📌 This article is for users of elvex 2.0. Find out which version you're using.
The Context Strip
When you start a new conversation, you'll notice a strip of items in the chat box — this is the context strip. It shows what background knowledge elvex is starting your conversation with, before you even type a word.
The context strip can include:
Your company context — shared organizational knowledge set by your admins: what your company does, its products, terminology, and norms. It flows into every conversation for every user automatically, so you never need to set it yourself.
Your personal context — your role, priorities, and working style (set once in your profile; flows into every conversation automatically)
A Space — if you're opening a conversation within a team or project Space, its pinned resources and context document are automatically included
An agent — you can start a conversation directly with a specific agent rather than a general chat
Think of the context strip as your conversation's foundation. It's what elvex knows before you ask anything.
Once you send your first message, the context strip moves up to the thread header so you can always see what context your conversation is operating in.
When should you disable part of the context strip?
Most of the time, you won't need to change anything — the context strip is doing helpful work in the background. But there are cases where you might want to turn something off:
Disable your personal context when you're doing something where your role and preferences aren't relevant — for example, drafting a general-purpose template for your whole team, or exploring a topic completely unrelated to your job function.
Rule of thumb: Leave the context strip as-is unless you have a specific reason to strip something out. When in doubt, more context is better.
Attachments
Beyond what flows in automatically through the context strip, you can attach resources directly to your messages in two ways:
The + button in the message input box
Drag and drop from the open side panel — you can drag threads, spaces, agents, and resources directly into your message
Attachments tell elvex: "this is specifically relevant to what I'm asking right now."
You can attach:
Attachment type | What it does |
Files | Upload a document, spreadsheet, image, or other file for elvex to read |
Datasources | Ground elvex's response in a specific internal knowledge repository |
Agents | Hand off to a specialized assistant mid-conversation when a task calls for deeper expertise |
Spaces | Bring in all the pinned resources and context from a collaborative workspace |
Threads | Reference a past conversation to build on prior work |
When should you add attachments?
Add attachments when you want to point elvex at something specific: a file you want analyzed, a datasource you want answers from, or a past conversation you want to build on. You don't need to attach things that are already flowing in through the context strip.
Good reasons to attach something:
You have a document, spreadsheet, or file that's central to your question
You want elvex to answer from a specific datasource rather than its general knowledge
You want to hand off a specific task to a specialized agent mid-conversation
You want to reference a past conversation thread as context for a new question
You probably don't need to attach something if:
It's already available through your personal context or the Space you're in
You're asking a general question that doesn't require specific internal data
Do you need to re-add attachments throughout a conversation?
Not necessarily. Once you attach something to a message, it remains part of your conversation context for the rest of that thread. You don't need to re-attach the same file or datasource in every follow-up message.
If you start a new conversation, you will need to attach resources again — context does not carry over between separate threads. If you find yourself repeatedly attaching the same resources at the start of new conversations, that's a signal to either pin those resources to your My Space or create an agent with those resources built in.
Context Strip vs. Attachments: At a Glance
| Context Strip | Attachments |
What it is | The background context elvex starts every conversation with | Resources you explicitly add to a specific message |
When it applies | Automatically, from the moment you start a conversation | Only when you add them |
Persists across messages? | Yes — set once and flows through the whole thread | Yes — once attached, stays active for the rest of that thread |
Persists across conversations? | Yes — personal context and Space context always flow in | No — must be re-attached in new conversations |
How to control it | Toggle items on/off before your first message | Use the + button in the message input box |
When Should You Chat Directly with an Agent?
Agents are purpose-built tools configured for a specific task. Instead of asking the general elvex assistant to do something it might do okay, you can go directly to an agent built specifically for that job.
Chat directly with an agent when:
You're starting a conversation and there's an agent for your task (e.g., a Competitive Battlecard Agent, an HR Policy Agent, a Data Analyst Agent)
You want responses to adhere to a specific set of rules or instructions (e.g., brand voice, legal review criteria)
How to do it: Click the three dot menu on the agent card and select Go to Agent or click on the Direct Chat button on the attachment.
When Should You Chat Directly with a Space?
A Space is a shared collaborative workspace with pinned resources and shared context. When you open a conversation within a Space, all of that context flows in automatically.
Chat directly within a Space when:
You're doing work that belongs to a specific team or project and the Space already has the right agents, datasources, and context loaded
You want your conversation to benefit from everything the Space knows, without manually attaching resources
You want your conversation to impact the Space’s context (this setting has to be enabled by the Space’s owner)
How to do it: Navigate to the Space and open a new conversation from within it. You'll see the Space's context appear in the context strip automatically.
Quick Reference
Starting a new conversation? → Check your context strip. Make sure you're in the right starting context (personal, a Space, or an agent).
Have a file or document that's central to your question? → Attach it using the + button, or drag it in from the side panel.
Looking for answers from a specific internal knowledge base? → Attach the relevant datasource, or chat from within the Space where it lives.
Need specialized help (competitive research, data analysis, legal review, etc.)? → Chat directly with the agent built for that task.
Doing team or project work? → Open the conversation from within the relevant Space.
Re-adding the same attachments every time you start a new thread? → Pin those resources to your My Space so they're always available automatically — or create an agent with those resources built in.