AI grading blog post#149
Merged
Merged
Conversation
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
miguelaenlle
requested review from
mfsilva22,
mwest1066 and
nwalters512
as code owners
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Add the typed/handwritten submission, model picker, graded results, and explanation screenshots; switch the how-it-works pair to equal-height boxes with vertically centered content via a new BlogImage fillHeight prop; tighten the model comparison and Get started sections. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Drop the unused BlogQuote import, polish wording across the proven accuracy and speed/costs sections, rename Pricing to Payment options, move the rubric-tweak callout above the explanation screenshots, and wire real URLs to the docs, ACM paper, and Slack links with target=_blank. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
miguelaenlle
commented
May 17, 2026
|
|
||
| Across a range of open-ended questions and frontier models, rubric-item accuracy exceeded 99% when paired with clear student work and a well-aligned rubric. Instructors and TAs reported that AI grading was as accurate as human graders for their needs and saved enormous amounts of grading effort. | ||
|
|
||
| Read our published research on <a href="#" target="_blank" rel="noopener noreferrer">image grading</a> and <a href="https://dl.acm.org/doi/10.1145/3770762.3772545" target="_blank" rel="noopener noreferrer">text grading</a>. |
Collaborator
Author
There was a problem hiding this comment.
I'll fill in the image grading link once it's on arXiv.
miguelaenlle
commented
May 17, 2026
| <BlogCalloutBox variant="info"> | ||
| More detailed information can be found in the{" "} | ||
| <a | ||
| href="https://docs.prairielearn.com/aiGrading/" |
Collaborator
Author
There was a problem hiding this comment.
This link doesn't work yet. It will once we merge in the AI grading docs.
Replace JSX <p> wrapper with plain markdown so the closing callout renders as a single flowing sentence rather than each link on its own line. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Round the measured AI grading speed/cost numbers to conservative round values, flip the table column order to time-then-cost, tighten card padding, and shrink the header's minimum font size for narrower viewports. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
reteps
approved these changes
May 18, 2026
Member
There was a problem hiding this comment.
This looks good to me. I liked the overall structure and presentation of the content.
I think some instructors will basically want to know that (1) they can try it out for free and (2) where to start -- I know this is at the bottom, but at the very top seems helpful as well.
basically, a callout box at the top saying:
Want to try it out now? Try AI grading for free by redeeming your credit on X page, then hit the "AI
grading mode" toggle on Y page. Find more instructions in the AI grading documentation.
Add a "Want to try it now?" CTA callout near the top of the post so instructors immediately see how to start, update the headline copy to "Use AI to grade", and tighten the header's minimum font size further. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Collaborator
Author
Here's what I added: 
|
Replace br-separated lines with a numbered list so steps wrap cleanly and read clearly on narrow screens, and split the navigate/click action into two separate steps. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Collaborator
Author
|
I'll merge this in once AI grading is ready. Final blocker is that we need @nwalters512 to create an AI grading product on Stripe. Right now users can't purchase AI grading credits on production PL. |
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Inline the title with mb-3 so there's a clear gap between the heading and the numbered list inside the callout. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Member
|
(approval stands) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Wrote marketing blog post for AI grading.
Testing
Go to the PL blog page, click the article, and review from there.
A few links aren't available yet -- see my comments below.