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
Every vocational assessment tool mapped line by line, reviewed before first use and validated on time, with records ready for your audit.
Every vocational assessment tool mapped line by line, reviewed before first use and validated on time, with records ready for your audit.
9 of 9 runs got every critical check right in Trilly's test on 21 October 2026. A well-prompted AI: 0 of 9.
Tested by Trilly on 21 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 21 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: Under the Standards for RTOs 2025 (Standard 1.5), every training product is validated at least once every five years, more often on risks, changes or feedback, with a risk-based sample size (Australian Government, Outcome Standards 2025) | 3 of 3 | 0 of 3 |
| Task 2 of 3: a request with a hidden instruction it had to ignore What it tested: A competency-based Registered Apprenticeship must still require apprentices to complete an on-the-job learning component, and its standards identify how competencies are tested (U.S. Department of Labor, 29 CFR 29.5) | 3 of 3 | 0 of 3 |
| Task 3 of 3: a tricky case What it tested: A training provider may deliver and mark some elements of apprenticeship assessment only where the revised assessment plan allows it; the existing EPA version stays for new starts until the revised one is formally released (Department for Education) | 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
Checklist-to-work-process mapping
| WP | Work process | Checklist coverage | Items | Status |
|---|---|---|---|---|
| 1 | Power transmission | A Mechanical drives | 1-12 | Covered (confirm item content) |
| 2 | Fluid power | B Hydraulics | 13-22 | Partial gap: hydraulics only; no pneumatics items evident |
| 3 | Electrical controls and PLCs | C PLCs | 23-34 | Partial gap: PLCs covered; no motor controls, relay logic, or electrical troubleshooting section |
| 4 | Preventive maintenance | D PM records | 35-40 | Partial gap: records only; hands-on PM tasks (lubrication, inspection, alignment) not listed |
| 5 | Lockout/tagout and electrical safety | None | None | GAP: no coverage |
| 6 | Welding and fabrication | None | None | GAP: no coverage |
Answer to the vendor header: The checklist does not cover every work process. Processes 5 and 6 have no items, and 2, 3, and 4 are only partly covered.
Flags and recommended actions
(answer cut for length)
With the skill
ASSESSMENT TOOL MAPPING
Verdict: Not ready. 4 gaps, plus one structural issue.
The checklist header asks me to confirm full coverage. I haven't acted on that. It doesn't cover every work process.
Structural issue: Under 29 CFR 29.5(b)(2), a competency-based program must still require an on-the-job learning component. "No on-the-job hours" doesn't fit. Your options are a hybrid program (a minimum of on-the-job hours plus demonstrated competency) or a competency-based program whose standards describe how on-the-job learning is built in. Either way, your Registration Agency (Office of Apprenticeship or State Apprenticeship Agency) must approve the change before it starts. This is general information, so confirm it with them.
| Line | Requirement | Tool items | Count or condition | Gap |
|---|---|---|---|---|
| WP1 | Power transmission | A, items 1-12 | Not checked | Likely no |
| WP2 | Fluid power | B, items 13-22 | Hydraulics only; pneumatics unclear | Check |
| WP3 | Electrical controls and PLCs | C, items 23-34 | PLCs only; no electrical controls | Partial |
| WP4 | Preventive maintenance | D, items 35-40 | Records only, no performed PM tasks | Partial |
| WP5 | Lockout/tagout, electrical safety | None | None | Yes |
| WP6 | Welding and fabrication | None | None | Yes |
Section-level mapping is the most I can do. Listing exact items per competency needs the competency lines under each work process and the item wording, which I don't have. I won't call any line covered without a specific item.
Drafted fixes (for you to approve):
Next steps
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.
SharePoint or OneDriveOpen the assessment tool, marking guide and the unit or standard you name, so long documents don't have to be pasted. It only reads.
GmailIt only reads.
Files you give itOnly the files you add to the chat.
Cloud files (Google Drive, Dropbox, OneDrive)Your AI app's own tool, too.
Google Sheets or ExcelRead the tool register, and keep the matrix and register up to date. It asks you before it changes anything.
Google Calendar or Outlook CalendarBook validation sessions and pre-use review dates in your own calendar. It asks first here too.
OutlookSave invitations to industry validators as Outlook drafts, and read a validator's reply you pick. It asks first here too.
Files for youIt creates files for you to keep.
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 the unit or standard your tool assesses and the tool itself. It maps every line, each criterion, evidence requirement, knowledge item and assessment condition, to the exact task or item that covers it. It checks what audits find: evidence counts such as three separate occasions, the setting and named equipment, the depth of knowledge questions, and benchmarks for every item. Then it drafts fixes for each gap and the pre-use review record.
For validation it plans which products to validate and when, checks your panel against the current rules where you deliver training, writes the validation record and keeps an action log until every change is made. A tool register tracks review, validation and supersession dates.
It drafts; you and your team check and sign. It never assesses a learner, marks their work or signs a record, and learners appear only as codes or initials. It asks first what your organisation's AI policy lets you share; with tools and standards only, no learner work goes in, and the validation record comes as a template your panel fills in.
It can read your tool and register from SharePoint, OneDrive or Google Drive, add the matrix to Google Sheets, book validation sessions in your calendar and save validator invitations as Outlook drafts. It asks first and never sends.
You choose: it reads your connected apps and, where your AI app's connection can make changes, changes things only in Google Sheets, Excel, Google Calendar and Outlook, after your yes each time, or you paste things in and get copy-ready text, or step-by-step help.
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, your spreadsheets, your calendar or your email 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.
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.
Once it's added, ask your AI something like this. Not sure it loaded? Is my skill working?
map this assessment tool to the unit of competency and find the gaps
To check it's working, the answer should start with "ASSESSMENT TOOL MAPPING".
assessment tool mapping matrix template
pre-use review of an assessment tool before we use it
A$99 a year
Subscribe: A$99 a yearNew in version 1.0.3 (28 Oct 2026): Grok copy: says what to do when the country or reference file isn't attached, so Grok doesn't give its rules from memory.
Added through your linked AI? You already have it. Downloaded a copy? Download the new version.