Everything you need to start, configure, and manage chats with CellCog agents: the editor chips, modes and tiers, the header bar, per-message actions, chat search, and the Agent Computer.
Cowork, Browse, and Tools each carry an approval level for the chat, so you decide how much the agent may do on its own before asking you.
The Tools chip has three positions:
You can connect a new tool from inside the picker, and the gear icon takes you to your connections. AI employees keep their own Tools selection, separate from your chats. See the Connectors & Tools Guide.
Browse works through your own Chrome and the CellCog extension. The chip lists your Chrome profiles: a green mark means the extension is installed and connected in that profile, amber means installed but not connected right now, and gray means the extension is not installed there. Click a profile to enable Browse for this chat with that profile; commands route to the profile the chat is bound to, so you can keep several profiles open.
AI employees are different: on a paid account, each one has its own cloud browser with its own logins, managed from Browsers (under Apps in the sidebar). Cloud browsers belong to employees, not to chats. See the AI Employees Guide.
You can attach files directly to any chat message. Each file can be up to 1GB; large uploads use resumable transfer, so a flaky connection picks up where it left off instead of starting over. Images are limited to 25MB per file. Uploaded files land in the agent's workspace, where it can read, analyze, and transform them.
Every file in a chat sits in one place: click the folder icon in the chat header (it shows how many files the chat has). It lists every file the agent showed you and every file you uploaded, in the order they appeared in the chat, oldest first. New files join at the end as the chat goes on.
On a wide screen the list opens beside the chat; on a phone or tablet it slides up from the bottom.
In an AI employee's chat, Files covers everything the employee has ever shown or you have uploaded. It opens at the newest files; scroll up for older ones. Show in chat takes you to that part of the conversation, and ↓ Latest messages brings you back.
Every chat runs on two settings you pick together in the selector: a mode (which agent does the work) and a tier (how much depth it runs with: Flash · Core · Max). Any combination is one click, and every mode row carries an info icon that opens a learn card with Speed and Depth meters, so the tradeoff is visible before you pick.
Best for:
Think of it as: one agent that executes your instructions, iterates on feedback, and produces videos, images, reports, code, and more, across every modality rather than just code.
When to avoid: when you need deep, multi-angled research out of the box, like academic work. Agent Team does that by default.
Best for:
Think of it as: our most imaginative agent, the same single agent as Agent Mode, tuned for taste. Give it a design brief and it delivers polished, opinionated results.
When to avoid: programmatic work, coding-heavy tasks, or deep research. Use Agent Mode for fast iterative and programmatic work and Agent Team for deep research.
Best for:
Think of it as: a team of specialized agents that research deeply, challenge each other's findings, and produce well-rounded outputs in any format you need.
When to avoid: when you expect many iterations to reach the final output. Each run costs more, so for back-and-forth refinement, Agent Mode gives more control at lower cost per iteration.
| Tier | What it means |
|---|---|
| Flash | Our quickest, most economical configuration of that agent. Answers begin almost immediately. Good for everyday questions and edits. |
| Core | The balanced everyday point, with real reasoning depth. |
| Max | The deepest configuration we can build for that agent. |
The selector stays live inside a conversation: switch between Agent Mode and Agent Creative, or change any mode's tier, at any time. Changes apply from your next message, with no lost context. The one exception is Agent Team: its multi-agent setup is created when the chat is born, so Team is chosen at creation and cannot be switched on or off mid-conversation.
It became a cell on the grid: Agent Team on the Max tier, every setting maximised, for high-stakes work like legal analysis and financial decisions where quality justifies the extra cost. Same premium orchestration as before, and existing chats keep their exact behavior.
The modes above are how you work with a CellCog agent directly: you send a message, it responds. If you instead want a worker that runs on its own, hire an AI Employee. An AI employee runs on the same engine, but it has its own email inbox, its own cloud browser (on a paid account), a place on your organization's task board, routines that wake it on a schedule you or it defines, and a memory that persists across sessions. You can also hand it work from any chat by asking the agent to put a task on that employee's board. See the AI Employees Guide.
In an active chat, the header shows the chat's mode and tier (hover the icon for a description), a meter of how much of the conversation's context is in use, and these controls:
| Control | Function |
|---|---|
| Files (folder icon with the file count) | Open every file in this chat in one list (see Files in a Chat) |
| Agent Computer (computer icon) | Open the agent's filesystem and workspace (in an AI employee's chat this is the Employee Computer, which opens on its Home app) |
| Save Artifacts | Save generated files to My Drive, the Organization Drive, or a project |
| Share | Make the chat and its apps public or private, and copy its link (not in AI employee chats: employees can't be made public) |
| View usage | Open the Usage app on this chat: the credits it has used, by day and by kind of work. In an AI employee's chat, it opens that employee's Usage app, covering every run |
Every message carries a small toolbar that appears when you hover over it: the timestamp and Copy message on every message, Delete message on your own messages (see below), plus Save Artifacts and Share on the latest agent reply. On touch devices there is no hover, so the buttons stay visible. Links to apps the agent built appear as tiles inside the message itself.
You can delete any message you sent, for example one where you pasted something private by mistake.
The message turns into a placeholder that reads "This message was deleted", and any file you attached to it is deleted too. Your agent sees a short note in its place saying the message was deleted, so it stops relying on what it said.
What it costs. Your agent re-reads the conversation from the deleted message onward on its next reply, so that one reply costs more than usual. Deleting a message from an earlier part of an AI employee's history costs nothing: that part of the conversation is never read again.
Limits:
Agents can write math and it renders in chat: $...$ for inline expressions and $$...$$ for display equations. Plain dollar amounts such as "$25 and $30" stay ordinary text; rendering only switches on when the span contains real math notation.
Click the magnifier at the top of the sidebar (or press ⌘K / Ctrl+K) and type at least two characters. Search covers chat names and message content across all your chats, including your AI employees' sessions, and also matches your employees, channels, and DMs by name. By default, chats are ordered by relevance: name matches come first, then content matches with highlighted snippets showing why a chat matched. Choose Newest first on the right to order the matching chats by their latest activity instead; your choice is remembered. Use the type filter to narrow the results (for example to Employees), then click a result to open it. A content match opens the chat, or your AI employee's conversation, at the matching message and highlights it, even when it is in an earlier session.
The sidebar shows a shortcut next to New chat when you hover it, in your platform's keys. On a Mac the modifier is ⌘; on Windows and Linux it is Ctrl.
| Action | Mac | Windows / Linux |
|---|---|---|
| New chat | ⇧⌘O | Ctrl+Shift+O |
| Search chats | ⌘K | Ctrl+K |
| Show or hide the sidebar | ⌘\ | Ctrl+\ |
| Start or stop voice input | ⇧⌘U | Ctrl+Shift+U |
| Send message | Enter | Enter |
| New line in the editor | Shift+Enter | Shift+Enter |
The sidebar groups your work into AI Employees and Chats. Each chat row shows:
Hover a chat and click its three-dot menu (⋮) to Rename it, Add to project (or Move to project and Remove from project once it is in one), or Delete it. Chats can be filtered by project using the project selector in the sidebar navigation. Drives, Avatars, Browsers and the other apps sit in the Apps grid of the sidebar; More holds the Learn links (Podcast, Blogs, Tutorials) and Pricing, plus the Apps grid when the sidebar is collapsed.
⚠️ Warning: deleting a chat permanently removes all messages and history, generated files, code, and apps, associated media, and uploaded files. This action cannot be undone.
The Agent Computer lets you see the agent's workspace:
The Agent Computer is a file browser. It does not include a web browser tab; only AI employees have a browser of their own (the Browser app inside the Employee Computer). Files stay put between sessions: workspaces of chats you have not opened in a while are archived and restored automatically the next time you return, and software the agent installs in its workspace persists with it.
Save generated content to persistent storage:
Apps the agent built can be saved as .ccapp shortcuts that open the app straight from Drive. See the Drive Guide and the Apps Guide.
Every chat reads the shared memory of My Drive and the Organization Drive: the facts, skills and canon your agents have saved. Every chat may also save durable facts and skills to My Drive and the Organization Drive memory once, quietly, after it goes idle: a correction to how the agent works, a preference you stated, a method worth reusing, a decision you made. Nothing changes in the chat: it sends you no message, keeps the status it stopped with, and saves no files or other artifacts unless you asked.
To save something now, just say so in the chat ("remember that I prefer short summaries", "save this as an organization skill", "save the final report to the project"). See the Memory System & Context Trees Guide.
CellCog comes with a few skills built in: proven methods we review and install for every user, so any chat or AI employee can use them with no setup. Nothing needs turning on. Name the skill in your message, for example: "Use the Anatomy skill to draw an isometric figure that shows how our checkout works."
| Skill | What it makes |
|---|---|
| Anatomy | Detailed, interactive isometric figures that explain a technical idea as a physical object, for docs, blog posts and landing pages |
| diagram-design | Branded diagrams (architecture, flowcharts, sequence diagrams, timelines, org charts and about 40 more types), exportable to PNG and SVG |
| UI/UX Pro Max | Interface design help: pages, components, design systems, accessibility, color and typography |
Credits: Anatomy, by Ryan (wheresryan22), MIT License, adapted by CellCog · diagram-design, by Cathryn Lavery, MIT License, adapted by CellCog · UI/UX Pro Max, by Next Level Builder, MIT License, adapted by CellCog.
Built-in skills can't be edited, and a skill of your own with the same name takes their place. See Skills in the Memory System & Context Trees Guide.
When an agent builds an HTML app, dashboard, or report, it lives in the chat's workspace and is served at its own URL. Apps are private by default; the Share control makes them public (AI employees' apps can't be made public). Paste an app's URL into a new chat to keep editing it. See the Apps Guide.
CellCog agents excel at complex, multi-step work described in natural language. You do not need special syntax or a builder: just describe what you need.
Write your prompt as a natural sequence of steps. The agent executes them in order, using earlier results to inform later steps. For example:
"First, research the top 10 competitors in the AI coding assistant space. Then analyze their pricing models and create a comparison spreadsheet. Finally, based on that analysis, write a strategic recommendation for our pricing."
The agent will:
CellCog's average first prompt is long. Our users routinely submit multi-step jobs with multiple deliverables in a single message, and executing a complex, multi-deliverable brief end-to-end (reports, spreadsheets, presentations, images) in one go is one of CellCog's core strengths.
For work that should happen on a schedule without you starting it, use an AI employee: put standing work on its task board and give it a routine. Chats are for interactive work you start yourself.
Chats are named automatically from their content. To choose your own name, hover the chat in the sidebar, open its three-dot menu, and select Rename.
Two ways, same result: open the chat's three-dot menu (⋮) in the sidebar and pick Add to project, or open the chat and choose the project in the Project chip of the message editor. From then on the chat can read the project's documents, and it appears on the project's Chats tab. Pick Remove from project on the same menu to unlink it.
Three ways. A sound plays in the tab when a chat finishes, needs you, or stops with an error (mute it under Settings, Notifications). For a system notification on your devices even when the tab is closed, turn on Browser notifications in Settings, or accept the offer that appears once a chat has been working for a moment: the switch is for your account, and each device asks once for your browser's permission (the same Settings row shows whether the device you are on has allowed them). Sound and browser notifications follow one rule: they fire when a chat finishes, needs you, or stops with an error, and only for the person who sent the message that started the work. An AI employee working on its own schedule does not notify anyone; what it needs from you appears on your task board and in its report. And if a completed chat stays unopened for 30 minutes you get a reminder email, at most a few per day. The email says whether the chat finished or is waiting on your input, and matches how the chat was started: opened in the browser, started by your agent through an API key (with the retrieval snippet), or started by a connected app such as Claude (with what to tell it). A result your agent or connected app already fetched counts as seen, so those chats never trigger the email.
No. Chat deletion is permanent and cannot be undone. Save important artifacts before deleting.
Hover over the message and click the trash icon next to Copy. The message and any file you attached to it are deleted, and the rest of the chat stays as it is. See Deleting a Message above for what it costs and what it does not reach.
Click the folder icon in the chat header (it shows how many files the chat has). Every file in the chat is there in chat order, and Show in chat takes you to the message that showed it. See Files in a Chat.
Click any chat in the sidebar, or find it with Search chats. Your full history is preserved.
Open the header menu and select View usage. It opens the Usage app on that chat; in an AI employee's chat, it opens that employee's own Usage app, covering every run it has made. To see every AI employee and chat at once, open Usage under Apps in the sidebar.
No. Scheduling belongs to AI employees: routines wake an employee at the times you or it define. See the AI Employees Guide.
Our safety systems locked it. A locked chat stays readable, but no new messages can be sent. We don't share what triggered a lock. If you think it was a mistake, use the Contact support link shown in the chat.