Modes, Feedback, and Tips
How you set up and phrase a request shapes how well Autopilot does it. This page covers the two reasoning modes, the two ways to view Autopilot's work, how to attach files, how to give feedback, the keyboard shortcuts, and prompts you can copy to get started.
Fast and Thorough modes
Autopilot offers two reasoning modes. You choose one per conversation, before you send your first message, using the toggle in the bottom-left of the composer.
- Thorough — the default. Autopilot reasons more deeply and surfaces its thinking and tool steps. Use it when you are building, editing, or refining an AI Employee, or for any multi-step request.
- Fast — quicker responses with streamlined reasoning. Use it for simple, single-step requests like looking up information or listing AI Employees.
When Fast is on, the toggle shows a lightning icon and the label Fast mode; click it to switch back to Thorough. Thorough mode shows no special badge because it is the default.
The mode locks once the conversation starts. After your first message lands, the mode is fixed for the life of that conversation and can't be changed mid-conversation. If you picked the wrong one, start a new chat and set the mode before sending your first message.
Narrative and Developer view
The view setting controls how much detail Autopilot shows about its work. Change it from the More actions menu (the three-dots button in the panel header) under View mode.
- Narrative — the default. Autopilot's steps are grouped into clear, human-readable summaries — "Searched knowledge base," "Created workflow," "Completed 3 sub-tasks" — so you can follow along without technical detail.
- Developer — shows the individual tool steps verbatim, each with its inputs and outputs, plus Autopilot's step-by-step reasoning. Use it to debug an AI Employee's behavior or to see exactly how Autopilot carried out a task.
Both views show reasoning (Autopilot's thinking, when the mode produces it) and tool steps (the actions it takes); Developer view simply shows them in full rather than summarized. A long tool output is previewed with a Load full output control to expand it.
The same menu has a Thinking setting (Off, Minimal, Low, Medium, High) that controls how much room Autopilot has to reason before it acts. Higher levels are slower but better on hard, multi-step problems. Your view and thinking choices are remembered across sessions.
Uploading files
Attach a file to give Autopilot extra context — a policy document for an AI Employee to learn from, or a spreadsheet of test questions. There are three ways to attach:
- Select the plus (+) button in the composer to open your file picker.
- Drag and drop files into the panel — a highlighted border appears to show the drop zone is active.
- Paste an image directly into the composer.
Attached files appear as chips above the composer showing the filename and size, with an X to remove one before you send. After attaching, tell Autopilot what to do with the file — for example, which AI Employee the data belongs to.
Each file must be under 20 MB. A larger file is rejected with a message naming the file and the limit. Attachments are not saved as drafts — if you close the panel before sending, you'll need to re-attach.
Giving feedback
Your feedback helps improve Autopilot. Hover over any Autopilot reply to reveal an action row:
- Thumbs up — marks the reply as helpful and saves it right away.
- Thumbs down — opens a short form where you can pick a reason and add an optional comment, then submit. The reasons are: Wrong or lacking information, Not what I requested, Laggy or malfunctioning, Safety or legal issue, and Miscellaneous.
- Copy — copies the reply text to your clipboard.
Feedback is per reply, so you can rate individual responses within the same conversation. Selecting a thumb again clears your rating.
Keyboard shortcuts
You can drive Autopilot without leaving the keyboard.
| Shortcut | Action |
|---|---|
⌘E / Ctrl+E | Open or close the Autopilot panel (works anywhere in the builder) |
⌘⇧E / Ctrl+Shift+E | Flip between side panel and expanded view (while the panel is open) |
Esc | Close the side panel |
Enter | Send your message |
Shift+Enter | Insert a new line in the composer |
Example prompts
When you open a new conversation, the welcome screen shows suggestion cards that pre-fill the composer when you select one. The starting set covers the most common first tasks:
| Card | What it sends |
|---|---|
| List my workflows | Lists the most recent workflows (AI Employees) in your tenant |
| Search the knowledge base | Searches a Knowledge base for a topic and summarizes the top results |
| Inspect an integration | Lists the integrations installed in your tenant and which are healthy |
| Browse templates | Shows the workflow templates available in your tenant |
Beyond the cards, here are prompts you can paste and adapt:
List the most recent 5 workflows in my tenant.
Search my knowledge base for our refund policy and summarize the top results.
Draft a one-page onboarding guide covering our PTO policy, expense process, and IT setup checklist. Use headers and bullet points.
Write specific prompts. Name the AI Employee, the data, and the outcome you want. A specific request lets Autopilot take the right steps the first time and cuts down on back-and-forth. For a full build, you can tell Autopilot to "make all design decisions yourself without asking me for input" — it will still pause for approval on destructive actions and on deploy.
For the complete set of actions you can ask for, see Core actions.
What's next
- Core actions — everything Autopilot can build and change.
- Permissions and scoping — what Autopilot can access and when it asks for approval.
- Limits, availability, and troubleshooting — what Autopilot can't do, and what to do when it's unavailable.