AI Chat

​

Overview

AI Chat is your intelligent assistant that can answer questions about your contracts and data using natural language. Ask questions about deal terms, compare contracts, and get summaries — all with citations to source documents.

​

Data Snapshot

AI Chat works from a snapshot of your project data, not a live connection. This means the AI has access to all contracts, catalog, CRM, and statement data as it existed at the time of the snapshot. Check the snapshot timestamp in the chat sidebar — any data added or changed after that point won’t be reflected in the AI’s answers until a new snapshot is created.

​

Context-Aware Queries

AI Chat always has access to all data in your current project — contracts, catalog, CRM, and statements. But you can make it significantly more effective by giving it specific context: when you ask a general question like “What’s the royalty rate?”, the AI has to search across all your contracts, whereas opening chat from a specific contract’s detail page tells it immediately which contract you mean, giving faster, more precise answers. Opening AI Chat directly from any detail page automatically scopes the conversation:

​

Research Agents

When you ask a complex question, the AI doesn’t just look up a single answer — it spins up one or more research agents that autonomously investigate your data. Each agent specialises in a different type of research and can work in parallel.

​

How It Works

You ask a question, the main AI breaks it into research tasks, and one or more specialised agents are dispatched to investigate — in parallel when tasks are independent. Each agent explores your data autonomously, then the main AI synthesises all findings into a final answer with citations. For complex tasks, the AI also tracks a running plan of the steps it intends to take so you can follow progress as it works.

​

Specialised Sub-Agents

​

File Search Results

When the Research Agent searches your contracts, it returns the matching passages pulled directly from the contract text, rather than a single summarised answer. Each result shows:

• The source contract — its name, with a link to open the contract detail page
• Where it came from — the section, defined term, and/or page number the passage was found on
• A confidence level — how strongly the passage matches your query (e.g. high, medium, or low)
• The passage text — the relevant excerpt itself

This lets you trace exactly which parts of which contracts informed the AI’s answer, and jump straight to the source document. When an agent finishes its research, it produces a summary with:

• Summary — a brief written overview of what the agent found
• Findings — a list of key facts or data points the agent discovered (e.g., royalty rates, entity names, totals)
• Referenced files — if the agent compiled datasets into files, each file appears with its filename, a short description of its contents, and a row count so you can see what was captured

​

Organizational Knowledge

AI Chat can also draw on your organization’s Brain — the shared, confirmed knowledge your organization maintains about its people, processes, decisions, and policies. When it’s relevant to your question, the AI retrieves this organizational context alongside your project data, so its answers reflect what your organization actually knows, not just what’s in the current project’s documents. As with everything else, only confirmed knowledge and evidence you have access to is used — the AI never surfaces knowledge tied to projects you can’t see.

​

Web Search

The AI can also search the web when a question requires external context (e.g., industry rates, general music business information), citing the source links it used. For long or complex conversations, the AI automatically compacts its context to stay within limits — this happens on its own and doesn’t require any action from you.

​

Cross-Domain Questions

Because agents have access to both contract data and revenue/statement data, you can ask questions that span both domains:

​

Answer Output Types

The AI presents information in the format that fits the question:

• Tables — structured data (e.g., a list of contracts with their royalty rates) as a formatted table in the chat
• Charts — a bar chart when the question has a clear visual answer, such as revenue by artist or royalty rates by deal type, including multi-series comparisons
• Files — for large result sets (50+ items), a downloadable file instead of listing everything inline

​

File Generation

The AI chooses the format based on your request — ask for “a CSV” for a simple export, or “an Excel file”/“a spreadsheet with multiple sheets” for a formatted, multi-sheet XLSX. For complex reports it may generate XLSX automatically. A file is generated automatically when a query returns a large dataset, you ask for a report or export, multiple data sources need combining into one output, or you request specific formatting like multiple sheets or styled headers. Generated files are available both inline in the chat response and from the Files section of the chat sidebar, which lists every file from the conversation — AI-generated or uploaded by you.

​

Memory

AI Chat can remember things across conversations. Memories are stored per project and per user — the AI reads them at the start of every conversation, so it can tailor its responses based on what it has learned about you and your work. The AI saves memories automatically during a conversation when it learns something worth retaining, and you can also add, edit, or delete memories yourself at any time from the Memory section of the chat sidebar.

​

Commands

Type / in the chat input to access commands. Two commands are available:

​

Select

Type /select to reference specific items from your project in the conversation. This opens a search panel where you can find and attach:

• Contracts
• Recordings
• Compositions
• Entities
• Artists
• Writers
• Relations
• Statements

You can add multiple items to a single message, which is useful for comparison questions like “Compare the royalty terms between these two contracts.”

​

Upload

Type /upload to attach files to your conversation, either by searching files you’ve previously uploaded to chat or uploading a new one. This is how you provide additional context from external documents or data files.

​

Supported File Formats

Uploaded files are not processed through the contract pipeline — they’re provided as-is to the AI for analysis. This is useful for:

• Quick analysis of external documents or draft agreements
• Comparing spreadsheet data against your contract terms
• Analyzing images or scanned documents
• Working with supplementary data files in JSON format

​

Stopping a Chat

You can stop the AI mid-response at any time. It finishes its current step cleanly and delivers a final message rather than cutting off mid-sentence or leaving agents in a broken state; any research agents still running stop at their next natural step boundary. You can then continue the conversation with a new message.

​

Multiple Chats

You can run multiple chat sessions simultaneously, each with its own conversation history, context, and research agents running concurrently — useful for researching different topics in parallel, keeping a reference conversation open while starting a new investigation, or running a long-running analysis in one chat while asking quick questions in another.

​

Best Practices

• Run parallel chats for complex research — start multiple sessions for independent research threads, e.g. a long catalog export in one chat while asking quick questions in another
• Be specific — more specific questions yield better answers; instead of “What are my deals?”, ask “What recording deals have advances over $50,000?”
• Use memory for recurring preferences — add memories for things you always want the AI to know, such as preferred output formats, deal types you focus on, or terminology conventions

​

What You Can Ask

Ask questions in natural language about your project data.

​

Contract Analysis

​

Dates & Deadlines

​

Financial & Revenue

​

Catalog & Assets

​

Comparisons

​

Reports & Exports

​

Cross-Domain Analysis

​

Limitations

​

Privacy & Security

• AI Chat only accesses data within your current project
• Conversations are private to your account
• No data is shared between projects or organizations
• Chat history can be deleted at any time
• Agents are entirely sandboxed, meaning they physically can not access data they are not allowed to see.

​

Related Documentation