Follow Discord
Sweep 02 Oct 2026 · 18:55Z Build v2.1.288 509 read Stable v2.1.285 Latest v2.1.288 Next v2.1.288 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform 1 Oct 2026
One change · api

computer-use-tool changedagents-and-tools/tool-use/computer-use-tool

Nearest release: v2.1.287, published 4 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+1added
Lines−1removed
From line 716 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits15to this page, all time

The whole hunk

from line 716, old and new numbered
/
lines
from line 716
716716### Optimize model performance with prompting
717717 
7187181. Specify simple, well-defined tasks and provide explicit instructions for each step.
7192. Claude sometimes assumes outcomes of its actions without explicitly checking their results. To prevent this you can prompt Claude with `After each step, take a screenshot and carefully evaluate if you have achieved the right outcome. Explicitly show your thinking: "I have evaluated step X..." If not correct, try again. Only when you confirm a step was executed correctly should you move on to the next one.`
7192. Claude sometimes assumes outcomes of its actions without explicitly checking their results. To prevent this you can prompt Claude with `After each step, take a screenshot and carefully evaluate if you have achieved the right outcome. State in one sentence what the screenshot shows and whether the step succeeded. If it didn't, try again. Only when you confirm a step was executed correctly should you move on to the next one.`
7207203. Some UI elements (such as dropdowns and scrollbars) might be tricky for Claude to manipulate using mouse movements. If you experience this, try prompting the model to use keyboard shortcuts.
7217214. For repeatable tasks or UI interactions, include example screenshots and tool calls of successful outcomes in your prompt.
7227225. If you need the model to log in, provide it with the username and password in your prompt inside XML tags such as `<robot_credentials>`. Using computer use within applications that require login increases the risk of bad outcomes as a result of prompt injection. Review [Mitigate jailbreaks and prompt injections](https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks) before providing the model with login credentials.
Feedback