Building Better AI Agents: From Production Decisions to Agentic Search
Event PAST

Building Better AI Agents: From Production Decisions to Agentic Search

28 May Online

About this event

Building Better AI Agents: From Production Decisions to Agentic Search

AI agents are moving fast, but building them well still means making the right decisions: which frameworks to trust, when to rely on SDKs, how to structure tools, what to observe in production, and how to make agents search and retrieve information effectively.
In this Embrace:AI event, we’ll bring together two technical talks on what it actually takes to build useful, reliable AI agent systems beyond the hype.

Talk 1: Building AI Agents: A Year of Decisions That Actually Mattered

Speaker: Valiantsin Zavadski is co-founder of evy.so, a voice assistant for teams. He previously co-founded Narrative BI and Rubyroid Labs, has 20 years of experience in software, and has spent the last three years working deeply with production LLM systems.

In this talk, Valiantsin will share what he learned after a year building multiple production agents across different stacks. He’ll cover the choices that mattered, the ones that created unnecessary complexity, and when it makes sense to use frameworks versus dropping closer to the SDK.

Expect a practical developer retrospective with live comparisons, including LangChain vs CrewAI, MCP vs custom tools, and framework-based approaches vs raw SDKs.

Talk 2: What AI Agents Want from Search and How to Build It

Speaker: Philipp Pahl is co-founder and technical lead at peachstone.ai, an AI studio. He comes from a background in particle physics, machine learning, large data, and infrastructure projects.

Philipp will explore how search changes when the user is an AI agent reasoning through a task step by step.

He’ll explain recent developments in agentic search and retrieval, including reasoning-aware retrieval, reasoning-intensive retrieval, and late-interaction retrieval.

The talk will end with a live demo of a working agentic search system.

Supported by Quidgest
A special thank you to Quidgest for supporting spaces where people can learn, share knowledge, and explore the future of AI together.

Stay connected
Follow Embrace:AI on LinkedIn to keep up with future events, community updates, and conversations around AI, technology, and learning together.
https://www.linkedin.com/company/embrace-ai-event/

Want to find AI jobs?

Join thousands of AI professionals finding their next opportunity

We respect your inbox. Unsubscribe at any time.

© 2026 DevFound.ai. All rights reserved.

Common Questions

Frequently asked questions

Quick answers about how DevFound's AI matching, resumes, and referrals work.

DevFound's AI Copilot ingests your profile, goals, and live job data to deliver curated matches in seconds. Every match includes a resume variant, suggested referrals, and interview prep so you can act immediately. The more feedback you provide, the sharper the Copilot becomes.

AI-led job searches shrink the hours spent sifting through boards and formatting resumes. DevFound pairs automation with your personal outreach, so you reserve energy for interviews and negotiation. Traditional networking still matters, but AI gives you a lift before you even send a message.

Modern AI roles expect comfort with production-grade code, data fluency, and practical ML tooling. The strongest candidates pair deep technical chops with storytelling—translating model impact to product, GTM, and exec partners. Continuous learning keeps you ahead as stacks evolve.

DevFound rewards active seekers. Keep your profile fresh, respond to match quality prompts, and enable alerts so you never miss a role. The AI prioritizes companies and teams that align with your feedback, accelerating both introductions and interview invites.

High-density tech hubs continue to host the deepest AI talent pools, yet distributed teams are catching up fast. Use DevFound filters to hone in on onsite, hybrid, or fully remote roles and watch openings expand across time zones.

DevFound aggregates thousands of remote AI openings and flags the nuances—core hours, async culture, and visa needs—up front. The Copilot also recommends how to position your distributed work experience so hiring managers know you can thrive on a remote team.