AI assistants in Learnivo Beta
Learnivo includes seven AI assistants. They are Beta: functional and evolving, with known limitations. What sets them apart is governance — AI drafts and explains; humans approve publication and consequential decisions.
The seven assistants
| Assistant | What it does | Plans |
|---|---|---|
| Learner tutor Beta | Answers learner questions from your own course content, not from the open internet. | Pro+ |
| Course authoring copilot Beta | Drafts lesson content to your brief; authors edit, review and publish. | Every plan |
| Assessment assistant Beta | Helps build and review assessments and question banks. | Pro+ |
| Admin insights agent Beta | Summarises what's happening across your organisation and suggests where to look next. | Pro+ |
| Translation assistant Beta | Drafts content translations; a human review workflow approves them before publication. | Pro+ |
| Organisation setup wizard | Walks new administrators through configuring their organisation. | Every plan |
| Support guide Beta | Guides users through features; escalates complex queries to human support. | Pro+ |
What "human-governed" means here
- AI never publishes to learners or makes final assessment decisions by itself.
- Administrative actions — sending emails, enrolling people, changing data — are mediated by a human-approved proposal workflow on every plan.
- Every AI action is written to agent audit logs (Pro and above), so you can see what AI did and what human approved it.
- Each plan includes a monthly AI-credit allowance — 100 (Free), 10,000 (Pro), 50,000 (Max), unlimited (Enterprise) — with usage visible to administrators.
Honest limits, per capability
- AI evaluation of submissions Beta (Pro+) — advisory only; staff-only actions produce final grades.
- AI roleplay coaching Beta (Pro+) — advisory feedback against a fixed rubric; practice only, final grades are recorded by staff.
- Similarity review Beta (Pro+) — runs on a simulated provider adapter today; it makes no compliance claims.
- Tutor and insights — grounded in your organisation's data; outside their scope, they say so rather than guessing.
Plan availability
- Authoring copilot, setup wizard, human-governed approval workflow — every plan, including Free
- Learner tutor, admin insights, support guide, translation assistant, assessment assistant — Pro plans and above
- Agent audit logs — Pro plans and above
Questions people ask
Can AI contact our learners on its own?
No. Emails, enrolments and other administrative actions go through a human-approved proposal workflow — a person approves each action before it runs.
Does AI grade work?
AI evaluation is advisory only and labelled as such; final grades are always recorded by staff.
Where does the tutor get its answers?
From your own course content and organisation data. Out-of-scope questions get an honest "that's outside what I can help with", not an invented answer.
What happens when the Beta ends?
The assistants keep working and graduate out of Beta once their evaluation cases — a live suite that tests honest fallback, approval gating and tenant isolation — pass consistently. Status labels on the feature register are kept current.
Feature-by-feature explanations
Choose a capability below for its meaning, practical benefits and current readiness. Planned features are not yet available; features marked To confirm need validation before relying on them.
- AI course authoring copilot
- AI learner tutor
- AI admin insights agent
- AI support guide
- AI translation assistant
- Organisation setup wizard
- AI credits per month
- Human-governed AI approval workflow
- AI assessment assistant
- AI evaluation of submissions (advisory only)
- AI roleplay coaching (advisory feedback)
AI learner tutor
What it means: Learners ask an AI tutor questions about their course; consequential decisions always stay with humans.
Why it matters: For administrators, this helps reduce repetitive work while keeping people responsible for decisions. Instructors can spend more time on instruction and review. Learners can get timely help and feedback with human oversight. Partner organisations can coordinate repeatable processes at scale.
Current status: Beta — Functional but actively evolving. May have limitations. AI tutoring — human review required for consequential decisions.
AI admin insights agent
What it means: Ask plain-English questions about your training data; humans act on the recommendations.
Why it matters: For administrators, this helps reduce repetitive work while keeping people responsible for decisions. Instructors can spend more time on instruction and review. Learners can get timely help and feedback with human oversight. Partner organisations can coordinate repeatable processes at scale.
Current status: Beta — Functional but actively evolving. May have limitations. AI insights — human review required before acting on recommendations.
AI support guide
What it means: An AI guide answers how-to questions and can recommend human help; its answer does not itself create a support request.
Why it matters: For administrators, this helps reduce repetitive work while keeping people responsible for decisions. Instructors can spend more time on instruction and review. Learners can get timely help and feedback with human oversight. Partner organisations can coordinate repeatable processes at scale.
Current status: Beta — Functional but actively evolving. May have limitations. AI support guidance can recommend human help for complex questions; do not assume a support request has been submitted.
AI translation assistant
What it means: Translate course and interface content with AI; humans review before anything is published.
Why it matters: For administrators, this helps reduce repetitive work while keeping people responsible for decisions. Instructors can spend more time on instruction and review. Learners can get timely help and feedback with human oversight. Partner organisations can coordinate repeatable processes at scale.
Current status: Beta — Functional but actively evolving. May have limitations. AI-assisted translation — human review required before publication.
Organisation setup wizard
What it means: A guided assistant to set up your organisation, branding and first courses.
Why it matters: For administrators, this helps reduce repetitive work while keeping people responsible for decisions. Instructors can spend more time on instruction and review. Learners can get timely help and feedback with human oversight. Partner organisations can coordinate repeatable processes at scale.
Current status: Available — Available in the app; confirm fit and readiness for your organisation before purchase.
AI credits per month
What it means: Your monthly allowance for AI features such as generation, transcription and summaries.
Why it matters: For administrators, this helps reduce repetitive work while keeping people responsible for decisions. Instructors can spend more time on instruction and review. Learners can get timely help and feedback with human oversight. Partner organisations can coordinate repeatable processes at scale.
Current status: To confirm — Listed in the catalogue; end-to-end availability has not been confirmed. Plan credit allowances are listed, but per-plan enforcement still needs confirmation.
Human-governed AI approval workflow
What it means: AI-proposed actions such as emails and enrolments queue for human approval before they execute.
Why it matters: For administrators, this helps reduce repetitive work while keeping people responsible for decisions. Instructors can spend more time on instruction and review. Learners can get timely help and feedback with human oversight. Partner organisations can coordinate repeatable processes at scale.
Current status: Available — Available in the app; confirm fit and readiness for your organisation before purchase.
AI assessment assistant
What it means: AI drafts feedback and marking suggestions; staff always finalise the grades.
Why it matters: For administrators, this helps reduce repetitive work while keeping people responsible for decisions. Instructors can spend more time on instruction and review. Learners can get timely help and feedback with human oversight. Partner organisations can coordinate repeatable processes at scale.
Current status: Beta — Functional but actively evolving. May have limitations.
AI evaluation of submissions (advisory only)
What it means: AI feedback is advisory — only staff finalise actions produce final grades.
Why it matters: For administrators, this helps reduce repetitive work while keeping people responsible for decisions. Instructors can spend more time on instruction and review. Learners can get timely help and feedback with human oversight. Partner organisations can coordinate repeatable processes at scale.
Current status: Beta — Functional but actively evolving. May have limitations. AI feedback is advisory — staff-only finalize actions produce final grades.
AI roleplay coaching (advisory feedback)
What it means: Learners practise conversations with an AI coach against a fixed rubric; practice only, staff record final grades.
Why it matters: For administrators, this helps reduce repetitive work while keeping people responsible for decisions. Instructors can spend more time on instruction and review. Learners can get timely help and feedback with human oversight. Partner organisations can coordinate repeatable processes at scale.
Current status: Beta — Functional but actively evolving. May have limitations. AI coaching against a fixed rubric — practice only, final grades are recorded by staff.