> ## Documentation Index
> Fetch the complete documentation index at: https://help.casaconect.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Conversations and the composer
> Start and organize conversations, attach files, reference documents, share what you are looking at, and use modes, skills and memory.
A **conversation** is one thread of work with the agent. It keeps its own history, runs in its own [cloud session](/agent/cloud-execution), and can belong to a project.
## The composer
The composer is the box you type in: *"Ask anything, or describe a task…"*. Around it are the controls that shape a message.
| Control | What it does |
| :--------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------- |
| **Project** | Sets the project the conversation works in, which decides the vault it drafts into and who can see the conversation |
| **Model** | **Auto**, or a specific model. See [Models](/models/overview). |
| **Attach** | Add up to **5 files** to a message: images (PNG, JPEG, WebP, GIF), PDF, plain text, Markdown, CSV, Word (`.docx`) and Excel (`.xlsx`) |
| **Reference** | Point to up to **10 documents** already in Casa Conect, so the agent reads the current version instead of an upload |
| **Include what you're looking at** | Shares your current context: the project, matter, Shared Space, document, email, file or browser session on screen, along with your open tabs |
| **Workflows** | Attach [Populate](/workflows/populate) or [Anonymize](/workflows/anonymize) to the message |
| **Dictate** | Speak your message and have it transcribed |
| **`/`** | Open the slash menu for **Modes** and **Skills** |
Prefer **Reference** over **Attach** for anything already in a vault. A reference always points to the latest version, costs nothing to upload, and lets the agent edit the real document rather than a copy.
### Context from your screen
With **Include what you're looking at** on, *"summarize this"* and *"draft a reply to this"* work as you would expect. Up to 12 open tabs are included. If you have more, the composer tells you how many were left out so you can close some.
## Modes
Type `/` and choose a mode.
The default. The agent reads, writes and acts to complete the task, within your [permission level](/agent/permission-levels).
*"Plan and design before doing…"* The agent investigates with read-only tools and writes a plan. Nothing is changed until you approve the plan. Then the agent carries it out.
Use Plan for anything large, unfamiliar or hard to undo: reorganizing a vault, setting up a Shared Space, a multi-document review.
## Skills in a message
Type `/` followed by a skill's name, for example `/draft-email` or `/property-due-diligence`, to tell the agent to follow that playbook for this message. The agent also picks skills by itself when a task matches one. See [Skills](/agent/skills).
## Memory
The agent remembers useful context about you between conversations, so that you do not start from nothing each time.
| What | How it works |
| :-------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **A working profile** | A short note the agent maintains about you: your name and role, your organization, working language, active project or matter, key parties, standing preferences for tone and format, and open follow-ups |
| **Recall** | When relevant, the agent retrieves a handful of passages from your earlier conversations |
| **Recent history** | Within a conversation, the most recent messages are always in view |
Memory belongs to **you, within one organization**. It is not shared with colleagues, and if you belong to more than one organization, what the agent remembers in one never appears in another.
In conversations that other people can read, namely shared conversations and matter threads, memory is confined to that conversation. The agent neither draws on your private conversations nor updates your personal profile there, so nothing private surfaces in front of colleagues.
Deleting a conversation deletes its messages and everything remembered from it. For preferences you want applied reliably, use [guidance](/agent/guidance). Memory is a convenience; guidance is an instruction.
## Organize conversations
From a conversation's menu you can **rename** it, **pin** it to the top of the sidebar, **move it to a project**, change its **visibility**, **archive** it or **delete** it. Titles are written for you from your first message, and you can change them.
Conversations can be searched from the sidebar.
### Who can see a conversation
| Conversation | Visible to |
| :------------------------------- | :-------------------------------------------------------- |
| Private conversation | Only you |
| Shared conversation in a project | People with access to the project |
| Matter thread | People who can see the matter |
| Inbox conversation | Your organization, unless it is tied to a private project |
## Helpers
For research-heavy tasks the agent can start **helpers**: up to three at a time, each with read-only tools, working in parallel and reporting back. Helpers cannot edit documents, ask you questions or start helpers of their own. You can open a helper's transcript from the conversation to see what it read.
## Good habits
* **One subject per conversation.** Long, wandering conversations cost more and drift. Start a new one when the subject changes.
* **Name the documents.** Reference them rather than describing them.
* **Say what finished looks like**: language, length, audience, format.
* **Stop and redirect.** If the agent is heading the wrong way, stop it and say so. You do not need to wait for the turn to finish.