OpenAI is finally tapping into MCPs As ChatGPT will be getting a custom connector option, which is likely similar to the recently added Remote MCP feature on Claude.
TOOLS
-
Perplexity introduces new Projects feature for AI-driven workflows
By
–
Perplexity is working on Projects! “Create plans, docs, apps and more”
-
OpenAI developing ChatGPT desktop feature for recording and transcribing meetings
By
–
OpenAI is working on a possibility for ChatGPT to Record, Transcribe and Summarise meetings. Sounds like it will be a desktop feature
-
Agent Inbox: Human-in-the-Loop Control and Oversight for Agents
By
–
Next up, Nick is back with a deep dive into Agent Inbox and the UI/UX around human in the loop interactions! A non-technical end user can use it to gain oversight into an agent's actions, accepting/editing/ignoring suggested actions as an agent runs! This human component
-
Agent Inbox: Human-in-the-Loop Control for Agent Actions
By
–
Next up, Nick is back with a deep dive into Agent Inbox and the UI/UX around human in the loop interactions! A non-technical end user can use it to gain oversight into an agent's actions, accepting/editing/ignoring suggested actions as an agent runs! This human component
-
Google reportedly planning Gemini Live integration for Chrome browser
By
–
Looks like Gemini Live will be coming to Chrome along with a “Personal AI” during Google I/O 2025. Google is planning to enter AI browser competition for real this time!
-
Google AI Studio Update: New Capabilities and Models Released
By
–
We just shipped an update to Google AI Studio which makes it easier to see new capabilities / models at the top level much more to come still!
-
LangSmith Evals: Build Production-Ready Agents with Confidence
By
–
Evals are a key part of bringing your agent from prototype to production Nick Huang shows how LangSmith evals and experiments give you confidence in the reliability of your agents! Define metrics and run against a dataset, or get started quickly with our pytest integration
-
LangSmith Evals: Moving Agents from Prototype to Production
By
–
Evals are a key part of bringing your agent from prototype to production Nick Huang shows how LangSmith evals and experiments give you confidence in the reliability of your agents! Define metrics and run against a dataset, or get started quickly with our pytest integration