eric zakariasson's banner
eric zakariasson's profile picture

eric zakariasson

@ericzakariasson85,270 subscribers

tinkering @spacexai, prev @cursor_ai

Shorts

orchestrate a swarm of agents here's a visualization of the swarm and how it's using multiple planners, verifiers, and workers try it today with /add-plugin orchestrate and then /orchestrate [goal]

orchestrate a swarm of agents here's a visualization of the swarm and how it's using multiple planners, verifiers, and workers try it today with /add-plugin orchestrate and then /orchestrate [goal]

412,679 次观看

You can now build Cursor agents in Rust, Go, or any other language! We're open-sourcing the SDK Bridge so you can write a thin adapter in your language that keeps up when we add agent features. Try it at

You can now build Cursor agents in Rust, Go, or any other language! We're open-sourcing the SDK Bridge so you can write a thin adapter in your language that keeps up when we add agent features. Try it at

62,354 次观看

try the shadcn plugin in cursor!

try the shadcn plugin in cursor!

260,384 次观看

here are sevent grok 4.5 vs 4.6 comparison videos! age of empires clone

here are sevent grok 4.5 vs 4.6 comparison videos! age of empires clone

34,830 次观看

"my favorite enterprise service is cursor" thanks jensen, glad you like it!

"my favorite enterprise service is cursor" thanks jensen, glad you like it!

409,798 次观看

fantastic read! these interactions and animations to explain various technical concepts are incredible! great job on this Vicent Martí and Lee Robinson

fantastic read! these interactions and animations to explain various technical concepts are incredible! great job on this Vicent Martí and Lee Robinson

92,903 次观看

play this game to see how many terminal commands you can safely approve in 30 seconds. try to beat auto review, it's harder than you think!

play this game to see how many terminal commands you can safely approve in 30 seconds. try to beat auto review, it's harder than you think!

44,079 次观看

cafe cursor is coming to sf again! coffee & credits june 10, rsvp:

cafe cursor is coming to sf again! coffee & credits june 10, rsvp:

33,879 次观看

should we ship this in cursor

should we ship this in cursor

46,280 次观看

build custom agents with the cursor sdk! here's a kanban board for your agents, more examples in our cookbook repo:

build custom agents with the cursor sdk! here's a kanban board for your agents, more examples in our cookbook repo:

32,577 次观看

have you tried todo lists for agent yet? if not, you can enable from settings → chat. let us know what you think!

have you tried todo lists for agent yet? if not, you can enable from settings → chat. let us know what you think!

80,717 次观看

generate diagrams and visualize code with this command

generate diagrams and visualize code with this command

52,145 次观看

here's a quick demo on how to get started. after browser is open, you can ask the agent to click, navigate and take screenshots!

here's a quick demo on how to get started. after browser is open, you can ask the agent to click, navigate and take screenshots!

54,901 次观看

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

57,554 次观看

in 0.50, Cursor got a lot more efficient working with long files agent can now search & replace which allows for surgical edits making it much faster, around 2x in this example

in 0.50, Cursor got a lot more efficient working with long files agent can now search & replace which allows for surgical edits making it much faster, around 2x in this example

66,706 次观看

cursor 1.7 is out, and there are a lot of exciting features in this one! i'm particularly excited about hooks that will allow you to build analytics, security, auto commit and much more. go to our docs and ask the agent to build the hook you want, it has all the context!

cursor 1.7 is out, and there are a lot of exciting features in this one! i'm particularly excited about hooks that will allow you to build analytics, security, auto commit and much more. go to our docs and ask the agent to build the hook you want, it has all the context!

49,159 次观看

see cursorbench results on you can now sort by score and avg cost / task as well

see cursorbench results on you can now sort by score and avg cost / task as well

14,303 次观看

cursor can now more accurately answer questions about itself and guide you through various features and capabilities! under the hood, it'll spawn a subagent to fetch the latest docs and updates

cursor can now more accurately answer questions about itself and guide you through various features and capabilities! under the hood, it'll spawn a subagent to fetch the latest docs and updates

15,345 次观看

you can now generate rules from conversation using the command /Generate Cursor Rules great way to capture decisions from back and forth chats you might want to reuse later

you can now generate rules from conversation using the command /Generate Cursor Rules great way to capture decisions from back and forth chats you might want to reuse later

38,840 次观看

Videos

ericzakariasson's profile picture

cursor cli is a fast cli

eric zakariasson

57,939 次观看 • 7 个月前