Modes & Approvals

Modes control how actions execute. Town provides multiple layers of control — from routine-level defaults to per-tool settings to the settings for each thread.

Thread settings

When chatting with your assistant in a thread, the thread’s access setting controls who can use your assistant there and how often it checks with you. Open it from the shield button in the message box.

Setting your defaults

To change your default approval mode, go to Settings → General and scroll to Permissions and access.

Group thread defaults are applied when a thread starts. In a group thread you were added to, the Only Trusted contacts or Someone isn’t a Trusted contact setting can switch when someone joins. For example, if someone who isn’t a Trusted contact joins, the thread moves to your Someone isn’t a Trusted contact setting, and the thread shows a notice. This only happens if you haven’t changed that thread’s setting yourself. To change the setting in a thread that already exists, use the shield button in its message box. If Town can’t check who is in a new group thread, it starts that thread on Strict to be safe.

Some work accounts start with stricter defaults. Any setting you choose here still applies.

When you’re asked to approve

When your assistant wants to take an action, you have these options:

Routine modes

Every routine has a default mode that controls how it handles actions. You can change it under Execution mode in the routine’s Tools and permissions panel. Team Routines always run in Auto mode.

Auto mode

Actions execute immediately without asking for approval.

What happens:

• Reading actions run immediately
• Actions that make changes also run immediately
• No approval requests sent
• Fastest execution

Best for:

• Well-tested, trusted routines
• Low-risk actions (labeling, archiving)
• High-frequency triggers (processing every incoming email)
• Routines that only report information to you

Human in the Loop mode

Actions that other people would see wait for your approval before executing.

What happens:

• Reading actions run immediately
• Changes only you see — like labels, archiving, and drafts — also run immediately
• Actions other people would see — like sending email to others, calendar invites, and Slack messages — create approval requests
• You receive notifications with approve/reject options
• Those actions only execute after you approve them

Best for:

• Routines that send emails or messages
• High-stakes automations
• Routines that access external communication tools

How approvals flow:

Per-tool permission levels

You can override the mode for individual tools within a routine. This gives you fine-grained control.

Example: You want a routine that automatically labels and archives emails, but always asks before sending an email. Set the routine to Auto mode, then override the email-sending tool to require approval.

This way, labeling and archiving happen instantly, while sending emails always waits for your OK.

Where to find these settings

Per-tool permissions live in the Tools and permissions panel:

• For your assistant: go to Assistant Settings  → Capabilities & behavior → Tools and permissions.
• For a routine: open the routine and go to its Tools and permissions panel.

The panel lists every tool the assistant (or routine) can use, grouped by category — Email, Calendar, Google Drive, Web Search, Code, and so on. Select any tool to set its Approval mode:

Making your assistant more autonomous

If you find yourself approving the same actions over and over, set the tools you trust to Always allow. This is the most direct way to give your assistant more autonomy: it stops asking for those specific tools and just runs them.

A common setup:

• Set low-risk tools — web search, reading email, viewing your calendar, creating drafts — to Always allow so the assistant moves fast.
• Keep anything that sends externally — sending email, calendar invites, Slack messages — on Ask each time until you’re confident.

Meetings with other people use the Scheduling tools

When a meeting involves other people and your assistant is already working out a time across everyone’s calendars, it doesn’t book with the plain calendar tool. Town deliberately steers that booking to the scheduling engine, which re-checks the time against everyone’s availability before writing the event — so the invite is sent by Commit Scheduling Session, not Create Calendar Event.

That means setting Create Calendar Event to Always allow does not stop approval prompts for those invites. To let your assistant book and send them without asking:

1. Go to Assistant Settings  → Capabilities & behavior → Tools and permissions.
2. Open the Scheduling category.
3. Set Commit Scheduling Session to Always allow.

What counts as a “safe” action?

In the per-chat permissions menu, choosing Allow safe actions (shown as Always allow safe actions in some chats) lets your assistant act without approval cards. The exception is a chat that combines private data, untrusted input, and a way to send things out: there, actions that can communicate externally still ask first. See the lethal trifecta.

Always approved automatically:

• Reading and searching emails
• Adding and removing labels
• Archiving and moving emails
• Creating drafts
• Viewing calendar events
• Reading files

Asks first when the chat combines all three (external communication):

• Creating calendar events with attendees (sends invitations)
• Editing calendar events (can notify attendees)
• Sending Slack messages
• Creating GitHub commits or pull requests
• Updating shared Google Sheets or Docs

Which actions require approval?

In Human in the Loop mode, actions that other people would see require your approval:

Approval notifications

When a routine needs your approval:

1. In the web app — Visible in the chat and on the Notifications page 
2. Your chosen channel — Pick where approval requests reach you under Approvals from routines and your Townie in Settings → Notifications
3. Action options — Allow or reject the action

Each approval includes:

• Which routine is requesting
• What action it wants to take
• The routine’s reasoning
• Options to approve with different scopes

Clearing a backlog of approvals

If pending requests have piled up across several sessions, you don’t have to work through them one at a time. The header of the Notifications page  — and the notification bell in the sidebar — has three actions that apply to every pending request at once:

Each one asks you to confirm first, and none of them can be undone. On the Notifications page a large backlog is processed in batches, so if part of it fails you’ll see how many were handled and the rest still go through. From the bell, Approve all and Reject all are sent as one request, so a big backlog is best cleared from the page.

Progressive trust

A common pattern is to start restrictive and expand trust over time:

At the routine level

New routines start in Auto. If you’d like to review a routine’s actions first:

1. Switch to Human in the Loop — Let it propose actions for your review
2. Return to Auto — When behavior is stable and low-risk

Within a thread

Start a thread on Strict to see every action first, then switch it to Auto as you gain confidence in what your assistant is doing.

Choosing the right mode

Best practices