You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs-site/examples/case-tasks/browser-evidence.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -15,14 +15,14 @@ This is a good first “browser + LLM” workflow.
15
15
```bash
16
16
export REXOS_BROWSER_HEADLESS=0
17
17
18
-
rexos agent run --workspace . --prompt "Use browser tools to open https://en.wikipedia.org/wiki/Large_language_model . Wait for #firstHeading (browser_wait). Run browser_run_js to extract document.title and the heading text. Scroll down by 800px (browser_scroll). Read the page and write notes/browser_evidence.md with: URL, title, heading, and a 5-bullet summary based only on the page text. Save a screenshot to .rexos/browser/wikipedia_llm.png. Close the browser."
18
+
loopforge agent run --workspace . --prompt "Use browser tools to open https://en.wikipedia.org/wiki/Large_language_model . Wait for #firstHeading (browser_wait). Run browser_run_js to extract document.title and the heading text. Scroll down by 800px (browser_scroll). Read the page and write notes/browser_evidence.md with: URL, title, heading, and a 5-bullet summary based only on the page text. Save a screenshot to .rexos/browser/wikipedia_llm.png. Close the browser."
19
19
```
20
20
21
21
=== "PowerShell (Windows)"
22
22
```powershell
23
23
$env:REXOS_BROWSER_HEADLESS = "0"
24
24
25
-
rexos agent run --workspace . --prompt "Use browser tools to open https://en.wikipedia.org/wiki/Large_language_model . Wait for #firstHeading (browser_wait). Run browser_run_js to extract document.title and the heading text. Scroll down by 800px (browser_scroll). Read the page and write notes/browser_evidence.md with: URL, title, heading, and a 5-bullet summary based only on the page text. Save a screenshot to .rexos/browser/wikipedia_llm.png. Close the browser."
25
+
loopforge agent run --workspace . --prompt "Use browser tools to open https://en.wikipedia.org/wiki/Large_language_model . Wait for #firstHeading (browser_wait). Run browser_run_js to extract document.title and the heading text. Scroll down by 800px (browser_scroll). Read the page and write notes/browser_evidence.md with: URL, title, heading, and a 5-bullet summary based only on the page text. Save a screenshot to .rexos/browser/wikipedia_llm.png. Close the browser."
0 commit comments