Context graphs will be the best way for businesses to enable and deploy agentic harnesses. There's a lot of context fragmentation across so many different tools in every company. A god-mode view that self-improves and self-organizes is the way tacit knowledge can be captured.
AGENTS
-
Microsoft Teams introduces Viktor, first AI employee
By
–
An assistant helps. A chatbot replies. An employee delivers.
— Nico (@nicos_ai) 18 juin 2026
Meet Viktor, Microsoft Teams just crossed that line.
The first AI employee in Microsoft Teams: it remembers what your team has done, sees where you're headed, and turns conversations into finished work before you… https://t.co/WvsdLYFPK1An assistant helps. A chatbot replies. An employee delivers. Meet Viktor, Microsoft Teams just crossed that line. The first AI employee in Microsoft Teams: it remembers what your team has done, sees where you're headed, and turns conversations into finished work before you
-
Brain improves accuracy and reduces costs with full context
By
–
With Brain, the computer starts each task with the full context of your projects, decisions, and sources, instead of starting from scratch. On tasks that require past context, Brain improves answer accuracy by 25%, recall by 16%, and reduces costs by 13%.
-
Grok models now available on Databricks Agent Bricks
By
–
Grok models are now available on Databricks Agent Bricks.
— xAI (@xai) 18 juin 2026
Bring SpaceXAI's latest models to your enterprise data to power capable AI agents.https://t.co/BAjiDZnipq pic.twitter.com/GwLff8atiCGrok models are now available on Databricks Agent Bricks. Bring SpaceXAI's latest models to your enterprise data to power capable AI agents. https://
x.ai/news/grok-data
bricks
… -
GLM-5.2 free on Hugging Face via multiple inference providers for 6 hours
By
–
GLM-5.2 is free on Hugging Face Inference Providers via Zai, Together AI, Novita, Fireworks, DeepInfra for the next 6 hours. Configure it with Pi, opencode, Codex, Claude Code or any coding agent.
-
Making Depth Reusable by Looping World Models
By
–
“World Models in a Loop” World models require deep computations for stable long-horizon simulation, but deeper models are costly and errors accumulate over deployments. This paper makes depth reusable by looping
-
Anthropic fumbled badly with Claude Code last Christmas
By
–
Remember Christmas from 6 months ago when everyone was talking about Claude Code? Anthropic fumbled so bad it's actually crazy
-
Introducing Doc-to-LoRA at DLCT by Sakana AI
By
–
Sakana AI research scientist Rujikorn (Tan) Charakorn recently presented Doc-to-LoRA at @MLCollective’s DLCT journal club, covering hypernetworks, cost amortization, and future directions. A very lively discussion followed. Many thanks to the organizers! https://youtube.com/watch?v=jb_0XcBMJQU
-
Iteratively improve your agents for production with LangSmith
By
–
✅ Take your agent from first run to production-ready through iterative cycles of improvement.
— LangChain (@LangChain) 18 juin 2026
✅ Learn how to observe and evaluate agents with LangSmith
✅ Build reliable agents that last pic.twitter.com/pXS87Pk47xTake your agent from first run to production-ready with iterative improvement cycles. Learn to observe and evaluate agents with LangSmith. Build reliable agents that last.
-
How to Make Web Agent Skills Reusable
By
–
If you build web agents, this one is worth your time. It's on how to make agent skills reusable. (bookmark it) LLM web agents usually run as tool callers. Each turn, the model reads a fresh page and emits one low-level action, so horizons and policy-facing LLM completions both