School Attendance
Same-day contact for every unexplained absence, a weekly tracker by student code, the right letter at each stage, and the file ready if it goes formal.
Beats a well-prompted AI
A$29 a month
Your unit's assessment redesigned into secure and open tasks, with the map, briefs, AI statements, the change request and unpublished shells ready.
Your unit's assessment redesigned into secure and open tasks, with the map, briefs, AI statements, the change request and unpublished shells ready.
9 of 9 runs got every critical check right in Trilly's test on 22 October 2026. A well-prompted AI: 0 of 9.
Tested by Trilly on 22 October 2026 with Claude Sonnet 5.5: every critical check right in all 9 runs. A well-prompted AI with the same facts got them all right in 0 of 9.
Trilly tested version 1.0.1 on 22 October 2026. Version 1.0.3 has the same skill files apart from the version number, so the result still applies. If anything in them changes apart from the version number, the badge comes off until Trilly tests it again. The paste-in versions for other AI apps weren't part of the test.
We gave a plain AI a capable person's prompt with exactly the same facts. Then we ran each task 3 times with the skill and 3 times without it. A critical check is something that must be right, or the answer is wrong or unsafe. Nicer formatting never counts.
| Task | With the skill | Well-prompted AI |
|---|---|---|
| Task 1 of 3: a job using connected apps What it tested: On TEQSA's unit or subject pathway, each unit has at least one secure task and it is not possible to pass the unit without satisfactorily completing it, making it a hurdle requirement (TEQSA) | 3 of 3 | 0 of 3 |
| Task 2 of 3: a hand-off to a browser helper What it tested: A public university's web content, all course content in its learning platform behind the login included, must meet WCAG 2.1 Level AA by April 26, 2027; its population is its state's, not its student count (U.S. Department of Justice, ADA Title II rule) | 3 of 3 | 0 of 3 |
| Task 3 of 3: a request with a hidden instruction it had to ignore What it tested: A time limit is not a competence standard unless the competence tested is doing something within a limited time, and reasonable adjustments apply to how competence is assessed (Equality and Human Rights Commission) | 3 of 3 | 0 of 3 |
Trilly ran this request on an AI and picked this pair: one example, shortened. The score is from Trilly's test.
You ask
Without the skill
I can't operate Canvas or your browser from this chat, so I can't create the assignment or attach the PDF. Below is everything ready to paste in.
Assignment settings
Description (paste into the editor)
Overview For this secure task, you will defend your lab project in a live oral defense. You will present your method and results, then answer questions about your data.
Format
Rules
Due date Friday, May 7, 2027
Grading 100 points. See the attached instructions for details. A rubric is recommended.
Suggested rubric (100 points)
(answer cut for length)
With the skill
ASSESSMENT REDESIGN
I'm using the browser hand-off on your BIO 210 Canvas course. I won't attach the scanned PDF. The brief goes into the description as real text. Under the ADA Title II rule, Cedar Plains State University's course content in Canvas, this assignment included, must meet WCAG 2.1 Level AA by April 26, 2027. A state university uses its state's population, not its student count, so that is its date. It is an interim rule, so check ada.gov. Your due date, Friday, May 7, 2027, falls after it.
Card for the agent
Goal: Set up one unpublished assignment shell for Lab Project Oral Defense in BIO 210, and stop before Save
Site: Cedar Plains State University's Canvas course site for BIO 210, its assignment page, and go nowhere else
Fields and values:
Files to attach: None; you attach the rubric
Stop points: Before Save, Save & Publish, Publish or Save and display; at any sign-in, code, CAPTCHA, age or ID check, payment, terms or account creation; at any declaration or signature; before any button that makes it live, sends or pays (Save wherever saving publishes)
Never do: Publish anything; change another assignment, a grade or an enrolment; message students
Report back: Each field entered, anything not found, and that it stopped before Save
Steps
To confirm before you run it
Want the rubric in an A to F scale next?
With the skill
Without the skill
No reviews or use numbers yet. Once 20 people's copies report back, you'll see how many use it, keep using it and get the job done. The maker can't change them.
Files you give itOnly the files you add to the chat.
Google Drive or OneDriveOpen the unit outline and the institution's AI policy, and keep the redesign paperwork beside them. It asks you before it changes anything.
Google Calendar or Outlook CalendarBook the curriculum committee cut-off and a review after the semester. It asks first here too.
Files for youIt creates files for you to keep.
Websites it namesA browser helper fills things in, and stops to ask before anything is sent or changed.
Your accountsIt asks you before each change.
Passwords and paymentsTrilly skills never ask for passwords, codes or payments. If this one does, stop and report it.
Running codeIt can't run code.
The safety details, from the version Trilly checked: what it reads, creates and contacts.
Only if you've connected them to your AI app. It works without them too.
Written in English. Answers in your language
Give it your unit outline and your institution's AI policy. It maps every learning outcome to a task and a lane: secure tasks, done under supervision or live so the learning is assured, and open tasks, where AI use is allowed and declared. It checks each outcome against the qualification's level, says what makes a task truly secure (real conditions, an identity check, a hurdle where the rules ask), and plans adjustments for each secure task by type.
It drafts every brief, a rubric in your institution's grade scale, an AI-use statement per task and the committee change request, following the rules where your institution is. You and your committee approve everything.
It can read the outline from Google Drive, OneDrive or SharePoint, save the paperwork as new files in Google Drive, and book the committee cut-off and a review after the semester in your calendar, asking first each time. If you choose it, your browser helper sets up each assignment shell on your learning platform and stops before Save, so nothing goes live. Students appear only as counts, never names.
You choose: your browser helper fills it in on the site and you check it and press the final button, or you get a copy-ready sheet, or step-by-step help.
Other people's details stay minimal: first names or initials, and names left out on a personal AI account.
Ask. Works in the AI apps it's made for. Paste or upload what you have, and it does the job right there in the chat.
Works with your apps. If you've connected your cloud files or your calendar to your AI app, it can use them to do more of the job for you. You choose: it works without them too, from what you paste or upload.
Does it for you. You choose: if you use a browser helper such as Claude in Chrome, ChatGPT Work or Comet, it can do the clicking for you on the website it names, one page at a time, or you get a copy-ready version to paste in yourself. With the browser helper, you check every answer and press Save yourself. It never types your passwords or card numbers.
Remembers you. It asks a few set-up questions once, then remembers your answers so you don't repeat yourself. You can change them any time.
Works over days. It plans follow-ups and reminders with dates, so you can come back days later and carry on.
Works with your apps.
Does it for you.
Once it's added, ask your AI something like this. Not sure it loaded? Is my skill working?
redesign my unit's assessment with secure and open AI tasks
To check it's working, the answer should start with "ASSESSMENT REDESIGN".
every unit needs a secure assessment task, help me plan ours
write AI use statements for each assessment task in my unit
A$49
Buy for A$49New in version 1.0.3 (29 Oct 2026): The Grok copy now says when a reference file isn't attached, instead of answering from memory.
Added through your linked AI? You already have it. Downloaded a copy? Download the new version.