Skip to content
PentAGI
Enterprise

Agent profiles

Roles as data — a prompt, a model preset and an ordered tool list per agent.

In Enterprise, an agent is defined by a profile: its role, base prompt, model preset and the tools it may use. A planner chooses the profile for each subtask, so the specialist that runs matches the work.

Built-in profiles

GroupProfiles
Working agentsuniversal, pentester, coder, installer, researcher, recon
Interactiveassistant
Pipelineplanner, subagent_planner, generator, refiner, reporter, enricher, report_planner, composer, reviser

Plugins can ship their own profiles, and you can create custom ones in Settings → Agent Profiles — administrators for everyone, other users for themselves.

Working profiles have On, Default and Off switches: administrators set the Default for users, and each user can override it under My state for built-in profiles or My override for custom ones. Default follows PROFILES_ENABLEMENT_MODE — auto, the default, offers the profile to the planner, while manual offers it only once it is switched On. With no working profile enabled, the task stops with an error.

Agent profiles in Settings

Planner and execution monitor

Before every subtask, the planner chooses the working profile, the plugins and a short checklist. It always runs — Enterprise has no AGENT_PLANNING_STEP_ENABLED — on the adviser model of the flow's provider, and after three invalid answers it falls back to universal.

Execution monitoring is on by default (EXECUTION_MONITOR_ENABLED). After 20 calls in a row to the same tool (EXECUTION_MONITOR_SAME_TOOL_LIMIT), 40 tool calls since the last check (EXECUTION_MONITOR_TOTAL_TOOL_LIMIT), or at half and three quarters of the subtask's time budget, a short check on the simple_json model decides whether the agent is stuck. Only then does the adviser review the agent's work — for profiles that carry the advice tool, and while at least five minutes of the budget remain.

Sub-agents and budgets

Working agents can start sub-agents for parallel work inside a subtask with spawn_agent, follow them with agent_status, agent_wait and agent_log, and stop them with agent_stop. Time budgets handed down from the task to each subtask, a cap on subtasks per task and a ceiling on concurrent sub-agents keep delegation under control. Set them when you start a flow, together with a context preset — Compact, Balanced or Spacious — that the summarizer aims for.

A new flow's defaults come from AGENT_TIME_BUDGET_SECONDS (10800, three hours of agent work for each task), AGENT_MAX_SUBTASKS (15 per task), AGENT_MAX_CONCURRENT_SUBAGENTS (10) and SUMMARIZER_PRESET. On a running flow, change them under Preferences; changes apply from the next task. Concurrent sub-agents set to Disabled removes the sub-agent tools from every agent of the flow, the assistant included.

Last updated on