What if an AI could write its own blueprint to prove math theorems? Princeton researchers introduce Goedel-Architect, a new agentic framework for formal theorem proving in Lean 4. Instead of recursively decomposing lemmas (which can loop on dead ends), it first generates a
TOOLS
-
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
-
Managed Deep Agents: Solution for Production Execution
By
–
Building a useful agent is becoming easier. Running them in production remains difficult. We built Managed Deep Agents so your team can focus on agent behavior rather than rebuilding the execution environment around it.
-
Any LLM can run on Codex, not just OpenAI
By
–
WHAAAT?! TIL you can run any LLM on Codex A lot of devs (including me!) still thought Codex was completely locked into OpenAI's ecosystem. It isn’t. You can completely bypass the default models and run the exact stack you want for your workflow. Here is what the routing
-
Post sharing links to Deepeval and LangChain
By
–
Docs: https://
deepeval.com/integrations/f
rameworks/langchain#in-cicd-pytest
… GitHub Repo: https://
github.com/confident-ai/d
eepeval
… -
Pytest for AI Agents: Testing LangChain chains locally
By
–
Pytest for AI Agents! (100% open-source and runs locally) Building agents with LangChain means chaining LLMs, tools, and retrieval steps together. Each component can fail differently. The output changes with every run. Traditional unit tests don't work here because there's no
-
Worktreeinclude customizes files copied by codex for new trees.
By
–
Yup! There’s even a worktreeinclude to customize which files codex should copy when creating new trees.
-
Intense week for AI in biology: record deal and scaling
By
–
it's been a huge few weeks for ai in bio: a $2.25b @profluentbio x @elilillyandco deal on ai-designed gene editors, verve's base-editing data, new scaling results on protein models from @czbiohub, @isomorphiclabs' haul.@thisismadani and i recorded a pod diving into all of it… pic.twitter.com/QNAuGmsjQW
— Nathan Benaich (@nathanbenaich) 18 juin 2026It has been intense weeks for AI in biology: a $2.25 billion deal between @profluentbio and @elilillyandco on gene editors designed by AI, Verve's base editing data, new scaling results on protein models from @czbiohub, the