Reference Document Analysis - User Guide

This guide explains how to upload reference material (PDF) to a project, turn it into a form the AI can read, and then ask the chatbot about its content. It covers the upload options (processing mode and model tier), the processing steps and document statuses, how to query the chatbot, and the cost.

Last Updated: 2026-02-21

1. Introduction

TFLOW's Reference Document Analysis feature has AI read your uploaded PDF documents and turn them into a searchable form. Documents prepared this way become the basis on which the AI chatbot answers questions accurately.

When you upload a document, you can select a Processing Mode and a Model Tier.

Per-Project Document Isolation

Documents uploaded to a project are searched only within that project. A document uploaded in Project A will not appear in Project B's search results, so each project maintains its own independent knowledge base.

2. Uploading Documents

If the upload was blocked — "Duplicate documents detected" means the same document is already uploaded, so check the list. If you see "Reference not found" or a notice that the original file is missing, the file did not upload properly — just upload it again.

2.1 Accessing the Upload Screen

1. On the project detail page, select the Reference Documents tab
2. Click the Upload button to open the upload modal
3. Drag and drop a PDF file, or click to select one

2.2 Selecting Processing Options

Two options are displayed below the upload area.

Processing Mode

When you select Batch, document analysis runs in the background and you receive a notification when it completes. Most jobs finish within 10 minutes.

Model Tier

The 5x · 3x · 1x next to each tier is how many times more tokens it uses.

2.3 Running the Upload

After selecting your options, click the Upload button to start document analysis. Once the document status changes from Analyzing to Analyzed, you can query that document in the AI chatbot. Batch runs in the background, so you can close the screen and you will be notified when it completes.

3. Processing Flow

If you see "Document is already being analyzed" — analysis for that document is already running. Wait for the completion notification (usually within 10 minutes). There is no need to upload it again.

Realtime

1. Analysis starts immediately upon upload
2. The document status changes from Analyzing to Analyzed
3. Once complete, you can immediately query the document content in the AI chatbot

Batch

1. After upload, the document joins the processing queue
2. In the background, the document is read and turned into a searchable form (usually within 10 minutes)
3. Click the Batch badge in the document list to see how far it has got, such as "Converting document (1/5)"
4. You receive a notification when it completes

Document Status

4. Querying Documents with the AI Chatbot

Once a document reaches the Analyzed status, you can ask questions about its content in the CYGNUS AI chatbot.

4.1 Using the Chatbot

1. Enter your question in the chat area at the bottom of the Reference Documents tab
2. The AI searches the project's analyzed documents and answers
3. The answer includes reference information for the source documents it found

4.2 Search Modes

4.3 Document Filtering

When you want to query only specific documents, you can use the document filter to narrow the search scope. If no filter is set, the search covers all analyzed documents in the current project.

5. Cost Guide

Document analysis consumes AI model usage tokens. The cost varies by processing mode and model tier.

Cost Comparison (based on a 100-page document)

You can check your remaining tokens in the token gauge on the top navigation bar.

6. FAQ

Processing time and model choice

Q: I uploaded in Batch. When will it finish?

Most jobs finish within 10 minutes. The time can vary depending on document size and how much is being processed, and may take up to 24 hours. You receive a notification when it completes.

Q: Can I do other work while analysis is running?

Yes. Batch runs entirely in the background, so you are free to do other work. With Realtime, analysis also continues even if you navigate to another page.

Q: Which model tier should I choose?

For documents where accuracy matters, such as technical specifications or contracts, we recommend Standard or higher. For simple reference materials, Basic is sufficient.

Q: My analysis failed. What should I do?

Delete the document from the document list and upload it again. If it still fails, let us know through Customer feedback. Note that tokens used are still deducted even when analysis fails.

Uploads, tokens, and project isolation

Q: Can I upload multiple documents at once?

Yes. You can drag and drop or select multiple files at the same time. Each document is processed independently.

Q: What happens if I run out of tokens?

If your balance is 0 or below, analysis will not start. Top up from the lightning (⚡) balance widget at the top (token charging), or ask your company Master if you cannot pay yourself.

Q: Can I see documents uploaded in other projects?

No. Each project's documents are completely isolated. A document uploaded in Project A is searchable only in Project A's chatbot and cannot be accessed from Project B.

Q: I want to use the same file across multiple projects.

You must upload it separately in each project. Even for an identical file, each project analyzes it on its own.