Agents & models
PENTER agents reason over the engagement, request capabilities and incorporate real results. Models do not directly become the execution authority: Desktop and Cloud policy decide whether and where actions actually run.
The agent loop
A useful PENTER turn is not just prompt → answer. The workflow can move through a sequence of reasoning, capability selection, execution, observation and verification while keeping the operator-facing state visible.
| Stage | What happens | Operator-visible result |
|---|---|---|
| Reason | The model interprets the current target, engagement state and prior evidence. | Thought/status summary and plan state. |
| Choose capability | The agent selects a registered desktop or Cloud tool instead of pretending it already ran. | Tool/command proposal. |
| Execute | Desktop or Cloud validates the request and runs the approved action. | Command, browser action, MCP call or Cloud run. |
| Observe | Output is parsed back into the same turn or continuation. | Tool result / browser state / output. |
| Verify | The agent can ask for a second check before promoting an observation. | Evidence-backed candidate or finding. |
Interactive work, planning and specialist delegation
Interactive agent work
Plan-oriented work
Specialist delegation
Background-capable work
Model sources and profiles
The desktop supports local Ollama models and configured Cloud/provider-backed workflows. PENTER Cloud exposes model profiles and specialist calls through authenticated APIs; plan and credit policy is decided server-side.
- Use local models when you want local inference and have enough hardware for the model you select.
- Use PENTER Cloud profiles when you want hosted models, metered credits and the website/device account flow.
- Do not assume a specialty-model failure means the whole agent runtime is broken; provider/model routes can fail independently.
- Keep secrets out of prompts; choose scoped Desktop tools when possible. MCP execution is blocked in packaged beta builds.
Models propose; runtimes execute
PENTER exposes tools such as HTTP requests, Browser Agent actions, shell commands, network scans, extension discovery, custom tools and MCP calls. Those tool descriptions tell the model what it may request, not what it has already done.
Write prompts around objectives and verification
- State the authorized target or refer to the active workspace target.
- Give a bounded objective: map routes, inspect auth, verify a finding, compare responses, review headers, etc.
- Say whether you want planning only, passive inspection, active checks or a verified report-ready result.
- Ask the agent to separate observations, candidates and verified findings when false positives matter.
- When using unfamiliar local tooling, tell the agent to use tools.search/tools.help instead of guessing flags.
Ready to get started?
Follow the setup guide, install the current approved Desktop release, and connect your account.