Skip to content

Add blog post on using AI coding agents with Selenium - #2853

Merged
diemol merged 1 commit into
trunkfrom
copse/create-a-blog-post-in-my-6c8647
Sep 29, 2026
Merged

diemol merged 1 commit into
trunkfrom
copse/create-a-blog-post-in-my-6c8647

Conversation

@AutomatedTester

Copy link
Copy Markdown
Member

Announces the AI agents documentation page added in #2846.

The post takes the angle that agents are not hallucinating when they emit Selenium 3 code — they were taught by a decade of blog posts and tutorials, a good share of which this community wrote, and which still outnumber everything published since. From there it pulls out the three things worth acting on:

  • point the agent at llms.txt
  • write the project rules into AGENTS.md / CLAUDE.md
  • let it drive a real browser so locators are verified rather than inferred

It singles out one pattern for review: agents "fixing" a flaky test by raising a timeout or adding a sleep, which hides the race instead of removing it.

The post links to the documentation page rather than restating it, so it stays short and the docs remain the reference.

Notes for review

  • The post is plain markdown and front matter only — no shortcodes — so it is structurally the same as chrome_fornightly_releases.md. I was not able to run a local Hugo build to confirm rendering, so worth a look on the deploy preview.
  • No [deploy site] in the commit, so this will not deploy on merge.

🤖 Generated with Claude Code

Announces the new AI agents documentation page added in #2846.

The post takes the angle that agents are not hallucinating when they emit
Selenium 3 code - they were taught by a decade of blog posts and tutorials,
a good share of which this community wrote, and which still outnumber
everything published since. From there it pulls out the three things worth
acting on: point the agent at llms.txt, write the project rules into
AGENTS.md/CLAUDE.md, and let it drive a real browser so locators are
verified rather than inferred.

Singles out one pattern for review: agents "fixing" a flaky test by raising
a timeout or adding a sleep, which hides the race instead of removing it.

Links to the documentation page rather than restating it, so the post stays
short and the docs remain the reference.

Co-Authored-By: Copse <noreply@copse.dev>
Copse-Models: acp:claude-agent-acp#opus[1m]
@netlify

netlify Bot commented Sep 29, 2026

Copy link
Copy Markdown

✅ Deploy Preview for selenium-dev ready!

Name Link
🔨 Latest commit c9002db
🔍 Latest deploy log https://app.netlify.com/projects/selenium-dev/deploys/6abb82fc5aa8360008af90b4
😎 Deploy Preview https://deploy-preview-2853--selenium-dev.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.
🤖 Make changes Run an agent on this branch

To edit notification comments on pull requests, go to your Netlify project configuration.

@diemol
diemol merged commit 94c7cbd into trunk Sep 29, 2026
5 checks passed
@diemol
diemol deleted the copse/create-a-blog-post-in-my-6c8647 branch September 29, 2026 12:58
selenium-ci added a commit that referenced this pull request Sep 29, 2026
Announces the new AI agents documentation page added in #2846.

The post takes the angle that agents are not hallucinating when they emit
Selenium 3 code - they were taught by a decade of blog posts and tutorials,
a good share of which this community wrote, and which still outnumber
everything published since. From there it pulls out the three things worth
acting on: point the agent at llms.txt, write the project rules into
AGENTS.md/CLAUDE.md, and let it drive a real browser so locators are
verified rather than inferred.

Singles out one pattern for review: agents "fixing" a flaky test by raising
a timeout or adding a sleep, which hides the race instead of removing it.

Links to the documentation page rather than restating it, so the post stays
short and the docs remain the reference.

Copse-Models: acp:claude-agent-acp#opus[1m]

Co-authored-by: Copse <noreply@copse.dev>

[deploy site] 94c7cbd
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants