Section 1: What is a V7 Go Agent?

Overview

V7 Go is an AI Agent powered work automation platform designed to turn complex documents into streamlined workflows. It leverages advanced large language models (LLMs) and multimodal AI to read and understand documents, images, and other data, emulating human reasoning steps to complete tasks with high accuracy.

Agents

A Go Agent is a logic-driven, modular automation system that uses LLMs, Python, Web Search and other tools to extract structured and unstructured data from your files, and turn them into actionable insights.

Agents are built to reduce repetitive manual work, enhance data accuracy, and streamline operational workflows across complex business processes.

Agents allow users to build end-to-end workflows that mirror your most complex chain of thought and reasoning processes. Through a visual interface, you can chain together multiple AI tasks and decision logic (if/then branches), and even insert human review steps for critical points.

For example, an automated insurance claims workflow might:

Intake a first notice of loss (FNOL) email with attachments,
Extract key data (policy number, loss details, etc.),
Run a fraud-check model,
If fraud risk is high, route to a human adjuster for review, otherwise
Auto-approve a simple claim and draft a settlement letter.

Think of an Agent as your AI-powered teammate that can read, understand, and process unstructured content — at scale.

Why Use an Agent?

Agents are ideal for:

Completing logical and repeatable processes across your entire organization.
Reducing manual data entry by extracting key fields from contracts, leases, reports, and more.
Summarizing documents to speed up internal analysis and decision-making.
Standardizing workflows across different document types or departments.
Improving auditability and QA with AI citations and logic-driven data handling.

Common Agent Use Cases

Each agent is built around the desired output. Here are the three most common forms:

1. Data Extraction & Enrichment for External Systems

Use case: Populate a CRM, CMS, or internal dashboard

Example: Extract income statement data → export to CRM

2. Report Generation

Use case: Generate a summary, report, or memo.

Example: Extract the key information from a home construction inspection report, and provide recommendations & next steps in a memo.

3. Workflow Automation & Augmentation

Use case: Equip analysts with quick insights and actionable next steps

Example: Extract critical terms from a quarterly investment report → Make a recommendation → Route a summary report to human analyst for review.

Key Components of an Agent

An agent is composed of:

Properties: The structured data fields to extract (text, number, date, etc.)
Tools: The logic engine powering each step (AI Model, Python, Web Search, etc.)
Inputs: Files or user prompts that start the workflow
Prompts: Custom instructions guiding the AI’s behavior
Workflows: Automations, routing logic, and sub-processes triggered by select conditions

Real-World Example

Scenario: A business wants to extract and compare private placement memoranda (PPMs**) for different real estate investment opportunities.

Agent Solution:

Input: Large Private Placement Memoranda (60+ Pages)
Agent uses:
- Text & Number properties to extract data points
- Single Select to classify outcomes
- Collections to group similar data
- Python to calculate total costs and validate compliance
- Web Search to compare against public sources
- Output: Structured exec summary to inform decision-making