First, choose or create a Deal. Then, navigate to Chats in the Deal menu at the top of your screen; hit the + Create a new Chat button, and name your Chat.

In the Create New Chat window, your chat will automatically be set to private, you can change it to Deal Team here or in the Edit Chat menu later on.

If you wish to limit the documents for Q&A, select the Restrict Chat Documents option and select which document(s) you'd like to converse with.

Optional: Include Vault Knowledge - You can also include shared knowledge from your firm's Vault by selecting the appropriate option during chat creation.

Select Confirm to create the Chat.

You should use Chat when:

A Restricted Chat limits the documents that will be used for Q&A

Not directly once the Chat has been initiated

If it is a Restricted Chat and you have selected Categories or Tags, any new documents with those settings will be added from that point forward

Yes. If you don't Restrict a Chat, your Chat will contain all the documents you uploaded to that Deal's file page.

Note: Answers are often less accurate in a broad conversation with all documents vs. Restricted Chats. We recommend restricting your Chat whenever possible.

Yes. Click the three dots next to the Chat name, and select Make Visible to Deal Team. This will adjust your privacy settings to allow others to see your chat.

Chats with the Deal Team visibility will be visible to everyone within your firm with access to the Deal

Yes, you can choose between All Chats and My Chats above the Chats listed on the left side of your screen

First, select a Deal and a Chat. Then, type your question in the message box at the bottom of the screen and press Send, or hit Shift + Enter to send it.

You can also select from a list of prewritten prompts by using the Prompts button on the bottom right corner of your screen when in Chat.

First, select the Gear icon to the left of the prompts button at the bottom of the screen. The adjustable models menu will appear above the message box. Then, select the Model option and select your desired model from the drop-down list.

Select a Deal and navigate to Chats. Then, navigate to the chat you would like to export. In the top right click the Export button.

Select the Export format (Word (table), Word (clean), Word (clean, answers only), Excel.)

Select a Deal from the main menu.

Select Exports from the Deal Menu at the top of your screen.

A check box is next to each Chat name so you can check all the Chats you want to export.

Select the format for the export and then select Export below the Deal menu at the top of the screen.

The document will appear in your browser's download list once the download is complete.

After your question is answered, you can choose to regenerate the response using the Regenerate icon on the bottom right corner of the response.

Responses can only be regenerated for the most recent question answered in a Chat.

The bad response icon (thumbs down) allows the user to give ToltIQ feedback on the quality of a response.

If a response is downvoted, you can select a specific reason from the provided drop-down list.

Downvoted responses will impact the ongoing context of the conversion, though they will remain visible in the Q&A session.

The Bubble icon allows you to ask a question directly of the LLM Only.

This Q&A is "stateless," meaning it will not be part of the conversation or considered for context purposes. It's a way to query the LLM's training data related to your diligence work as a side conversation that doesn't affect your main chat.

Suggested Follow Up Questions are auto-generated by ToltIQ based on the response to the last question answered. Three follow-up questions are generated each time. If you are interested in asking one of the questions, select it, and it will automatically be populated in the question box.

Follow-up questions remain as part of the answer, so you can return to them later for further diligence activities.

Chat History includes or excludes the prior conversation within a Chat as part of responding to the next question asked.

Conversations, by their nature, create bias in responses. This bias can be viewed as good, bad, or indifferent, depending on the nature of the next question. What the user wants included is always at their discretion. It can be re-enabled at any time after it is disabled.

Generally, if your next question significantly changes topics or you want to ask the same question again but with slightly different wording or retrieval options, we recommend un-selecting Consider Chat History so the response is free of conversational bias.

Consider Chat History is on by default. To turn it off, select the Gear icon to the left of the message box at the bottom of the screen. The adjustable settings menu will appear above the message box. Then, you will have the option to unselect Consider Chat History.

The 30 most recent messages (typically 15 human questions and 15 AI responses) will be stored for purposes of chat history.

With chats involving extremely large messages and documents, it is possible (although unlikely) that less of the conversation will be kept if the conversation exceeds the LLM's context window.

When in a Chat, if you de-select Consider Chat History, the LLM will no longer consider prior context/chats.

ToltIQ allows you to enable or disable the use of your documents to respond to a question

If you un-select Consider Sources, then ToltIQ will remain aware of the conversation up to that point, but the response to your question will be sourced from the LLM only.

You can switch it on and off as needed, but be mindful that it will impact the conversation with potential responses that aren't footnoted.

Consider Sources is on by default. To turn it off, select the Gear icon to the left of the message box at the bottom of the screen. The adjustable settings menu will appear above the message box. Then, you will have the option to un-select Consider sources.

Yes. De-Select Consider Sources, and then your question will only use the LLM for a response. This does not access the internet and only uses the training data of the specific model.

Example: LLMs are trained on large but selective datasets that include data up to a certain cutoff date. However, these datasets only represent part of the internet, even up to that cutoff. Training data is curated from proprietary and publicly available sources, aiming for a diverse set that balances quality, relevance, and compliance with privacy and ethical standards.

The ToltIQ platform embeds relevant footnotes in each Chat response, linking to the source documents the model used to answer your question.

Simply hover over any Embedded Footnote (indicated by a letter) in your response to see which document the information was sourced from and the page number.

When you click any Embedded Footnote, the source document opens directly to the page containing the response information in a window in front of your chat. From this window you can open the document to view in a webpage, download, print, or view the document's properties.

Depending on the complexity of the document and how we retrieve information, footnotes will get embedded during the streaming response.

However, embedded footnote notes are not always guaranteed (we are continually improving the consistency with which they are used). The source documents will always be listed after the response.

You can access Prompt Advisor when within a Chat or Data Chat.

Prompt Advisor will automatically refine your prompts when turned on.

To turn on Prompt Advisor, select the Speech bubble icon that says "Advisor" at the bottom of the chat window.

When selected, the icon should turn green. This indicates that Prompt Advisor is turned on and ready to be used.

If you have a specific prompt you don't want modified, it is recommended to turn off Prompt Advisor.

In chats, there is an export option to download all tables in chats. On the top right of the page, click the "Export" button and select the file form for the tables in chats you'd like to download. You have the option between:

When you click on a citation, the system now highlights the exact text being referenced. This enhancement helps you quickly identify the specific information being cited while still navigating to the source page as before.

Yes, the highlighting feature now supports both images and charts in addition to text, making it easier to identify all types of cited content.

Yes. You have two editing options for chat responses:

All knowledge sources have been consolidated into a single Source menu, conveniently located next to the Chat send button. This menu provides easy access to all your data options in one place.

The Source menu includes:

Simply click the Source menu next to the Chat send button and select Web Search to enable Web Mode, or choose from our beta financial integrations like FRED or EDGAR.

Yes, within the Source menu you can toggle "Consider chat history" on or off. When enabled, the system will use context from your current conversation to provide more relevant responses.

Auto-generated charts are visual representations that automatically appear alongside tables in Chats when your table contains numerical data. If the table includes quantitative information, ToltIQ will automatically create a corresponding chart to help visualize the data.

Auto-generated charts are only available in Chats. They do not appear in Data Chats.

Charts may take a few seconds to populate because they require an additional AI processing call to generate the visualization. You'll see your table first, and then the chart will appear shortly after.

Charts will only be generated for tables that contain quantitative (numerical) data. If your table is entirely qualitative (text-based), a chart will not be generated.

@commands are special functions you can run directly within any chat. To view all available commands, simply type "@" in the chat modal and a menu will appear showing the different commands you can execute.
​

@commands can be used within any chat modal on the platform. The command menu is accessible in every chat session for quick access to specialized functions.
​

Type the "@" symbol in your chat window and the platform will display a list of all executable commands along with their functions.

Data Chats Within Agents

Data Chat within Agents is a feature that combines the document analysis capabilities of Data Chats with the intelligence of ToltIQ's AI Agents, enabling you to have conversational, AI-driven discussions with documents that are already loaded in your workspace — across a wide range of file types.
In a standard Data Chat, you manually select the files you want to analyze before starting a conversation. With Data Chat within Agents, this step is fully automated: the Agent uses a built-in documents tool to intelligently identify and pull in the most relevant files from your workspace, then surfaces those documents into a Files API-powered conversation. This means you can ask questions and receive insights without needing to pre-select or manage your document inputs.
​

​Key benefits include:
​

How to enable: Select data chats in the source selector