Help & Guides

Chat is the command center where your work with Alkimi comes to life. It is the interface where you interact with your agents, but it is more than just a messaging window; it is a collaborative workspace. Here, you can seamlessly weave together your proprietary knowledge, real-time web data, and uploaded files into a unified conversation.

Designed for productivity, the Chat interface gives you powerful tools to manage your workflow. You can easily switch between different specialized agents, organize your history with favorites and archives, and use advanced features like temporary chats for privacy. Whether you're brainstorming strategy, analyzing a document, or running a complex query, Chat provides the structure and tools you need to get the most out of your AI workforce.

Alkimi AI BETA

MA301: Division Algorithm

New Chat

History Favorites Archived

Today

Proof of Existence

Euclidean Alg Example

Homework 1

Linear Congruence

Midterm Review

University of Alkimi

Proof of Existence

How do I prove the existence part of the division algorithm?

Consider the set S = { a - bk : k is an integer, a - bk >= 0 }. To show existence, you can apply the **Well-Ordering Principle** to this set.

• Show S is non-empty
• Apply Well-Ordering Principle to find least element r
• Prove r < |b|

Theorem 1.1.pdf

Alkimi AI can make mistakes. Check important info.

Ask a question about the Division Algorithm...

Managing Conversations

The chat sidebar is designed to help you keep your conversations organized. It features a tabbed interface to filter your chats and a context menu for quick actions.

Agent Selection

Chat Controls

Chat Tabs

Chat History

User & Org

Alkimi AI BETA

MA301: Division Algorithm

New Chat

History Favorites Archived

Proof of Existence

Just now

Euclidean Alg Example

2 hours ago

Homework 1

Yesterday

Linear Congruence

2 days ago

Midterm Review

3 days ago

Chat University of Alkimi

The Chat Tabs

• History: This is your main inbox for all non-archived chats. Favorited conversations are pinned to the top for easy access, followed by the rest of your chats sorted by recent activity.
• Favorites: This tab provides a focused view of only your favorited chats.
• Archived: To keep your History clean, you can move conversations here. Archived chats are kept for your records but are hidden from the main list.

Chat Actions

Temporary Chats

For quick, one-off conversations that you don't need to save, you can create a temporary chat by clicking the dashed message icon () next to the "New Chat" button. These chats offer enhanced privacy as they are never saved to your history and are permanently deleted when you navigate away from the page. You will be warned before leaving a temporary chat.

Searching Chats

The platform provides powerful search tools to help you find information within your chats. When you open the search bar in the sidebar, you have two options:

• Search Scope: A toggle button () in the search bar allows you to switch between searching only chat titles (for quick navigation) or performing a full-text search across all message content within your conversations. By default, it searches both titles and messages.
• In-Chat Navigation: When you perform a search that includes message content, a search navigator appears at the bottom of the active chat window. This tool shows the number of matches and allows you to jump directly to each instance of the search term within that conversation.

Alkimi AI BETA

MA301: Division Algorithm

Search chats...

History Favorites Archived

3 / 12

Suggested Questions

To help guide the conversation, the agent can provide a list of suggested questions. These AI-generated prompts may appear at the start of a new chat or after an agent's response to help you explore the topic further. You can customize how these suggestions are displayed from your Account Preferences.

Sharing Conversations

You can share conversations with others via a secure, read-only link. This is useful for collaboration, getting feedback, or simply sharing an interesting interaction with an agent. When you share a conversation, you are creating a static snapshot of the chat up to a certain point. The shared link will not update with new messages.

How to Share

There are two ways to share a conversation:

• Share Entire Chat: Click the share icon () in the chat header.
• Share a Snapshot: To share a conversation only up to a specific point, hover over any message, open its context menu, and select "Share from here". This creates a link that includes that message and all previous messages.

Both methods will open the sharing dialog, which provides several options to control how your chat is shared.

Sharing Options

• Visibility: You can control who can view the shared link.
  • External: Anyone with the link can view the conversation.
  • Organization: Only logged-in members of your organization can view the conversation.
• PII Safety: The system automatically checks for personally identifiable information (PII) and warns you if potentially sensitive data (like names or emails) is detected in the chat. Additionally, to protect your privacy, your name as the sender is automatically hidden on messages when sharing with "External" visibility, though it remains visible to colleagues on "Organization" shares.
• Custom Label: You can give your shared link an optional, memorable label to make it easier to identify later.

Managing Your Shared Links

You can manage all of your shared links from the My Shares page in your account settings. This page provides a centralized view of every share link you've created.

• View & Copy: See a list of your shares, including their custom names and the chats they belong to. You can easily copy the link to your clipboard.
• Delete: You can revoke access to a shared chat at any time by deleting its link. Once deleted, the link will no longer be accessible. You can also delete all of your shares at once.

What the Recipient Sees

When someone opens your shared link, they will see a clean, read-only version of the conversation. The page includes the chat title, the agent's name, and the date it was shared. If the share is an "Organization" type link and the viewer is logged in, your name will also be displayed as the person who shared it. A notice will be shown if PII was removed from the content.

Uploading Files & Images

If an agent has file uploads enabled, you can attach files and images to your messages. This allows the agent to analyze the content of your documents, answer questions about them, or use the information within them to perform tasks.

How to Upload

To upload a file, click the paperclip icon () in the chat input bar. This will open a file selector. You can upload multiple files at once. Supported file types include:

• Images: PNG, JPG, GIF, WEBP
• Documents: PDF
• Code Files: LaTeX files (.tex, .latex, .ltx, .sty, .cls) and other text-based formats.
• Text Files: TXT, MD

Once uploaded, files will appear as small badges above the text input area. You can remove a file before sending by clicking the 'x' on its badge.

Viewing and Managing Files

Understanding Upload Capacity

Each agent with file uploads enabled has a maximum upload capacity, which is determined by its Context Budget. This capacity is measured in "pages" (for documents and images). As you attach files, a progress ring around the attachment button will show you how much of the available capacity you are using. This ensures that the total size of uploaded files does not exceed what the agent can process in a single message.

Using Tools

When you're chatting with an agent that has tools enabled, you can invoke them to bring external information into the conversation.

Tips for Effective Web Searching

The web search tool is powerful, but you can get even better results by providing clear instructions. The agent uses an AI model to generate search queries based on your message, so the more specific you are, the better the outcome.

1. Be Explicit with Multiple Queries: If you need to compare or gather information on multiple topics, guide the agent to perform separate searches. This yields more focused results than a single, broad query.
   Example: Instead of asking Compare Google's Gemini Pro with Anthropic's Claude Sonnet, a more effective prompt would be:
   Please perform web searches for the technical specifications of Google's Gemini Pro and Anthropic's Claude Sonnet, then summarize the key differences.
2. Guide the Source Priority: You can tell the agent what kind of sources to prioritize.
   • First-Party: To get information directly from the official source, include a phrase like prioritize official sources or prioritize first party sources in your request. Different models may respond better to one phrase over the other, so using either is a good way to guide the agent. The agent will attempt to select URLs from the main subject's website (e.g., openai.com for a query about ChatGPT).
     Example: What are the latest features in Next.js? Prioritize first-party sources.
   • Third-Party: Conversely, if you're looking for reviews or independent analysis, you can specify that.
     Example: Search for reviews of the new M4 MacBook Pro, prioritizing third-party tech blogs.
3. Specify Content and Site Types: You can be even more granular by requesting information from certain types of websites or content.
   Example: Find information on sustainable farming practices from .edu or .gov websites.
4. Exclude Unwanted Sites: If you find that results are consistently coming from a source you don't want, you can ask the agent to avoid it.
   Example: What are the best vegetarian recipes? Avoid results from pinterest.com.

Understanding Web Search Limits

To ensure performance and relevance, the web search tool operates within a set of technical limits. It's helpful to be aware of these as you use the feature.

• Search Queries per Message: The agent will generate a maximum of 5 distinct search queries based on a single message from you.
• Websites Visited per Message: From the search results, the agent will select and "visit" (read the content of) up to 3 websites per search query, with an overall maximum of 10 websites in total for a single message.
• Total Content Limit: The agent has a reading limit. It will stop processing content from web pages after it has collected a significant amount of text. This means that even if 10 URLs are selected, the agent may not read all of them if the first few pages contain a large amount of text. This mechanism prevents the agent from being overloaded with information that exceeds its context capacity.

Monitoring the Process: Understanding Statuses

When an agent uses a tool like Web Search, you'll see a series of status updates in the chat window. These are designed to give you real-time insight into the agent's actions.

• Searching: The agent is actively performing a web search for the given query.
• Searched: The agent has completed the web search for the query.
• Browsing: The agent is currently reading and processing the content of the linked URL.
• Browsed: The agent has finished reading the content of the linked URL.
• Skipped: The agent selected this URL to read but did not process it because the Total Content Limit was reached first.
• Failed: The agent was unable to read the content of the URL. This can happen for various reasons, such as the website being down, access being forbidden, or the page containing no readable text.

Each status includes a clickable link that allows you to view the relevant search results or webpage in a new tab, giving you the same context the agent is working with.

How the Agent Selects URLs to Read

After performing a search, the agent uses an AI model to analyze all the resulting links and selects only the most promising ones to read. You will only see status updates for the URLs the agent decides to browse. Links that are deemed irrelevant by the model are discarded and will not appear in the agent's action steps.