AI inside the LMS, under your admin’s control
Pick Anthropic or OpenAI, switch on only the AI tools your policy allows, and track token use and estimated cost by feature and user. Course and question drafts wait for a person to review them.
At a glance
- Course and lesson drafting
- Rewrite tools in the editor
- In-lesson AI Tutor
- Question generate, audit and tag
- Assignment grading suggestions
We added AI to LMS Advisor where our clients were losing the most hours: turning a policy PDF or an expert’s outline into a first course draft, writing and cleaning up question banks, answering the same learner questions every evening, and marking written assignments. Each job has its own AI tool on the screen where the work already happens, and each hands you something to accept, edit or discard.
The other half is governance. Your security reviewer will want to know which provider sees your content, what it costs and how to turn it off. Those answers live on one settings tab and one usage report, covered below.
Where AI in an LMS usually disappoints
A chatbot with no course context
General assistants answer anything, including things your course never taught. Learners get confident answers that contradict your own policy.
Drafts that publish themselves
If generated lessons or questions reach learners untouched, one bad output turns into a support ticket or an audit finding.
Costs nobody can see
Token billing spread across several AI tools is hard to budget for without a log broken down by feature and user.
Stuck in security review
Reviewers ask which vendor receives your data and whether AI can be disabled. A vague answer stalls the purchase for weeks.
AI tools for the people who build and run training
Every AI feature runs on the one provider and key you configure, and all of them sit behind a single master switch. Here is what each tool does.
Course and lesson drafting
Enter a topic, level, language, section count and lesson types. AI outlines the course, writes each section, and saves the result as a draft.
Rewrite tools in the editor
Improve, expand, simplify, summarize or fix grammar in a lesson, regenerate a single section, or give your own instruction.
In-lesson AI Tutor
Your tutor name and avatar. It answers from the lesson the learner has open, declines unrelated questions, and can summarize or translate the lesson.
Question generate, audit and tag
Draft up to 25 questions per request, audit up to 40 at a time for wrong keys and vague wording, and fill in missing categories and difficulty.
Assignment grading suggestions
AI scores a submission against your rubric and drafts feedback. The instructor approves or overrides it before the learner sees anything.
Reporting agent and usage log
Ask the back-office agent about completions or quiz pass rates, and review AI calls, tokens and estimated cost on the AI Usage page.
How the AI settings and review steps work
One provider, one key, one master switch
Everything starts on Settings, AI Integration. You choose Anthropic (Claude) or OpenAI (GPT), pick a model from that provider’s list and paste the API key, which is stored encrypted. The “Enable AI Features” switch sits above everything else: turn it off and every AI tool stops, tutor and reporting agent included. Below it are separate switches for the reporting agent, the AI email writer, the course recommender and the assignment grader, and the tutor button has its own toggle in lesson settings, so you can approve features one at a time.
Watching cost
You enter a cost per 1,000 tokens, and the AI Usage page turns logged calls into an estimate. It shows the current month by feature, daily calls for the last 30 days, the ten heaviest users, and a list of individual calls you can filter by feature, with model and token counts. The settings tab also holds a monthly token budget, and the usage page shows the month’s total against it.
What the AI Tutor will and will not answer
In lesson settings you set the tutor’s display name and avatar: an animated character that speaks its answers, or an instructor photo with no animation. The tutor is instructed to treat the current lesson text as its main source, answer only about that lesson or course, and decline anything else in one sentence. It remembers the last ten messages of each learner’s conversation on that lesson, accepts voice input, and replies in the language the learner uses the platform in. Tutor conversations can be purged automatically under data retention.
Where a person stays in the loop
Generated courses are saved as drafts. The interactive module assistant drafts 6 to 12 blocks, including at least one knowledge check, into the builder for you to edit. Question Bank tools only propose: new questions appear in a preview you pick from, audit findings are sorted from high to low severity with a suggested fix, and auto-tagging only fills fields that are empty. The grader writes a suggested score and feedback for an instructor to release. There is an auto-approve switch that skips that review. It is off by default, and we suggest keeping it off for any grade that counts.
The reporting agent is read-only
The agent answers questions like “which quiz in Fire Safety has the lowest pass rate?” by calling a fixed set of queries: course lists, course stats, lessons where learners drop off, quiz performance, enrollment trends, top students and a platform overview. It is told never to state a number a query did not return, and it cannot create, edit or delete anything.
See AI-Powered Learning in a live demo
We will show it with your own scenario, answer the security questions and send a written quote after the call.
From API key to first reviewed draft
Connect a provider
Choose Anthropic or OpenAI, select a model and add the API key on the AI Integration tab.
Switch on what you approved
Turn on the master switch, then only the tools your policy allows: tutor, grader, agent, email writer or recommender.
Generate a draft
Run the course generator, module assistant or question tools from the screen you already work in.
Review and edit
Read it, fix it and save it. Courses wait as drafts and question proposals wait until you accept them.
Check the usage page
Look at calls, tokens and estimated cost by feature and by user at the end of each month.
Teams using AI this way
A policy change on short notice
Finance revises the travel expense policy. An L&D coordinator pastes the changed clauses into the generator’s instructions, gets a two-section draft with a quiz, edits it and publishes it the same day.
Cleaning an inherited question bank
A certification team imports a few thousand legacy questions from spreadsheets, audits them in batches, fixes high-severity answer keys first, then lets auto-tag fill in missing difficulty labels.
Evening questions in a customer academy
Customers studying after hours ask the tutor what a setting in lesson 4 means and get an answer drawn from that lesson.
Marking written assignments
Instructors on a management program get a rubric-based score and draft feedback for each submission, adjust the wording, and release it.
What your team gets back
- First drafts of courses and questions without a blank page
- Learner questions answered from your own lesson content
- AI use and estimated cost broken down by feature and user
- A human decision before AI output reaches learners
- Clear answers for your security review on providers and switches