Two weeks of dogfooding Engram, Weaviate’s memory product, in daily Claude Code sessions. This surfaced where a dedicated memory product adds value, and the specific mechanics that prevent integration with coding assistants from working well.
Memory isn’t just a feature for AI applications—it’s infrastructure. As agents scale, the limited loop of stateless interactions breaks down, and continuity becomes a systems problem that requires active maintenance.
Context engineering is how AI agents manage LLM memory—selecting, retrieving, and organizing context from short-term and long-term memory to improve reliability in production.
Hands-on patterns: Design pattern for gen-AI enterprise applications, with Arize AI.
A strategic guide to the costs, risks and rewards of upgrading embedding models in production AI
Hands-on patterns: LLM-as-Judge with LangChain and W&B
Learn how chunking strategies improve LLM RAG pipelines, retrieval quality, and agent memory performance across production AI systems.
Get spun around by our new vector quantization algorithm that utilizes the power of random rotations to improve the speed-quality tradeoff of vector search with Weaviate.
Evals and Guardrails in enterprise workflows part 1
Key consideration for customizing an embedding model through fine-tuning it on company- or domain-specific data to improve the downstream retrieval performance in RAG applications.