Avatar for RedisTLV
Presented by
RedisTLV
66 Going
Registration
Welcome! To join the event, please register below.
About Event

โ€‹All talks will be delivered in Hebrew.

โ€‹โ€‹17:30-18:00 Pizza, beers and networking ๐Ÿ•๐Ÿบ

โ€‹18:00-18:30 From the Open Web to Redis: Context for Stateful Agents

โ€‹Stateful agents need two things - memory of what they've seen, and access to what's happening right now. Most teams build the memory and skip the web. I'll show how Bright Data turns the open web into clean, structured signal that agents can actually use, and how that signal pairs naturally with Redis for caching, vector search, and conversation memory. Concrete patterns, real numbers from a production MCP server, and a clear take on where each piece of agent context belongs.

โ€‹Speaker: Meir Kadosh, AI Engineer at BrightData

โ€‹18:30-19:00 Building Agents That Actually Remember

โ€‹We design AI agents with human-like personalities and emotions, yet they often suffer from "memory lapses," reverting to the limitations of their last token. In this session, weโ€™ll move beyond the "persona" to explore how to build persistent, institutional memory for our agents.
Weโ€™ll bridge the gap between human-like behavior and technical reality by covering:
- The Psychology of Memory: Why AI struggles to maintain context compared to human episodic memory.
- Evolving Memory Layers: How to use Cognee to ingest, structure, and reason over unstructured data.
- Production-Ready Memory: Using Redis as a stateful memory server to implement custom forgetting policies and shared context across agents.

โ€‹Speaker: Amit Rosen, AI Solutions Architect at Keshet Media Group

โ€‹19:00-19:30 RAG is not enough; Introducing Context Surfaces

โ€‹Weโ€™ll introduce Redis Context Engine - a new way to expose structured, real-time data to AI agents. Including Retriever, Memory and Caching for agents.
Weโ€™ll cover:

  • โ€‹Why unstructured context breaks down in production

  • โ€‹How agents move from retrieval โ†’ tool-driven reasoning

  • โ€‹Turning data models into queryable interfaces (MCP)

  • โ€‹What this means for building reliable AI systems

โ€‹Speaker: Itay Tevel, Principal Solutions Architect at Redis

Location
Alon Towers
Yigal Alon St 94, Tel Aviv-Yafo, Israel
Avatar for RedisTLV
Presented by
RedisTLV
66 Going