Equipping Tools

Tools are an AI employee’s capabilities. A newly created employee has every tool from day one (from web search to running code), so there’s nothing to pick and choose. What you do control, per tool, is whether it runs automatically or waits for your approval first.

Setting each tool’s approval policy

1. Open the employee → Permissions tab → Run automation group
2. Expand the Tool Approval Policy section to see the full list (the count next to the title reads something like 44 tools)
3. Use the Run without approval / Approval Required button next to each tool to set whether it must request approval before running (risky tools default to Approval Required, and a few especially risky ones have this button locked to Approval Required)
4. Each change saves right away. There’s no separate save button.

These steps are for the web. The mobile apps (iOS and Android) still change the tool approval policy from the employee’s Settings screen for now.

The employee’s Settings tab also has an External tools (MCP) section, a separate feature. Instead of a per-tool setting, you connect per server: pick an external MCP server you’ve already registered under Settings → External tools (MCP) and connect it to this employee. A connected server’s tools don’t appear in (or count toward) the list above; they’re managed separately, and each server has its own Auto-approve tool calls switch. Leave it off and every call from that server’s tools needs approval.

💡 Note: there’s no way to reduce the tool count. If an employee’s scope is so broad it gets confused, split the work into a team instead, so each AI employee can carry a different job and a different approval policy.

Common tool categories

Category	Tools
🌐 Info gathering	Web Search · HTTP Request · Web Browser
✍️ Output	Ask User · Share File · Canvas Create/Update · Canvas Read · Canvas List
💾 Memory & files	Read File · Write File · Edit File · List/Fetch Received Files
💻 Code/system	Command · Computer Use
⏰ Automation	Create/List/Update/Delete Scheduled Run · Create/Update/List Task · Update Plan
👥 Team collaboration	Team Member List · Team Chat Send/Read · Shared Team Notes Get/Set/List/Delete · Start Child Run
🧩 Skills	Skill Search · Skill Install/Activate · Skill Load · Skill Export · Skill Feedback · Skill Patch
🎨 Creative	Image Generate · Employee Set Avatar
🔐 Connection details	Save/Delete Connection Details · Authorize Webapp Access · Authorize External API Access

How detailed are list/search results?

Tools that scan through several items at once behave differently depending on how often their results get acted on right away. List Scheduled Runs and Team Chat Read normally show just the key facts, then fetch the fuller version (with whatever detail a follow-up needs) once the employee decides it’s about to act on one of those results (updating a scheduled run it just looked up). Canvas List, List Tasks, and Skill Search default to the fuller version already, since acting on a result immediately (installing a skill it just found) is the common case for these. Either way, the employee makes this call mostly on its own, but you can also nudge it: asking for “just the summary” or “the full details” gets you the corresponding version.

🌐 Information gathering

Settings label	When to use
Web Search	When you need to search the web by keyword (with optional domain allow/block lists). Automatically combines multiple search engines and breaks complex queries into sub-searches, returning results with citations
HTTP Request	When you know the URL and need to call an external API or fetch a static page. Supports custom methods, auth headers, and request bodies
Web Browser	Sites that require login, clicks, scrolling, or input. Whether a click auto-proceeds or shows an approval card depends on what the target element does: a “Post” or “Pay” button always asks; opening a menu does not. A logged-in site’s session can be saved straight into secure storage for reuse, so the password or login values never appear in the conversation or logs. See Handling Approvals for the full breakdown

Tip: For quickly pulling information, web search is the lighter, faster option. Reach for Web Browser when you need to work a site directly (login, clicks, or typing). You can also grant both and let the employee pick whichever fits the task.

Connecting a browser makes both stronger: with a browser connection linking this computer’s Chrome or Edge to the employee, Web Search and HTTP Request automatically run through that browser instead. Search reads the exact results page you’d see yourself, and both tools can now reach sites that only work once you’re logged in, or that are only reachable from this computer. See the browser connection doc for setup.

✍️ Output

Settings label	When to use
Ask User	Ask the user a question mid-flight and wait for the answer. It can bundle up to 4 questions into one round trip, answered together in a single reply, and any question can allow picking several options at once instead of just one. When it needs a sensitive value like a password or API key, the question card also shows an Answer with secure input button, so you can hand it over without ever typing it into the chat box
Share File	Share a generated file as a download link. Regular attachments like images stay free and permanent up to 10MB; documents (PDF/PPTX/DOCX) up to 10MB; other archives and data files (zip/tar/parquet, etc.) up to 200MB; video up to 1GB. Video is always billed in SU by size and auto-deleted after 14 days regardless of size; other files are billed and expire the same way only once they pass 10MB. Either way the original is removed after 2 downloads
Canvas Create/Update	Show markdown/code/document content (or a full webpage or slide deck) in the in-app canvas panel (same title → new version)
Canvas Read	Pull the current content of a canvas the employee already created. Used before a partial edit, to see the full text again
Canvas List	List the canvas documents the employee has created
Send Card	Always-on plumbing, not shown in settings. Attaches a structured card (info card, connect with account, file picker, etc.) alongside a message, available whatever run condition started the run

Canvases now come in just two forms: document and slide deck (the old standalone “webpage” type has been folded into documents). A plain document or webpage with no slide markers is automatically treated as a page: one continuous, scrollable view.

Tip: For a page-style canvas, use the export button in the top-right corner to save it as HTML, PDF, or PNG, and in the web app you can view and edit the source directly, or double-click text in the preview to edit it inline (mobile apps are view-only). A slide-deck canvas works differently: hit Edit and a dedicated slide editor opens, with your slide list on the left and a working canvas on the right. Draw and place text boxes, images, and shapes freely; adjust color, font (20 options, including 11 Korean and 5 Latin web fonts), alignment, and formatting; drop in tables and charts; apply layout and theme presets; undo/redo and copy/paste; and reorder slides by dragging their thumbnails. It handles like a real slide-design tool. Each slide can carry its own presenter notes, and once you’re done you can play the deck right there or export it as PPTX, PDF, or PNG. Vertical formats like Instagram-story ratios are automatically laid out correctly too (mobile apps are view-only for the slide editor as well). Either way, when you edit a canvas, the employee picks up your changes the next time it works on it. A single canvas can hold up to roughly 8 million characters; saving is rejected past that, so trim images or split the document if you hit the limit.

A canvas card in a chat bubble isn’t a live link that reloads the newest content every time you click it. It’s a snapshot of what existed the moment that card was created. When an employee revises the same document several times, cards keep piling up in the conversation, and clicking one opens the version it was created from, not today’s latest, so you can see exactly what a given pass changed. While you’re viewing a past version, the edit and delete buttons disappear and only a Back to latest button remains; you can still tap the version indicator at the top to open the version history and jump to other points in time. Pick an older version and hit Restore this version to bring it back as the current one. Version history doesn’t grow forever, though: everything saved in the last 14 days is kept, and anything older than that is kept only for the most recent 20 versions (a version you edited yourself, and whichever version is current right now, are always kept regardless of age or count). Opening a version that’s aged out shows the current version instead, with a note explaining why.

If the same canvas gets edited and saved from another device or another chat session first, trying to save from the screen you’re on shows a “this canvas was updated elsewhere” notice. You get to choose: Reload (replace your screen with what was just saved), Overwrite with mine (save your edits as-is), or cancel (dismiss the notice and keep editing). Nothing is silently dropped either way. Web, iOS, and Android all work the same way here.

💾 Memory & files

Settings label	When to use
Read File / Write File / Edit File	Work with the employee’s working files and persistent storage
List/Fetch Received Files	Find files you or a team member uploaded, or a large attachment sent in chat, and pull one into the current workspace. Works for employees that aren’t on a team and for attachments sent in one-on-one conversations too. The list shows a short preview of a file’s text content, and once fetched, the employee reads a document or spreadsheet’s actual content to work with it directly
Memory Scan	Always-on plumbing, not shown in settings. Lets the employee list its own accumulated memories
History Search	Always-on plumbing, not shown in settings. Searches set-aside chunks of earlier conversation from long sessions by keyword; the body of a match is then pulled back with Read File above
Source Chat Read	Public version sessions only, not shown in settings. Reads the original user’s conversation up to the moment the public version was made, useful when a visitor asks about decisions or facts that predate it
Read Public Version Transcripts	Dynamically provided to employees that have published at least one public version link. Review the conversations external users had through your shared links to improve future versions

Tip: Recall happens automatically on every turn. For employees that repeat work, keeping Read File / Write File enabled helps them build on what they’ve learned.

💻 Code & system

Settings label	When to use
Command	Run a one-shot shell command on the isolated AI work computer (data wrangling, file processing, simple API calls). Stdout and stderr are returned separately. A long-running command doesn’t lose its result if the connection drops mid-run. It keeps running on the AI work computer, and the employee reconnects to pick up whatever it produced so far
Computer Use	Control the AI work computer’s GUI desktop environment and shell. Includes terminals and general GUI apps, not just browsers

⏰ Automation

Settings label	When to use
Create / List / Update / Delete Scheduled Run	Let the employee register and manage its own scheduled runs. Supports recurring runs (e.g. every day at 9 AM) and one-time delayed runs (e.g. run once in 30 minutes)
Create / Update / List Task	Explicitly track multi-step tasks with dependencies and completion state, for commitments that span multiple sessions
Update Plan	Automatically maintains a step-by-step checklist for whatever the employee is working on right now. Remembers finished steps so it doesn’t re-fetch the same source or re-read the same file. Where Task (above) is a lasting, cross-session commitment, this is a lightweight checklist scoped to the current piece of work only
Open / Dispatch to / Complete Workspace	Always-on plumbing, not shown in settings. Keeps recurring work that needs to be revisited in a separate workspace instead of mixing it into the main chat. See Working Across Workspaces for details

👥 Team collaboration

Settings label	When to use
Team Member List	Discover other team members (for @mentions)
Team Chat Send / Read	Post to the team chat. @EmployeeName wakes up that team member automatically. When a mention requires a reply, the mentioned team member sends a return mention once it finishes. A thread reply (a reply to a specific mention) can wake the original sender even when the mention link only points the other way
Shared Team Notes Get / Set / List / Delete	A memo the whole team can read and write (facts, decisions, and reference info, separate from each employee’s own memory). Only the last team member to write a value, or the manager, can delete it
Start Child Run	Delegate part of the work to a one-off child run and collect the result. Available equally to employees on a team and to those working solo

Tip: There’s no tool for adding an AI employee. Press + Hire on screen and someone new starts right away, asking you about the job themselves. There’s no “equip” step for an existing employee either: every employee has every tool from day one. See Setting Up a Team for the full flow.

🧩 Skills

Settings label	When to use
Skill Search	Search Official skills in the Skills tab or the employee’s own Library
Skill Install/Activate (⚠️ approval required)	Add a skill found in Official skills to this employee, or install one directly from a public GitHub repo (owner/repo) by its address. The latter needs the Also allow public GitHub repos checkbox nested under this item switched on. Either way, the first call installs nothing and only previews the skill’s description (SKILL.md) and file tree; calling again with the same target actually installs it. Carries higher risk, so no auto-approve scope is ever offered; every call needs its own one-off approval. An official skill install is registered as a reference to the original without copying content; if you have previously customized the skill, your version is used
Skill Load	Deploy an installed skill’s files onto the AI work computer and load its instructions. The employee then runs it itself with the Command tool
Skill Export	Automatically packages code on the AI work computer into a reusable skill and saves it as a draft. A review card arrives right away, and you save it from that card to keep it as your own private skill (it can’t be made public)
Skill Feedback	Reports a defect in a skill the employee just used; for someone else’s skill it goes to the author as an improvement suggestion, and for a skill you have customized yourself it points you to fix it directly
Skill Patch	Self-edits a skill you have customized via exact-string replacement; saves a version before and after the change so you can roll back to the earlier one
Skill Inspect	Always-on plumbing, not shown in settings. Runs automatically the first time Skill Install is called, previewing a skill’s full description file (SKILL.md) and bundled file list before installing

🎨 Creative

Settings label	When to use
Image Generate	Text→image, reference-image edits (up to 14 reference images), multi-turn iterative refinement. Four resolution tiers (512·1K·2K·4K) and 14 aspect ratios available. A generated image keeps working as a real file in later turns: the employee can process it with the Command tool, embed it in HTML, or share it as a download, and it can drop the image straight into a Web Browser upload field or a file dialog opened through Computer Use (e.g. “put the logo you just made into this upload form”)
Employee Set Avatar	Change the employee’s profile image via AI generation or URL. Any employee can update its own avatar

🔐 Connection details

The screens for storing and managing connection details are covered in full in Connecting External Services. Here’s just what each tool does.

Settings label	When to use
Save / Delete Connection Details	Store a value the employee received in chat (or obtained itself) under a name for long-term reuse, or remove it. Once saved, the employee can reuse it even during scheduled and other automatic runs when no one is watching
Authorize Webapp Access (⚠️ approval required)	Asks the owner to let a webapp the employee built and published call an external service using a stored account or connection details. The approval card summarizes exactly what it would be allowed to do
Authorize External API Access (⚠️ approval required)	Asks the owner to let the Command tool call an external service directly using a stored account or connection details, approved the same way, with a summary card

Approval (human-in-the-loop)

Each tool has its own Run without approval / Approval Required setting. Skill Install/Activate (GitHub installs included) has its per-tool approval setting turned on to Approval Required from the start, so the employee has to wait for you to approve from chat before running it.

Skill Export is not approval-required. It runs automatically. The moment the employee calls it, a draft skill is created and a review card arrives with it, and you save it from that card to keep it as your own skill. Saved skills are private to you.

Beyond that, a few more tools ask for approval by default because of what they do. Share File, Start Child Run, Create/Update/Delete Scheduled Run, Authorize Webapp Access, and Authorize External API Access raise an approval card before running by default. The last two carry even higher risk, so no auto-approve scope is offered for them at all: every call needs its own one-off approval. HTTP Request (requests that send or change data), Computer Use (actions that change the screen), and Web Browser (actions with lasting effects like posting, paying, or deleting) also ask depending on how risky the action is. You can still tune these through their per-tool setting or your auto-approve settings. See Handling Approvals for the full breakdown.

Example tool combinations

Since every tool is already there, these aren’t “enable only these”; they’re a guide to which tools matter most for each kind of work.

📰 Information curation employee

Web Search is the core one. Automatic runs deliver their results straight to chat automatically regardless of their run condition, plus a push notification if you’re not looking at the app.

📊 Monitoring employee

HTTP Request + Memory Scan + Write File + Create/List Scheduled Run: track changes over time.

📝 Report writing employee

Web Search + Write File + Canvas Create/Update: research, write, and display in-app.

🔧 Data wrangling employee

Command + Write File + Share File: process data and deliver as a download link.

The tool list looks long. Is that a problem?

No need to worry about the length of the full list. What actually reaches the model each turn is automatically compressed down to what’s relevant in the moment, so the number of tools on the list doesn’t by itself slow responses down or raise cost.

The real limit isn’t tool count. It’s one employee’s job being too broad. When that happens, split the work into a team instead. Each AI employee can carry a different job and approval policy, and they coordinate through team chat.

---

Advanced

Read this only if you want to know exactly how approval decisions are made, or why some tools never show up in Settings.

• There’s no way to turn tools on or off: every employee is created with the full tool set already, and no screen lets you toggle individual tools. The only thing you set per tool is whether it needs approval.
• How approval is decided: Each tool judges its own risk from the call itself. Web Browser, for example, only asks for approval when the element it’s about to click does something hard to undo (“Post,” “Pay,” “Delete”) and lets ordinary clicks, like opening a menu, proceed automatically. On top of that, your per-tool Run without approval / Approval Required setting applies, along with whatever auto-approve scope you picked from an approval card (next N calls, for the rest of this task, or always). The Command tool loses only the “always” option, for safety; the other scopes stay available. Skill Install/Activate (GitHub installs included), Authorize Webapp Access, and Authorize External API Access carry even higher risk: no scope picker appears for them at all, so every call needs its own one-off approval.
• Always-on built-in tools: Send Card, Memory Scan, History Search, and the skill-preview step that runs automatically the first time you install a skill are wiring every employee carries by default. They don’t appear in Settings and can’t be turned off.
• Tools only visitors get: In a public version session, a couple of extra tools attach automatically for the external visitor: reading the original conversation up to the share point, and (once you’ve published at least one public version link) reading back what visitors discussed through your links. Neither shows up in your own Settings list.
• Recently widened access: Start Child Run (sub_spawn) is now granted to employees on a team too. It used to be missing from team members’ tool set. List/Fetch Received Files (file_list/file_fetch) scopes access by organization, not team, so it also reaches employees that aren’t on a team and attachments sent in one-on-one conversations. A file assigned to a specific team is reachable only by that team’s members, while a file with no team assigned is reachable by anyone in the same organization.
• Retired tool names: The old Notify User, Team Agent Create, Team Agent Equip, and History Read tools no longer exist. Notify User was replaced by automatic delivery: automatic runs now reach you in chat and, via push if you’re not looking at the app, regardless of their run condition. Creating an AI employee moved to the Hire button on screen (the manager’s own creation tools, Create Agent and Create Team, were retired alongside it on 2026-08-21); the separate tool for adding tools to an existing employee was dropped entirely once every employee got every tool from day one; History Read was absorbed into Read File; and GitHub Skill Install was folded into Skill Install/Activate as a second way to call the same tool, by address instead of ID. Older conversation history may still show these retired names.

Next steps

• Installing Skills & Templates: Use official packages where the tool combination is already tuned
• Skills & the Autonomous Skill System: Save proven procedures as reusable skills. Covers how Skill Feedback and Skill Patch connect to the autonomous skill system in detail.