- Docs
- AI
- Autonomous Agents
- FAQ & limits
FAQ & limits
Answers to common questions about autonomous agents, how agents relate to AI assistants, and the module’s limits.
In short
On this page you can
- Get short answers about changes, cost, permissions and data.
- Filter the questions for customers or admins.
- Run a five-minute agent demo for a prospect.
- Look up every agent limit in one table.
How to use it
- Pick your audience in the filter bar above the questions.
- Open a question; follow its link for the full procedure.
- Check Limits before you change an agent’s settings.
Questions and answers#
Will an agent change my tests on its own?Customers
No. When the SmartestQA server runs an agent, every change is recorded as a proposal and waits until a person clicks Apply. New agents also start paused. See Apply or dismiss proposals.
What does an agent cost to run?Customers
A server run uses tokens of the project’s AI connection; the cost of each run is shown in Runs and capped by Max cost per run and Daily budget. A run in Claude Desktop runs on your Claude plan and records no cost in SmartestQA. See How spend is counted.
Do I need Claude Desktop?Customers
No. The report agents (Daily triage, Daily QA report, Weekly management report, Coverage gap report) run only on the SmartestQA server, and you can set any other agent to run there. Claude Desktop is an option for agents that work through MCP tools. See Runs on.
Does an agent run when my computer is off?Customers
On the server, yes. In Claude Desktop, no: Claude Desktop must be open at the scheduled time. If Claude Desktop asks later in the same period, the run still happens, unless its Late cutoff (HH:mm) has passed.
Where do the reports go?Customers
Always into the run detail, with Download PDF. Optionally to Slack, Microsoft Teams, Discord or WhatsApp (from Integrations), up to 10 e-mail addresses (formatted, with a PDF) and a webhook. See Reports.
Which agents should I install first?Customers
The ones marked Core: Daily triage, Daily QA report and Coverage gap report, and the two deploy agents once your CI reports deploys. Try each on-demand agent once. See The catalog.
What is the difference between an agent and an AI assistant through MCP?Customers
An agent works alone on a rhythm and leaves you a report and proposals. An assistant through MCP works with you in a chat: it shows you each change as a diff and writes only after you say yes. Both use your SmartestQA permissions.
Who can create, run and delete agents?Admins
Every role (Super Admin, Admin, User) in the projects they can open. Tools that need a permission (such as VIEW_REPORT) are refused for a user whose role lacks it; admins have every permission. Today the User role has no permissions assigned, and roles are fixed, so an Admin cannot add one. Deleting an agent keeps its run history.
Whose permissions does an agent use?Admins
A scheduled or deploy run uses the agent’s creator. Run now uses the person who clicked it. An applied proposal runs as the person who applied it. Each can reach only the projects that person can reach.
What data is sent to the AI provider?Admins
For a server run: the agent’s instructions and the results of the tools it calls (for example run results, test case names, defects, app map pages) go to the AI provider configured for the project. Each model call is logged with its tokens and cost, under the query type AI_AGENT. For a Claude Desktop run the data goes to Claude through your MCP connection.
Is every run kept?Admins
Yes: status, every step with its input and output, tokens, cost and the settings used. The Runs tab shows the latest 100 of the project; older runs stay stored.
Can my AI assistant install agents for me?Customers
The assistant’s status overview (smartest_status) tells you when no agent watches the project (the work key AGENTS). Installing and switching agents on is done on this page.
Limits#
| Item | Limit |
|---|---|
| Agent name · description | 150 · 1,000 characters |
| Max steps per run | 1–60 |
| Max cost per run | above 0, up to 10 USD |
| Daily budget | above 0, up to 100 USD |
| E-mail recipients per agent | 10 |
| Runs of one agent at the same time | 1 |
| Runs listed on the Runs tab | latest 100 |
| Bars in Last runs | 14 |
| Deploy check for After each deploy | every hour |
| Deploy events handed to one run | 20 (the rest go to the next run) |
| Overdue warning (Claude Desktop) | 90 minutes after the scheduled time |
| Stuck run closed | Queued 15 min · Running 10 min · Claude Desktop 6 h |
| Catalog agents per project | 1 per catalog entry |
Didn’t find your answer?Write to support with your project name and what you see on screen.
info@smartestqa.ai