System maintenance in progress — some features may be temporarily unavailable
How business agents work, what they do, and how you stay in control
Building an external AI agent or automation against RTOFlow?
Start at /for-agents — the machine-readable reference page covering RTOFlow's OpenAPI 3.0 surface, supported document types, authentication model, and data governance commitments for agentic workflows.
RTOFlow includes optional AI-powered business agents that can assist your organisation with sales outreach, marketing content, and customer communications. Each agent operates under strict governance controls and requires human approval for all actions.
Helps draft outreach messages, follow-up communications, and prospect engagement materials for your training services.
Creates draft marketing copy, social media content, and promotional materials tailored to your RTO's offerings and industry focus.
Assists with drafting customer responses, support communications, and enquiry follow-ups for your training programmes.
Every piece of content created by a business agent goes through a multi-step review process before it can be used. Nothing is sent or published automatically.
The agent generates content based on your organisation's context and objectives. The draft is saved with a pending status.
A separate AI supervisor model checks the draft for quality, safety, and compliance with your organisation's guidelines.
You review the draft in the approval queue. You can approve it, edit it, or reject it entirely. Only approved content moves forward.
Organisation administrators have full control over which agents are active and what they can do. Agents are not enabled automatically.
Turn specific agents on or off from your organisation settings. You can enable only the agents your team needs.
Within each agent, you can enable or disable specific task types. For example, you might enable the Sales Agent's outreach drafting but disable other tasks.
Administrators can disable all agent activity across the organisation instantly from the settings page.
Every organisation can set spending limits for AI agent activity. Costs are tracked in real-time and displayed in Australian dollars.
Set maximum AUD spend limits per period. Agents automatically pause when limits are reached.
View token usage and costs per agent session. All costs are converted to AUD for transparency.
Detailed breakdowns of agent costs by task type, time period, and model used.
When an agent creates a draft, it appears in your approval queue. Here's how to manage the review process:
Navigate to the Agent Drafts section in your dashboard. Pending drafts are highlighted and sorted by creation date.
Click on any draft to see the full content, the agent's rationale, and the supervisor's review notes. You can see exactly what was generated and why.
For questions about agent configuration or to request changes to your agent settings, contact us at support@rtoflow.au or speak with your organisation administrator.
| Method | Path | Description |
|---|---|---|
| GET | /api/course-builder/outlines | List all outlines for org |
| POST | /api/course-builder/outlines | Create new outline |
| GET | /api/course-builder/outlines/{id} | Get outline with sections |
| PUT | /api/course-builder/outlines/{id} | Update outline metadata |
| DELETE | /api/course-builder/outlines/{id} | Delete draft outline |
| POST | /api/course-builder/outlines/{id}/sections | Add section |
| PUT | /api/course-builder/sections/{id} | Update section |
| DELETE | /api/course-builder/sections/{id} | Soft-delete section |
| POST | /api/course-builder/outlines/{id}/reorder | Reorder sections |
| POST | /api/course-builder/outlines/{id}/generate | Start generation pipeline |
| POST | /api/course-builder/conversations | Start AI design conversation |
| GET | /api/course-builder/conversations | List conversations |
| GET | /api/course-builder/conversations/{id}/messages | Get messages |
| POST | /api/course-builder/conversations/{id}/messages | Send message (triggers AI response) |
| POST | /api/course-builder/conversations/{id}/approve | Create outline from AI conversation |
| DELETE | /api/course-builder/conversations/{id} | Delete conversation |
| POST | /api/course-builder/outlines/{id}/tga-framework | Generate TGA framework for outline |
| GET | /api/course-builder/outlines/{id}/tga-framework | Get TGA framework data |
| GET | /api/course-builder/outlines/{id}/tga-framework/export | Export TGA framework as DOCX |
| POST | /api/course-builder/outlines/{id}/tga-proposal | Generate TGA proposal from framework |
| PATCH | /api/course-builder/outlines/{id}/branding | Update branding settings |
| POST | /api/course-builder/outlines/{id}/tga-research | Trigger TGA-specific research |
| GET | /api/course-builder/outlines/{id}/tga-research | Get TGA research results |
| PATCH | /api/course-builder/outlines/{id}/tga-research | Update TGA research decisions |
course_builder — must be enabled per organisation via feature flags
course_design — conversation AI for outline designcourse_design_research — TGA-specific research framework for industry/regulatory context
cost_category="setup" and track via the unified AiUsageEvent system.
app/services/course_builder_adapter.py converts CourseOutline → UnitBlueprint format for Stage C compatibility.
| Table | Description |
|---|---|
| course_outlines | Main outline with metadata, status (draft → ready → generating → completed), AQF level, audience context, quality mode, tga_proposal_enabled, and rpl_pack_enabled flags |
| course_outline_sections | Sections with learning outcomes, key topics, content type (theory/practical/assessment), complexity hint, and word targets |
| course_design_conversations | AI design chat sessions linked to org/user, with context snapshot and status tracking |
| course_design_messages | Individual messages (user/assistant/system) with interactive elements, user selections, and token usage tracking |
| Index | Entries | Size | Generated | Status |
|---|---|---|---|---|
| Loading... | ||||
