AI agents in training

AI Agents That Work Inside Syllabium

This page is about the AI agents that work inside Syllabium, not a course that teaches agentic AI. Syllabium is the learning management system (LMS) your training runs on, and its AI agents work in it beside your people, under the same checks.

Syllabium is an enterprise learning management system (LMS) for regulated industries, made by Athantic AI LLC.

Each agent has authority granted capability by capability, its safety-critical work waits for a person, and every attempt it makes is recorded with the check that decided it.

What Is an AI Agent in Syllabium?

An AI agent in Syllabium is a named actor with its own account and role, which does defined work in the platform under the authority an administrator grants.

  • Each AI agent acts through its own account: it has no password, cannot sign in, and is never impersonated.
  • No person can hold an AI role.
  • Administrators manage AI agents as users of their own kind, beside learners, staff and alumni.
  • A person activates or retires an AI role, with a recorded reason.
  • An agent never approves, and the assistant does not appear on the pages that govern it.

Which AI Agents Work in Syllabium?

AI agents in Syllabium help author content, watch engagement, check assessment questions, draft notes on reflections and run the platform’s quality checks.

The agent’s workWhat it doesWhere a person decides
AuthoringIt works beside authors in the studio, on a block’s text, in Off, Ask, Suggest or Act mode.In Suggest, the author applies each change; in Act, it writes only the author’s own draft, with undo.
EngagementEach day it reads three counts per learner (overdue lessons, missed reflections and days unseen) and raises a suggested intervention in fixed words. It calls no model and reads no learner’s writing.Every raise waits for a staff member, who approves, rejects or resolves it.
Question checkingA verifier, then a separate critic, checks each assessment question against the slides it cites.A rejected safety-critical question goes to a reviewer.
Reflection notesIt drafts a note for a supervisor on a learner’s reflection, and the learner never sees it.It runs only when the enrollment consent names it and a person turns it on.
Quality assuranceIt runs the platform’s built-in test suite and writes only a short summary of each run.Rules decide every verdict, never a model, and a failed run stays failed, acknowledged by a named person with a reason.

Further roles, among them a tutor, a grader, a translator and a proctor, are on the roadmap. Block-level LLMs and Agentic RAG describe two kinds of AI work in more detail.

How Is an Agent’s Authority Granted?

For each AI agent and each capability, an administrator sets one of four outcomes: Allowed, Human review, Admin review or Blocked. Unset means refused.

OutcomeWhat happens
AllowedAn explicit grant for a named agent and capability.
Human reviewThe action waits for a person. Safety-critical work by an AI agent does too.
Admin reviewA different administrator must decide.
BlockedThe refusal and its check are recorded.
UnsetThe action is refused.

Authority also runs in levels, from viewing through drafting and ordinary publishing to safety-critical publishing, deleting and full authority, and above ordinary publishing an agent’s act always waits for a person. A grant can be limited to one library or one block.

  • Grants for people and for AI agents sit side by side in the administrator console, each with a reason.
  • Roles and capabilities are data, changed without a release of the software.
  • A review of AI agents’ permissions is recorded, and is due every ninety days.

How Does Authority Work by Level?

AI settings exist at three levels, the platform, each tenant and each organization, and a lower level can only be stricter than the one above it.

The administrators of each tenant and each organization set their own level. A cap across all agents applies at each level, beside each agent’s own limits on actions, tokens and spend. Loosening a safety-critical setting, any change an agent proposes, and a loosened rule each wait for a second, different administrator. Your own models explains how each level’s route chooses the model.

What Happens to Safety-Critical AI Work?

On content flagged safety-critical, an AI agent’s work waits for a person. No setting changes that.

  • A person sets the safety-critical flag.
  • No setting gives an agent a plain “allow” on that content, and the rule is enforced both in the code and in the database.
  • A change to safety-critical content stays hidden from learners until a second person approves it, and the person who submitted it cannot approve it.
  • An administrator can switch the second person off for people’s own acts, which itself needs a second administrator, but never for AI.

AI review before publish explains the review in full.

How Is Every Attempt Recorded?

Every attempt by an AI agent is recorded with the check that decided it, whether the act was allowed, refused or failed.

Before any agent act, twelve checks run in this order.

CheckWhat it settles
Emergency stopWhether a stop is in force for this work.
SwitchesWhether this kind of AI work is switched on.
TenancyWhether the act stays inside the right tenant and organization.
The role’s stateWhether the agent’s role is active.
PermissionWhether the agent holds this capability.
Safety-critical ruleWhether the content is safety-critical, in which case the work waits for a person.
OverrideWhether an override applies.
Level askedWhether the grant reaches the level of authority the act needs.
Library scopeWhether the grant covers this library.
LimitsWhether the act is within its rate and spend limits.
Data classWhether this kind of data may be sent to this model’s provider.
The decisionAllowed, Human review, Admin review or Blocked.

A refusal names its check, is recorded, and never reaches a model. Every model call is logged with its model, tokens and cost, in tamper-evident records kept seven years. The platform’s quality suite tests that each of the twelve checks can refuse. Evidence explains how the records are chained and checked.

How do agents and people work under the same checks?

People and AI agents act through one route: the same authority check, then the act, then a record, written whether the act was allowed, refused or failed.

An agent’s action takes the same path a person’s does, and no service has a back door for AI.

PeopleAI agents
IdentityTheir own sign-in.Their own account, with no password and no sign-in.
AuthorityRoles and capability grants, each with a reason.Capability grants per agent, each with a reason and an outcome.
Safety-critical contentA second person approves each change, and an administrator can switch that off for people’s own acts, with a second administrator.The work always waits for a person, and no setting changes that.
The recordEvery act is recorded.Every attempt is recorded with the check that decided it, and every model call with its model, tokens and cost.
  • Staff see “(AI)” and the role beside an agent’s work, an AI activity tab, and marks on content the assistant changed.
  • Authors can search the library by author, with people and AI roles alike.

How Is an Agent Stopped?

An emergency stop, read before every agent act, can halt all AI, one agent, one kind of work or one type of content.

It is set in two steps, with STOP typed again to confirm, and a red banner shows on every AI page while it holds. Each agent also stops at its limits on actions and tokens an hour, and on spend a day and a month. Governed AI shows the one route every AI action passes, and Platform the rest of the system.

What Can Reviewers Read About the Agents?

Syllabium keeps a record that reviewers can read: who each agent is, what it may do, what waited for a person, and which check decided each attempt.

An administrator exports a period’s records as one archive, with a verification report and a list of file fingerprints, and every export is logged. Evidence explains the export for an auditor.

Get Started

Enroll your organization online, see the pricing, or talk to us. Syllabium is made and operated by Athantic AI LLC.

Contact us