Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Background Agent (Preview) "a remote, asynchronous agent that runs outside the main Cursor editor in a remote containerized environment. It allows you to offload long-running or complex task" works best for tasks that require less human interaction like fixing simple bugs, small features, or long changes more information about... show more

Melvin Vivas

21,937 subscribers

81,372 views • 1 year ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

13 Comments

Melvin Vivas1 year ago

cursor v0.50 is here lots of juicy features here's all the features you need to know 🧵 👇

Melvin Vivas1 year ago

Simpler, unified pricing for @cursor_ai – All model usage now on request-based pricing – Max Mode adopts token-based pricing (like model APIs) – Premium tool calls & long context mode removed

Melvin Vivas1 year ago

Max Mode for all top models (token-based) max mode is ideal for harder problems which require more context, intelligence and tool use @cursor_ai

Melvin Vivas1 year ago

Include your entire codebase in context use @ folders to add your entire codebase into context @cursor_ai

Melvin Vivas1 year ago

Inline Edit(Cmd/Ctrl+K) Refresh Supports full file edits. Full file edits makes it easy to do scope changes to a file without using agent You can also send the code block to the agent for multi-file edits @cursor_ai

Melvin Vivas1 year ago

Fast edits for long files with Agent Agent can now find the exact place where edits should occur and change only that part @cursor_ai

Melvin Vivas1 year ago

Workspaces Work across multiple codebases in one session

Melvin Vivas1 year ago

Exporting Chat You can now export chats to a markdown file. This is useful when you want to get advise from other AI about your code using the conversation you already have with @cursor_ai

Melvin Vivas1 year ago

Duplicate Chat Useful when you want to fork a chat and explore different options @cursor_ai

Melvin Vivas1 year ago

like this update? support me by reposting this thread 👇 you can also follow me @donvito for more AI

Melvin Vivas1 year ago

FYI, this is dropping in cursor 0.50 as well — added after I posted this thread Tab to edit other files — perfect for refactoring Tab suggestions also now have syntax highlighting!

Melvin Vivas1 year ago

Here's how you enable Background Agents

MightyBot1 year ago

🧠 Unified Search. Smarter Meetings. Effortless CRM. MightyBot is your AI agent platform for seamless workflows—record meetings, automate CRM updates, and find answers across apps in seconds. 🌟 Focus on what matters. We'll handle the grind.

Related Videos

You can now delegate tasks to Cursor directly from Notion. It's built on the Cursor SDK, so every cloud agent runs on the same models, harness, and runtime that power Cursor. @Cursor on any spec or assign it a task to open a PR your whole team can review.

You can now delegate tasks to Cursor directly from Notion. It's built on the Cursor SDK, so every cloud agent runs on the same models, harness, and runtime that power Cursor. @Cursor on any spec or assign it a task to open a PR your whole team can review.

Cursor

322,004 views • 2 months ago

🚨 Cursor for writing is here! 📝 Meet the HyperWrite document editor. A next-gen agent-driven editor that: - Searches + writes naturally - Applies changes for you - Incredible autocomplete as you type - Generates rewrites - Pulls in your relevant docs How to try it:

🚨 Cursor for writing is here! 📝 Meet the HyperWrite document editor. A next-gen agent-driven editor that: - Searches + writes naturally - Applies changes for you - Incredible autocomplete as you type - Generates rewrites - Pulls in your relevant docs How to try it:

Matt Shumer

66,785 views • 1 year ago

Anthropic is rolling out Dispatch, a major new update for Claude Cowork that turns your mobile phone into a remote control for your desktop AI agent. Currently in research preview, this feature allows you to assign complex, multi-step tasks to Claude while you are away from your keyboard, and it will execute them using your computer's local resources.

Anthropic is rolling out Dispatch, a major new update for Claude Cowork that turns your mobile phone into a remote control for your desktop AI agent. Currently in research preview, this feature allows you to assign complex, multi-step tasks to Claude while you are away from your keyboard, and it will execute them using your computer's local resources.

Wes Roth

13,281 views • 6 months ago

cursor continues to curate the most frictionless way to build software. - planned a new app idea with Cursor Agent (Laptop) - left cafe for gym so i hand off to Cloud Agent (Cloud) - mid workout, i get an msg that my PR is done (Email) - mid pump, i get a new idea. message Cursor via iphone to add it - monday morning comes. i already forgot about my app - cursor emails me w/ a 30 sec demo of agent clicking through the core feature. shows me that it works if you showed me this in 2022, i would have put my life savings into cursor stock immediately

cursor continues to curate the most frictionless way to build software. - planned a new app idea with Cursor Agent (Laptop) - left cafe for gym so i hand off to Cloud Agent (Cloud) - mid workout, i get an msg that my PR is done (Email) - mid pump, i get a new idea. message Cursor via iphone to add it - monday morning comes. i already forgot about my app - cursor emails me w/ a 30 sec demo of agent clicking through the core feature. shows me that it works if you showed me this in 2022, i would have put my life savings into cursor stock immediately

shawn

13,123 views • 5 months ago

Introducing a coding agent that documents every code file in a GitHub repo in minutes!⚡ It keeps docs up to date by updating when the code changes, and you can also read and chat with the docs directly in Cursor or VSCode.

Introducing a coding agent that documents every code file in a GitHub repo in minutes!⚡ It keeps docs up to date by updating when the code changes, and you can also read and chat with the docs directly in Cursor or VSCode.

Felix Waweru

14,573 views • 1 year ago

Cursor for video editing is here. The new Underlord agent from is insanely good at automating edits. Upload a clip and describe what you want changed - like "cut out pauses and filler words" or "add captions." The agent does it for you. A quick example 👇

Cursor for video editing is here. The new Underlord agent from is insanely good at automating edits. Upload a clip and describe what you want changed - like "cut out pauses and filler words" or "add captions." The agent does it for you. A quick example 👇

Justine Moore

36,723 views • 1 year ago

I think I finally found the sweet spot for long-running AI coding tasks: GLM 4.7 feels like Sonnet, costs ~20× less, and runs forever without melting your budget. Pair it with a good agent setup and it quietly does real work.

I think I finally found the sweet spot for long-running AI coding tasks: GLM 4.7 feels like Sonnet, costs ~20× less, and runs forever without melting your budget. Pair it with a good agent setup and it quietly does real work.

Mervin Praison

98,539 views • 8 months ago

Last, but not least, don't sleep on this one: Le Chat now has Work mode (Preview) — a powerful agent for complex long-horizon tasks like research, analysis, and actions across your connected tools. Connectors are on by default so the agent pulls context from docs, email, and calendars as it works, and sessions persist across many turns until the task is complete.

Last, but not least, don't sleep on this one: Le Chat now has Work mode (Preview) — a powerful agent for complex long-horizon tasks like research, analysis, and actions across your connected tools. Connectors are on by default so the agent pulls context from docs, email, and calendars as it works, and sessions persist across many turns until the task is complete.

Vibe

34,302 views • 4 months ago

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

Santiago

17,438 views • 2 months ago

Agent mode is now available in public preview for all users in Visual Studio 17.14. Agent mode in Visual Studio allows you to define tasks using natural language, with Copilot autonomously planning, editing your codebase, invoking tools, and iterating to resolve issues. Unlike Copilot Chat or Edits, agent mode doesn’t stop at one suggestion or file edit. Read more about it in our blog. 📖 #visualstudionews #githubcopilot #agent

Agent mode is now available in public preview for all users in Visual Studio 17.14. Agent mode in Visual Studio allows you to define tasks using natural language, with Copilot autonomously planning, editing your codebase, invoking tools, and iterating to resolve issues. Unlike Copilot Chat or Edits, agent mode doesn’t stop at one suggestion or file edit. Read more about it in our blog. 📖 #visualstudionews #githubcopilot #agent

Visual Studio

93,284 views • 1 year ago

Replicas is a background coding agent that lives in sandboxed VMs and works like a teammate: it runs codebases locally with all your dependencies and tooling, iterates until it's satisfied, and opens a PR. Delegate to it from Slack, Linear, or GitHub. Congrats on the launch, Connor Loi!

Replicas is a background coding agent that lives in sandboxed VMs and works like a teammate: it runs codebases locally with all your dependencies and tooling, iterates until it's satisfied, and opens a PR. Delegate to it from Slack, Linear, or GitHub. Congrats on the launch, Connor Loi!

Y Combinator

22,332 views • 5 months ago

Sick of Cursor mess up your code? This new flow reduced 90% error for my Cursor - by adopting a task system: 1. Break down PRD into small tasks with dependencies 2. Maintain & update task list as we go 3. Self improve with cursor rules With tools like claude task master & Boomerang tasks, this process is a no brainer I broken down my step by step process in the video If you want to learn more about vibe coding beyond basics, join my community here: (also get free access to 10xCoder.Dev)

Sick of Cursor mess up your code? This new flow reduced 90% error for my Cursor - by adopting a task system: 1. Break down PRD into small tasks with dependencies 2. Maintain & update task list as we go 3. Self improve with cursor rules With tools like claude task master & Boomerang tasks, this process is a no brainer I broken down my step by step process in the video If you want to learn more about vibe coding beyond basics, join my community here: (also get free access to 10xCoder.Dev)

Jason Zhou

43,014 views • 1 year ago

Progress in open models is keeping Big AI labs up at night, and I'm here for it! We have a brand new open-weight multimodal model optimized for long-horizon tasks. This model is really good at something: it can work on tasks that keep evolving over time. • 280B total parameters, but only 16B active • 512K context window • Understands text, images, and audio • Strong reasoning, coding, and tool use But the best of all: the model learns and adapts to new information! Imagine you start running an agent today to solve a problem, and while it's working, you get new information that changes the initial conditions, or you change your mind. The agents you run today don't have issues with short tasks and goals that don't change, but reality is messy, and that makes it hard for long-horizon agents to succeed. The new dots3-note Preview model introduces TEMPO. TEMPO is a new reinforcement learning technique that lets the model periodically pause and critique its own progress. Basically, from time to time, the agent asks itself: "Am I getting closer to the goal, or am I wasting my time?" The same model switches between actor and critic. The actor works on the problem. The critic looks at the current state, reasons about how much progress it has made, and determines what should happen next. TEMPO gives the model feedback along the way. This is huge for any agent that can work on long-horizon tasks without wasting its time.

Santiago

80,792 views • 25 days ago

working with cloud agents in cursor feels the same as local, but the fact that i can shut down my computer and still have it running is amazing. one of my favorite use cases is planning in cursor, then send off to cloud agent for impl. here's a short demo

working with cloud agents in cursor feels the same as local, but the fact that i can shut down my computer and still have it running is amazing. one of my favorite use cases is planning in cursor, then send off to cloud agent for impl. here's a short demo

eric zakariasson

61,966 views • 10 months ago

we are working on OpenControl - a library that uses AI to finally solve the headache of internal tooling idea is simple - define a set of tools in code that can reference functions from your codebase or anywhere else these tools get deployed to your infra (runs anywhere, lambda, worker, containers, etc) and exposes a protocol that allows clients like cursor, claude-code, etc to use them they can orchestrate tasks like "can you reset the password of anyone who hasn't logged in a year" demo below and details on how it works in the thread

we are working on OpenControl - a library that uses AI to finally solve the headache of internal tooling idea is simple - define a set of tools in code that can reference functions from your codebase or anywhere else these tools get deployed to your infra (runs anywhere, lambda, worker, containers, etc) and exposes a protocol that allows clients like cursor, claude-code, etc to use them they can orchestrate tasks like "can you reset the password of anyone who hasn't logged in a year" demo below and details on how it works in the thread

dax

109,046 views • 1 year ago