Guides
Set up, assess, review, release - a guided walkthrough
Ten steps from an empty account to a signed-off result in a respondent’s hands - with the real screens, so you can read it through first or work along beside it.
The “open” links go straight to that screen inside your account. If you are not signed in yet, you will be asked to log in first.
- 01
Create your first assessment
Start with a title and a short description, then build out the questions in the editor. An assessment stays a draft until you publish it - nothing is reachable by a respondent while you are still working.

- Twenty-six question types, including long-form written answers, file uploads, and video or audio responses that are transcribed automatically - plus instruction and answer reveal screens that are never scored.
- Give the AI your context and methodology in Marking, under Scoring & rubric - that is what it evaluates against, alongside your rubric.
- Optional open and close dates, and time limits per assessment or per question (Settings, under Delivery). The whole-assessment limit is enforced on the server, not just in the browser; per-question limits are too in live sittings.
- 02
Build a rubric and set weighting
The rubric turns a written answer into a defensible score. You define the criteria and performance levels; the AI places each answer against them and quotes the evidence it used.

- Open Scoring under any question to set its weight and its own criteria. Questions without their own use the default rubric in Marking, under Scoring & rubric.
- Up to ten criteria, each with up to six performance levels written in your own language. Weight each criterion so the things that matter most carry the most score.
- The AI is never asked whether an answer is good. It is asked where the answer sits against your levels, and it returns the quote that put it there.
- 03
Grading schemas
A grading schema maps a percentage to the band your organisation actually reports in - set per assessment, carried on every released result.
- Four presets: A to F, the Australian HD/D/C/P/F scale, Pass/Fail, and five-level Competency. Or define your own bands with your own labels and ranges.
- Pick a Default grading scale in your organisation Settings and every new assessment starts with it.
- The resolved grade appears on the report once an assessor has released it.
- 04
Invite respondents
Three ways in, all from the Responses tab: the assessment link you share yourself, Add respondent to email one person, or Import CSV for a whole intake at once.

- Copy link shares the public assessment link - no account needed at the other end.
- CSV import takes names and emails, can label the whole batch as an intake, and reports exactly what was imported or skipped.
- Send reminders chases unfinished respondents without rebuilding the list by hand.
- 05
Run a live, trainer-led session
For a classroom or an invigilated sitting where everyone answers the same question at the same time. You pace the room; candidates only ever see the question you have opened.

- Turn on Let an assessor control the pace of this assessment - in Settings, under Delivery.
- On the Live session tab, candidates wait on a holding screen until you start, then move on only when you move the room on. Presenter view is the screen to share on a projector or call.
- The Live session page works on a phone too - add it to your home screen and run the room from your pocket.
- 06
Show the ideal answer after each question
Discuss the model answer with the group after each question, Kahoot-style, without showing anyone how they scored.

- Write the ideal answer under any question (Ideal answer, below the question text), then turn on Show during the sitting in Settings, under Delivery > Ideal answers.
- Self-paced candidates see it after they move on. In a live session it appears when you press Show ideal answer on the Live session page.
- Once a candidate has seen the ideal answer, their own answer to that question is locked. The ideal answer is never used for marking.
- Show in the candidate's report (on by default) adds the ideal answers to each candidate's results page and PDF, even if you kept them hidden during the sitting.
- 07
Review, override and release results
The step that makes the result yours rather than the model’s. Nothing reaches a respondent until a person releases it - the gate is on by default and cannot be skipped.

- Review & release in the sidebar lists every result waiting for you. Each response shows Why this score, the evidence quoted behind each judgement, and every answer.
- Open Comment & score under an answer to leave feedback the respondent sees on their report, or press Change on any criterion to set the level yourself - the AI level stays on the record beside yours. Typed answers also show how much was pasted in and how often the respondent left the page.
- Release one result with Release result, or select several on the Responses tab and release them together. Releasing is stamped, audited, and is the moment the respondent first sees anything.
- 08
Cohort reports
Once a group has been assessed, the Cohort report tab aggregates the individual evaluations into a single programme-level view.

- Generate summary report for the score distribution, the strengths that recur across the group, the gaps they share, and programme-level recommendations - filtered to one cohort or all of them.
- Built from the individual evaluations rather than a separate scoring pass, so it agrees with the reports respondents received.
- Export it as CSV or PDF.
- 09
Exports and integrations
Get the data out, or let another system pull it - exports on every response, webhooks and a read-only REST API for wiring Scorafy into what you already run.

- Export responses as CSV, or any report as a branded PDF.
- Webhooks fire HMAC-signed POSTs for four events; report released fires only after an assessor signs off.
- API keys are scoped, hashed at rest, and revocable at any time.
- 10
Get a walkthrough on any screen
Inside your account, How do I...? sits at the bottom of the sidebar (top right on a phone). Search for what you want to do and it shows you on the real screen.

- Twelve everyday jobs, from creating an assessment to releasing results and exporting.
- Show me opens the right page and highlights each button in turn, one step at a time.
- Still stuck? Help & support reaches a person.
Deeper reading
The assurance library
Longer reference guides on running AI-assisted assessment defensibly - written for anyone doing it, whichever tool they use.
- What an audit trail for AI-assisted assessment must contain
- How to measure whether AI grading agrees with your assessors
- How to check new hires can explain your product
- AI-assisted marking when a person must make the decision
- How to mark recorded spoken answers
- AI assessment and the EU AI Act
- What human-in-the-loop assessment actually means
- What to look for in AI assessment software
- How RTOs use AI for assessment marking
- The best AI rubric grading tools in 2026, compared honestly
Work through it on a real assessment
The free plan carries one live assessment and ten AI evaluations a month - enough to take a real cohort through the whole loop before you decide anything.