Jev reads the conversation text only to pick the model and effort. It runs under zero data retention (ZDR) terms, so nothing is stored or trained on. Attachments are never sent to Jev, and requests with "zdr: true" work with Jev Router.

Claude reads your codebase and design files to build your team's design system, then applies it automatically, keeping every project on-brand. Give it a try: Read more:

I am sure this reads well and appeals to many "ango-saxon" readers (and certain circles on the continent) who are apostles of creative destruction and the migration of Western economies out of high end manufactures to services ...

🧰 The agent reads a skill but can't find its tools. Or it calls a tool without ever reading how to use it. Deep Agents just fixed that mismatch. Title: Revamping Skills in Deep Agents URL: Skills have worked by progressive disclosure: only a name and description in the system prompt at startup, full instructions read on demand. Three upgrades now target registries running into the thousands of skills. 🔗 Binding tools to skills List tools under include_tools in the skill's frontmatter and they stay hidden until the agent reads that skill. Tools now go to SkillsMiddleware rather than to the agent. Hand the middleware a function that resolves labels to tools and you also get group-level disclosure and runtime permission gating. 📌 Pinned skills Even when a user explicitly asked for a skill with a slash command, the agent still had to read its description first. Passing it via pinned_skills lets the middleware drop the instructions into the conversation before the next model call, so the agent starts working on model call 1 instead of 2. Bound tools come along automatically. 🔄 Reloading mid-thread Skills used to be fixed at thread start, so long-running agents missed anything added or edited afterward. Setting skills_metadata to None invalidates the cached list and rescans the library, and the post shows wiring that to a client-side /reload. What ties all three together is where things get inserted relative to the prompt cache. Tools arrive as a new system message below the cached prefix, and each pinned skill is added once as a tagged message so earlier turns never change. #AIAgents# #LangChain#

2/ It reads my write-ups. "Is there a write-up on NVDA?" → finds it, sums it up, explains why I leaned that way, and tells you how old it is. For crypto, it checks my call against the live chart: did the stop hold, did it hit the target? ---