New Frontier Red Team blog: Phase 2 of Project Fetch, where we test how well Claude can program a robodog. Opus 4.7, on its own, was ~20x faster than last year's best human team aided by Opus 4.1. (The robodog, alas, still failed to fetch a beach ball.)
AUTOMATION
-
Context Graphs: Best Way for Businesses to Deploy Agentic Harnesses
By
–
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.
-
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%.
-
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
-
LFM2.5-ColBERT-350M reliably selects top 5 tools from 151
By
–
LFM2.5-ColBERT-350M is a surprisingly reliable smart tool selector.
— Maxime Labonne (@maximelabonne) 18 juin 2026
We gave it 151 tools, and it consistently surfaces the 5 most relevant ones based on the user prompt.
This saves tokens and improves accuracy. Ideal for hmmmm agentic edge models? 👀 pic.twitter.com/IPyizctesULFM2.5-ColBERT-350M is a surprisingly reliable smart tool selector. We gave it 151 tools, and it consistently surfaces the 5 most relevant ones based on the user prompt. This saves tokens and improves accuracy. Ideal for hmmmm agentic edge models?
-
Technology integrated into human collaboration via Viktor in Teams
By
–
I like when technology is placed inside the flow of human collaboration, where people already work together every day.
— Antonio Grasso (@antgrasso) 18 juin 2026
Viktor brings this idea into Microsoft Teams as an AI employee designed to support the team in its everyday work.@viktor__com Partner. https://t.co/BpYcuvjRqRI like when technology is integrated into the flow of human collaboration, where people already work together every day. Viktor embodies this idea within Microsoft Teams as an AI employee designed to support the team in its daily work. @viktor__com
-
Viktor, AI employee for Microsoft Teams, reads 3,000 tools
By
–
Microsoft Teams users can now hire Victor as an AI employee to get support with their goals.
— 🚨 AI News | TestingCatalog (@testingcatalog) 18 juin 2026
Viktor can read from and write to more than 3,000 tools and maintain persistent memory across sessions, so it picks up where a team left off instead of starting over each day.
Zeta… https://t.co/2cr7KzSmN1 pic.twitter.com/dapOAicUruMicrosoft Teams users can now hire Viktor as an AI employee to get support in achieving their goals. Viktor can read and write in more than 3,000 tools and maintain a persistent memory between sessions, so that
-
Viktor, shared AI agent, arrives in Microsoft Teams
By
–
Viktor is now showing up in Microsoft Teams, Agents are thus entering the next significant work environment.
— Chubby♨️ (@kimmonismus) 18 juin 2026
The promise is exciting: one AI the whole team shares, that remembers your work and ships finished output, not just answers.
They proved that on Slack and reached… https://t.co/Vdi9QTRRhNViktor now appears in Microsoft Teams, agents thus enter the next significant work environment. The promise is exciting: a single AI that the whole team shares, that remembers your work and delivers finished results, not just