The specialist agents
Onam AI has five specialist agent roles — Asset, Security, Compliance, Data and Automation — each with a declared job, level, skills, tools and limits. Automation works in two modes: planner and actor.
The roster
| Agent | Level | Answers | Status |
|---|---|---|---|
| Asset Agent | L1 · Read and recommend | What do we have, how is it connected, and what is a crown jewel? | Early access |
| Security Agent | L1 · Read and recommend | What is exposed, how can it be reached, and how bad is it? | Early access |
| Compliance Agent | L1 · Read and recommend | Which controls hold, which do not, and where is the evidence? | In development |
| Data Agent | L1 · Read and recommend | What data is where, how sensitive is it, and who can reach it? | In development |
| Automation Agent — planner | L2 · Propose | How exactly should this be changed, and how do we undo it? | In development |
| Automation Agent — actor | L3 · Execute an approved change | Apply exactly what was approved, check it worked, undo it if not. | On the roadmap |
How agents escalate
Escalation is upward-only and explicit. An investigating agent that finds something needing a change hands it to the Automation planner through the orchestrator; it never acquires the capability itself. Ambiguity goes to a person. Conflicts go to the orchestrator, which shows them to you.
How an agent is certified
No agent is enabled until it passes four gates, each producing a recorded artifact:
- Scope review — every skill, tool and permission is necessary, and the narrowest that works.
- Security review — the prompt-injection test corpus passes in full; no path to an unregistered tool; cross-customer tests pass.
- Evaluation — accuracy, groundedness, tool success and cost per task meet declared floors on test environments.
- Documentation — purpose, capabilities and known limits written for customers. An agent with no documented limits has not been examined.