Run a session

A session starts in the Mo composer in the Momentic app, or with mo start from the CLI. You write what to test, and Mo asks you for anything it still needs before it starts work. The brief decides the boundary of the run. See write a good brief.

​

Start settings

Beyond the brief, a session takes three knobs:

• Granularity (low, medium, or high, default high) sets how deep the explore agents dig. high exercises every independently operable control and names whatever remains untested; low covers the happy paths and important failure states for a fast smoke pass.
• Max concurrency caps how many sub-agents run at once. The default is 100, capped further by your organization limit. Concurrency changes how long the pass takes, not how many cases run.
• Environment names a configured Momentic environment. Its non-secret variables are visible to the session, and a BASE_URL variable sets the starting URL, so one brief can aim at staging today and production tomorrow. The session header shows the environment it ran in.
• Secrets attach to a message from the composer’s attachment menu, up to 10 per message. Each one is saved into the session environment before the message is delivered, and a name that already exists in the session replaces the earlier value. Refer to a variable as $NAME in your message; the chat renders the reference as a lock chip and redacts the value from Mo’s output.

Momentic browser tools drive every web agent by default.

​

Workspace repositories

Connect GitHub, then pick repositories on the Mo workspace page. Every session then starts from a fresh snapshot of them at /home/user/workspace/repos/<repo-id> with read-only Git credentials. The session agent can read the code, run git log over a diff window, and trace a found behavior into the change that caused it. This is what makes diff-based regression possible. Only the default branch refreshes at session start. For another branch, say so in the brief and Mo fetches it inside the sandbox. The snapshot is context: Mo reads it to plan and to debug, but it does not run your application from the checkout.

​

Sign-in

Each web sub-agent starts in a fresh signed-out browser, so Mo signs in each agent:

• With a username and password, Mo passes those credentials to each agent that needs them.
• With one-time codes or MFA, Mo signs in once, saves the browser authentication state inside the session sandbox, and each agent loads that state instead of signing in again. This also avoids login rate limits.

Credentials stay inside the session. Mo instructs its agents never to quote authentication values or put them in a test case, a bug report, or a recording.

​

Set up and tear down test data

Some products need a fresh user per run, or an account with a role or a license that the flow uses up. Name a setup endpoint in the brief, with its payload and the response field that holds the account to sign in with, and name a teardown endpoint for the data the run leaves behind. Mo calls setup before the sub-agents start and teardown after the pass.

​

During the session

Test cases and bugs appear in the report while the run continues, and the first bugs can appear within minutes. Open the transcript of any sub-agent to see what it did, or message Mo to change the scope. You do not have to wait for the session to finish. mo send interrupts the active turn when Mo is working; the session resumes from saved history with your message. mo stop stops the root turn, and mo stop --subagents stops every active sub-agent turn too. mo archive stops and archives the session; unarchive is web-only.

​

Repeat a session on a schedule

Open Schedules in the Mo section of the app. A schedule holds a name, the prompt, a cron expression, and a time zone. Each occurrence starts a new session, and the schedule page lists the past runs and their reports.

​

What a pass costs

A session bills the active runtime of its agents, not the wall time of the session. Each agent reports the seconds it spent working. A session also bills the hosted browser time the sub-agents use, the emulator or simulator time for a mobile session, and the inference the agents use, which Momentic bills at cost. The scope of the brief drives the cost. The concurrency setting changes how long the pass takes, not how many cases run.

​

Next