Support

CellCog Chat Guide

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.


Starting a New Chat

  1. Click New chat in the sidebar (or press ⇧⌘O on a Mac, Ctrl+Shift+O on Windows and Linux)
  2. Type your prompt in the editor ("What can I do for you?")
  3. Configure options with the chips under the editor (all optional):
    • Cowork: give the agent access to your computer's files and terminal (see Cowork on my PC Guide)
    • Browse: give the agent access to your real Chrome browser (see Browse my Chrome Guide)
    • Tools: decide which of your connected tools the agent may use in this chat (see below)
    • Project: link the chat to a project and its documents
    • Agent role: once a project is selected, pick one of its agent roles
    • Mode and tier: the selector on the right chooses which agent does the work and how much depth it runs with
  4. Use the + button to attach files from your device or from Google Drive
  5. Press Enter or click send

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

The Tools chip has three positions:

  • All: every tool you have connected, plus the keys captured with them, can act in this chat
  • Choose: pick a subset for this chat. The picker lists your connected services, standalone keys, and your own MCP servers as one list. Picking a service includes its connector and any keys captured with it; you never have to tell connectors and keys apart
  • Off: the agent can still look up what tools exist, but cannot call them

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.


The Browse Chip

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: each one has its own cloud browser with its own logins, managed from Cloud Browsers (in the sidebar's More menu). Cloud browsers belong to employees, not to chats. See the AI Employees Guide.


Uploading Files

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.


Chat Modes: the Mode × Tier System

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.

The Modes

Agent Mode

Best for:

  • Fast, iterative work, suitable for most tasks
  • Step-by-step control with feedback after each task
  • The most versatile mode: building, editing, research, coding, co-work

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.

Agent Creative

Best for:

  • Web design, UI design, and frontend/visual work
  • 3D generation and other creative content
  • Product thinking: it excels as a product manager and designer
  • Ambitious one-shot creative builds

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.

Agent Team

Best for:

  • Deep multi-angled reasoning from multiple perspectives
  • Deep reasoning across every modality: reports, videos, images, code, PDFs
  • A team of agents that debates, cross-validates, and delivers comprehensive results

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.

The Tiers

table
TierWhat it means
FlashOur quickest, most economical configuration of that agent. Answers begin almost immediately. Good for everyday questions and edits.
CoreThe balanced everyday point, with real reasoning depth.
MaxThe deepest configuration we can build for that agent.
  • Agent Creative has all three tiers. Its Flash still thinks hard on every pass, so it suits quick design and writing work.
  • Defaults: a fresh chat opens on Agent Mode · Max; Agent Creative and Agent Team default to Core.
  • Credits to start a chat: any positive balance starts a chat in every mode and tier; there is no per-mode minimum. See the Billing Guide.

Switching Mid-Chat

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.

What happened to Agent Team Max?

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.


Chats vs. AI Employees

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, 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.


Chat Header Bar

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:

table
ControlFunction
Agent ComputerOpen the agent's filesystem and workspace (in an AI employee's chat this is the Employee Computer, which opens on its Home app)
Save ArtifactsSave generated files to My Drive, the Organization Drive, or a project
Update Agent MemoryStore this chat's insights in the agent role's memory (shown only when the chat has an agent role)
ShareCopy a link to the chat, make its apps public or private, or publish a community post
View CostsSee how many credits this chat has used

Per-Message Actions

Every message carries a small toolbar that appears when you hover over it: the timestamp and Copy message on every message, 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.


Math in Chat

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.


Search Chats

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. Name matches come first, then content matches with highlighted snippets showing why a chat matched. Use the type filter to narrow the results (for example to Employees), then click a result to open it.


Keyboard Shortcuts

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.

table
ActionMacWindows / Linux
New chat⇧⌘OCtrl+Shift+O
Search chats⌘KCtrl+K
Show or hide the sidebar⌘\Ctrl+\
Start or stop voice input⇧⌘UCtrl+Shift+U
Send messageEnterEnter
New line in the editorShift+EnterShift+Enter

Chat Sidebar

The sidebar groups your work into AI Employees and Chats. Each chat row shows:

  • Chat icon: a visual identifier chosen by the agent
  • Chat name: auto-generated, or your own (see Rename below)
  • Hover card: project, mode, and when the chat was last updated

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. The sidebar's More menu holds Drives, Avatars, and Cloud Browsers, plus the Learn links (Podcast, Blogs, Tutorials) and Pricing.


Deleting a Chat

  1. Find the chat in the sidebar
  2. Hover over the chat name and click the three-dot menu (⋮)
  3. Select Delete
  4. Confirm the deletion in the dialog

⚠️ 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.


Agent Computer

The Agent Computer lets you see the agent's workspace:

  1. Click Agent Computer in the chat header (the button shows "Starting..." while the workspace spins up)
  2. Browse the filesystem: generated files, downloaded resources, code and apps
  3. Click files to preview them; use the toolbar to move between folders

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 Artifacts

Save generated content to persistent storage:

  1. Click Save Artifacts in the header menu, or on the latest agent reply
  2. Choose destinations:
    • My Drive: your personal storage
    • Organization Drive: shared storage for every member of your organization
    • Projects: documents of a project you administer
  3. Confirm the save

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.


Update Agent Memory

For project chats with an agent role, you can manually update the agent's memory:

  1. Open the header menu and select Update Agent Memory
  2. Optionally describe what the agent should store
  3. The agent reviews the chat and stores relevant artifacts and insights

Requirements:

  • The chat must be linked to a project
  • The chat must have an agent role assigned
  • The chat must not be currently operating

The same memory update also runs automatically after the chat has been idle for a while. See the Memory System & Context Trees Guide.


Apps Agents Build

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. Paste an app's URL into a new chat to keep editing it. See the Apps Guide.


Complex Prompts & Multi-Step Tasks

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.

How It Works

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:

  1. Complete the research phase
  2. Analyze and create the spreadsheet
  3. Use those findings to write the recommendation

Tips for Complex Prompts

  • Be explicit about sequence: "First do X, then based on those results, do Y"
  • Mention output formats: "Create a spreadsheet for the data, then a PDF report for the analysis"
  • Set expectations for each stage: "The research should cover at least 10 sources" or "The recommendation should be 2-3 pages"
  • Use Agent Team for tasks requiring deep multi-angled reasoning across stages

Our Users Regularly Submit Complex Prompts

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.

Recurring Work

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.


Frequently Asked Questions

How do I rename a chat?

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.

How do I add an existing chat to a project?

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.

How do I know when a long chat has finished?

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.

Can I recover a deleted chat?

No. Chat deletion is permanent and cannot be undone. Save important artifacts before deleting.

How do I continue a previous chat?

Click any chat in the sidebar, or find it with Search chats. Your full history is preserved.

How can I see what a chat has cost?

Open the header menu and select View Costs.

What's the difference between Save Artifacts and Agent Computer?

  • Agent Computer: view the agent's workspace
  • Save Artifacts: copy files to permanent storage (My Drive, the Organization Drive, or a project)

Can a chat run on a schedule?

No. Scheduling belongs to AI employees: routines wake an employee at the times you or it define. See the AI Employees Guide.


Related Guides