Results for “context engineering”

…the broader thesis that “systems talent is the moat.” Agentic engineering & “context engineering” replaces prompt-only thinking Context engineering framing: Weaviate draws the taxonomy: prompt engineering = phrasing, context engineering =…

…Intelligence. Retrieval, model architectures, and software engineering would all matter to LlamaIndex, though Liu qualifies the suggestion that his earlier ranking work was already RAG. LlamaIndex began with a concrete constraint: Liu…

…one" or "this number present onscreen" refer to, based on 3 contexts - 1) what's on screen, 2) entities relevant to the conversation, and 3) background entities. They enable all sorts of assistant-like usecases: Which is a challenging task …

…company’s own data. Both ideas support her emphasis on customer context and the slow work of changing how people operate. Guo argued that focused applications can tune a workflow to consume fewer tokens and retain the savings, while private…

…parallel writes, while long-horizon agents focus on context engineering and persistent file-centric workspaces.

…own data, rather than depending on a single model. Models, context, and customer control Nadella described Microsoft’s AI products as multi-model harnesses: systems that give models access to tools and rich context. He stressed the work…

…Unreasonably Difficult Interview Process00:17:14 Entropy and Context Engineering: The Future of AI Agents00:23:28 The MCP Debate and AI Industry Sociology00:26:01 Consulting, Digital Transformation, and Conference Insights

As of February 2026, Sherwin Wu led engineering for OpenAI’s API platform. His work includes collective credit for the 2023 function-calling launch and public technical explanations of how developers connect models to tools, evaluate agents…

…supply chain AI system @LangChainAI. @hwchase17 also mentioned context management in langgraph. Weave-Agent Planner Discussion: @jd_pressman discussed the design and planning of Weave-Agent, considering approaches like ReActTree and MuZero …

…Its proposed advantage is the platform’s existing application context: runtime data, error logs, preview deployments, development-server setup, and configured secrets. These integrations reduce the onboarding work needed to make an agent…

…current standard of 3-year lock-in contracts with hyperscalers. Context Engineering & RAG Systems: The importance of context engineering for RAG systems was a major topic. LangChainAI held a meetup on the subject, with @RLanceMartin sharing…

…become capabilities such as generating text or images. The engineering question is what those capabilities let a customer do. Putting a model into production can mean three different operating situations: - Hosted API: call a provider’s…