Index de tous les contenus](https://ai-memory.io/llms.txt)
- [Plan du site (Sitemap)](https://ai-memory.io/sitemap.xml)
- [Retour à l'accueil](https://ai-memory.io/)