AI Agent
How to Survive in the Cursor World
· β˜• 6 min read
1. The Quantitative Change AI IDEs Have Brought AI generates a large amount of code that enters engineering work. AI IDEs are simply too good to use: from naming completion in the past, to generating function implementations, and now to delivering the code for an entire feature. You do not even need to know how to write code β€” through chatting you can complete many software iteration tasks.

You Can Also Implement AI Agents This Way - The MCP Edition
· β˜• 5 min read
1. What Is MCP MCP is short for Model Context Protocol, a protocol for passing context between models and applications. The greatest value of MCP is that, as the model wars are winding down and AI applications are about to explode, it gives developers a unified standard for invoking capabilities beyond the model itself.

You Can Also Land AI Agents This Way - The Operations Events Edition
· β˜• 6 min read
1. Why Operations Events Less invasive Operations teams usually already have observations accumulated in the Metrics and Log dimensions. Operations events can be a new entry point: introduce new operational capabilities without affecting the stability of existing systems. Better suited to automation Metrics represent system state, Log represents specific code behavior, while Event represents changes in components.

You Can Also Implement AI Agents This Way - The Case Studies Edition
· β˜• 3 min read
1. Handling Deterministic Faults For faults that have a specific handling procedure, just let the Agent handle them and send a notification to spread the word. For similar automated handling, we have exception load deletion at the application layer, disk cleanup at the node layer, masking an offline GPU card, masking a node, and so on.

Opscli Supports MCP to Provide Cline\Cursor Integration
· β˜• 3 min read
1. Using Ops from Cline Query which clusters exist Get the details of a node The case is very simple, but the data is real, which shows that Cline is already able to connect to Ops for operations tasks. More complex cases still need more testing. The specific approach might lie in: providing certain Workspaces as context information, setting custom instructions to reinforce certain characteristics, and so on.