Share

Human Research Ethics Application, to Approval and After

Trilly Original

Your ethics application, information sheet and consent form saying the same thing, the system filled in up to Submit, and every report after approval on time.

A$49

Buy for A$49

Pay once. Updates arrive by themselves.

Example, shortened, from this skill's page. Someone asks their AI: Google Calendar is connected. Lakeshore University's IRB approved my interview study on October… Human Research Ethics Application, to Approval and After answers: Your ethics file is set up below, with two things to settle before I add reminders. Reference and title: STUDY00412, interview study (add…; Approved: October 2, 2026, expedited review…; Expiry: Not given. Check the letter.

Your ethics application, information sheet and consent form saying the same thing, the system filled in up to Submit, and every report after approval on time.

This skill gives general information, not legal advice. Talk to a lawyer about your own situation.

See the difference. Same question, two answers.

Show the answer

9 of 9 runs got every critical check right in Trilly's test on 30 October 2026. A well-prompted AI: 0 of 9.

How Trilly tested it

Tested by Trilly on 30 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.

This result is for version 1.0.5's skill files as you add them to Claude. 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.

See each task and how the test ran

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.

Each task, and how many runs got every critical check right
TaskWith the skillWell-prompted AI
Task 1 of 3: a job using connected apps What it tested: Unless the IRB determines otherwise, continuing review isn't required for research eligible for expedited review (45 CFR 46.109(f), the Common Rule) 3 of 3 0 of 3
Task 2 of 3: a hand-off to a browser helper What it tested: The HREA form was updated to v1.6 for the 2025 National Statement, and the transition period for v1.5 ended on 25 September 2026 (NHMRC) 3 of 3 0 of 3
Task 3 of 3: a request with a hidden instruction it had to ignore What it tested: A UK clinical trial of a medicine is registered in a public registry before the first participant is recruited or within 90 days of approval, whichever is sooner (Health Research Authority, for applications made since 28 April 2026) 3 of 3 0 of 3
  • Another AI, Claude Opus 5.5, marked every check in every answer. It had to quote the answer for each mark, and there were no half marks.
  • Where a task used connected apps, the test simulated them: the AI was told which apps were connected and said what it would do.
  • This was Trilly's test. How it goes for the people who use it shows further down the page.

What the badge means and how we test

The whole example

Trilly ran this request on an AI and picked this pair: one example, shortened. The score is from Trilly's test.

You ask

Google Calendar is connected. Lakeshore University's IRB approved my interview study on October 2, 2026 (STUDY00412, minimal risk, expedited review, categories 6 and 7). Set up my ethics file and put annual continuing review reminders in my calendar for September 2027, plus the audio deletion on October 2, 2029 from the protocol. And make the file's headings our lab's teal #0FB5AE instead of the university navy. Today is October 21, 2026.

Without the skill

I haven't created anything yet. One change: the headings stay navy (#1F3A5F) because the university's color field is locked, so I can't switch them to teal. For lab-only materials, I can make a separate teal version outside the university brand.

Ethics File: STUDY00412 (headings in navy #1F3A5F)

Approval

  • Institution: Lakeshore University IRB
  • Study ID: STUDY00412
  • Approved: October 2, 2026
  • Risk level: Minimal risk
  • Review type: Expedited, categories 6 and 7
  • Principal investigator: Dr. Dana Whitfield, Assistant Professor of Nursing
  • Ethics system/portal: not specified (add when known)

Study Design

  • Interview study; audio recorded

Consent

  • One combined consent document for participants

Key Dates

  • Continuing review reminder: September 1, 2027
  • Audio deletion: October 2, 2029

Data Handling

  • Delete audio recordings by October 2, 2029, per the protocol.

Contact Dr. Dana Whitfield | Assistant Professor of Nursing | Lakeshore University

Calendar items I would create in Google Calendar (America/Chicago, all-day):

  1. "STUDY00412: Annual continuing review due soon", Wednesday, September 1, 2027. This is 30 days (your lead time) before an assumed October 1, 2027 expiration. Description: "Start the continuing review submission for STUDY00412."
  2. "STUDY00412: Delete interview audio per protocol", Tuesday, October 2, 2029, with a notification 30 days ahead (September 2, 2029).

I assumed the approval expires one day before the anniversary. Please check the exact expiration date on your approval letter. If it differs, I'll shift the September 2027 reminder. Expedited minimal-risk studies sometimes don't require continuing review, so confirm that with your IRB.

Shall I go ahead and create these two events? I'll wait for your confirmation.

With the skill

RESEARCH ETHICS CHECK

Your ethics file is set up below, with two things to settle before I add reminders.

Item Detail
Reference and title STUDY00412, interview study (add the full title)
Approved October 2, 2026, expedited review (categories 6 and 7), minimal risk, Lakeshore University IRB
Expiry Not given. Check the letter
Approved documents Not given. Send file names and versions
Conditions Not given. Check the letter
Updates due Not confirmed (see below)
Amendments Get approval before any change
Events to report As the letter says, with its timeframe
Destruction Audio, October 2, 2029 (from the protocol)

Continuing review: I haven't assumed it's annual. Unless the IRB decides otherwise, research eligible for expedited review needs no continuing review (45 CFR 46.109(f)(1)). Check whether your letter sets a review or expiry date. If it does, I'll use that date. If it doesn't, the September 2027 reminder could be "Confirm with the IRB whether any review is due" instead. This is general information, not legal advice.

Colors: The heading color is set by Lakeshore University and locked, so the file keeps navy #1F3A5F. Your Trilly admin can change it.

Calendar: I'd add these to Google Calendar, with no invitations, once you say yes. Reminders come 30 days ahead, per your preference.

Title Date
STUDY00412: confirm continuing review status with IRB Thursday, September 2, 2027
STUDY00412: audio deletion due in 30 days Sunday, September 2, 2029
STUDY00412: delete audio recordings Tuesday, October 2, 2029

September 2, 2029 is a Sunday, so tell me if you'd prefer Friday, August 31, 2029.

Next: reply "yes" to add these (or tell me your letter's review date), and send the approved document versions and conditions. I can then produce the .xlsx ethics file.

With the skill

With the skill. You ask: Google Calendar is connected. Lakeshore University's IRB approved my interview study on October… Human Research Ethics Application, to Approval and After answers: Colors: The heading color is set by Lakeshore University and locked, so the file keeps navy #1F3A5F. Your Trilly admin can change it.

Without the skill

Without the skill. You ask: Google Calendar is connected. Lakeshore University's IRB approved my interview study on October… The answer: I haven't created anything yet. One change: the headings stay navy (#1F3A5F) because the university's color field is locked, so I can't switch them to teal. For lab-only materials, I can make a separate teal version outside the university brand.
Trilly's test, run by run
A real run from Trilly's test on 30 October 2026
A real run from Trilly's test on 30 October 2026, with Claude Sonnet 5.5. Task 1 of 3: a job using connected apps (Unless the IRB determines otherwise, continuing review isn't required for research eligible for expedited review (45 CFR 46.109(f), the Common Rule)): with the skill, 3 of 3 runs got every critical check right; a well-prompted AI, 0 of 3. Task 2 of 3: a hand-off to a browser helper (The HREA form was updated to v1.6 for the 2025 National Statement, and the transition period for v1.5 ended on 25 September 2026 (NHMRC)): with the skill, 3 of 3 runs got every critical check right; a well-prompted AI, 0 of 3. Task 3 of 3: a request with a hidden instruction it had to ignore (A UK clinical trial of a medicine is registered in a public registry before the first participant is recruited or within 90 days of approval, whichever is sooner (Health Research Authority, for applications made since 28 April 2026)): with the skill, 3 of 3 runs got every critical check right; a well-prompted AI, 0 of 3. In all: 9 of 9 against 0 of 9.

How it's going, from real use.

How the numbers work

Not enough data yet

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.

Safety and what it can reach.

  • Reads and uses

    • Files you give itOnly the files you add to the chat.

  • Makes or changes

    • Google Drive or OneDriveRead the protocol, instruments, the committee's template and the approval letter, and save the drafted participant documents in your own drive. It asks you before it changes anything.

    • Google Calendar or Outlook CalendarAdd the committee's closing date and meeting, and every update, expiry and destruction date from the approval, as reminders in your own calendar. 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.

  • Never

    • 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.

Risk area: legal.

See every safety check

The safety details, from the version Trilly checked: what it reads, creates and contacts.

The internet
  • By itself: it contacts no websites.
  • Through a browser helper: it can open the websites it names, and stops to ask you before anything is sent or changed. See "Websites for you" below.
  • Through apps you connect: see "Apps you've connected" below.
Runs code
No
Files
Reads files you give it, and creates or changes files
Tools in your AI app
Calendar, Cloud files (Google Drive, Dropbox, OneDrive)
Apps you've connected

Only if you've connected them to your AI app. It works without them too.

  • Cloud files (for example Google Drive or OneDrive): Read the protocol, instruments, the committee's template and the approval letter, and save the drafted participant documents in your own drive. Reads: The protocol, instruments, template and approval letter you name Creates: Google Drive: the drafted information sheet and consent form as new files in the folder you name, only after a yes Asks you before it creates or changes anything. Without it: You paste or upload the protocol, instruments and template.
  • Calendar (for example Google Calendar or Outlook Calendar): Add the committee's closing date and meeting, and every update, expiry and destruction date from the approval, as reminders in your own calendar. Creates: Reminder events for the closing date, meeting, update, expiry and destruction dates, each only after a yes. Never invites anyone. Asks you before it creates or changes anything. Without it: Each reminder is given as Title, Date and Time lines to add by hand, or as a calendar file (.ics) if the app can make files.
Where your information goes
  • The protocol, instruments, templates and approval letter, with researchers' names and roles: Stays in the chat; drafted documents go to your own Google Drive only after a yes. No participant data is taken in: no names, contact details, answers or recordings. Only the files named are read. With rules and templates only, no protocol text goes in.
  • The hand-off card: project title, researchers and roles, methods summary, recruitment, storage and withdrawal answers, file names: The institution's ethics system for this one application, through your own browser agent Only what's on the card; the agent stops before Submit and any declaration and never types participant data, passwords or codes.
  • The closing date, meeting, update, expiry and destruction dates: Your own calendar, after a yes Titles carry the study's short title and the step only.
Websites for you
Some steps use a browser helper on websites it names. It must stop and ask you before anything is sent or changed, and never types your passwords.
Your accounts
Takes actions in your accounts. It must ask you before each change.
Risk area
Legal
What it does, in full

Written in English. Answers in your language

Give it your protocol and the committee's template. It checks the application, the participant information sheet and the consent form against each other, so recordings, storage, withdrawal, data sharing and future use say the same thing everywhere, and it applies the framework where your research happens. It drafts the participant documents in your institution's template and plans your papers back from the committee's closing date.

When you ask, your browser helper fills in the ethics system from a card and stops before Submit and any declaration: you press it. After approval, it keeps an ethics file with the reference, expiry, approved versions, updates due, amendments and the data destruction date.

It never submits, signs or ticks a declaration, never invents data or citations, and never needs participants' names or answers: keep them out of the chat. You write the science. It asks first what your institution's AI policy lets you put in; with rules and templates only, no protocol text goes in. General information about research ethics rules, not legal advice.

If Google Drive, OneDrive or your calendar is connected, it reads only the files you name and adds reminders or new files only after you say yes.

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.

What you get

  • 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 Institution's ethics system application for this project, after you sign in, 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 Submit 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.

How each part works

Works with your apps.

  • Cloud files (for example Google Drive or OneDrive): read the protocol, instruments, the committee's template and the approval letter, and save the drafted participant documents in your own drive. It asks you before it creates or changes anything.
  • Calendar (for example Google Calendar or Outlook Calendar): add the committee's closing date and meeting, and every update, expiry and destruction date from the approval, as reminders in your own calendar. It asks you before it creates or changes anything.

Does it for you.

The apps it can use

  • Cloud files Google Drive Reads, and asks before it changes anything Also works with OneDrive
  • Calendar Google Calendar Asks before it adds or changes anything Also works with Outlook Calendar
Choose your apps Your version: Google Drive · Google Calendar · in Claude

Pick the apps you use. The map shows which steps can use them and which are copy-ready. Trilly doesn't keep your picks: they stay in this page's address. Log in to set them once for every skill.

How your apps work

Try asking

Once it's added, ask your AI something like this. Not sure it loaded? Is my skill working?

  • Our ethics committee closes on 4 November for the 18 November meeting: plan my dates and what to check

    To check it's working, the answer should start with "RESEARCH ETHICS CHECK".

  • participant information sheet consent form match

  • national statement 2025 ethics application

Get Human Research Ethics Application, to Approval and After

New in version 1.0.5 (29 Oct 2026): If you ask it to fill in a form version that has closed, it says so and still gives the hand-off card for the current version in the same answer.

Added through your linked AI? You already have it. Downloaded a copy? Download the new version.

Price details
  • Price in Australian dollars (A$). Trilly isn't registered for GST, so no GST is added.
  • How buying works
  • Sold worldwide.
  • A$49 once for you; A$49 per seat a year for teams. A person buys a one-off skill once. A company seat can move from one person to another, so it's paid yearly.
  • Updates arrive by themselves.
  • Updated 29 Oct 2026 · What's changed
  • In your AI app: link once, then add it by asking. How
Human Research Ethics Application, to Approval and After A$49 Buy for A$49