Join our webinar on Tuesday 22 Sep.
Most AI rollouts stall in the same place: the agent has no access to what the company already knows.
45 minutes with @tricalt on building a company brain from @SlackHQ , @github , @linear and your @googledrive.
20:00 CEST
Register:
Berlin to San Francisco is 9,108 km. My talk was 5 minutes long, in front of 20k people, for @BerkeleyRDI Xcelerator !
Worth it? 1000%
Why? Because we believe there should be an alternative to Anthropic and OpenAI holding all your data.
Six people, five minutes each, and a room that actually wants to see what you built.
Bring Your Own Demo Night with @qdrant_engine and @cognee_ . Berlin, Wed 16 Sept, 18:30.
45 min networking, 15 min @qdrant_engine , 30 min demos, then games.
Register here:
Join us tonight in Berlin.
An evening on the extraction layer behind agent memory with @fastinoAI. GLiNER2 doing entity and relation extraction on CPU, @COGNEE turning it into a graph, live on stage.
18:00 doors, 19:00 talks.
Still open: luma.com/xsax8h6w
Agent memory quality depends on extraction quality. If extraction is slow, expensive, or imprecise, everything downstream inherits those problems: retrieval, reasoning, recall.
Come spend Thursday evening on that with @cognee_ and @fastinoAI in Berlin.
Mary Newhauser shows
