New updates and improvements
V7 Go

The next generation of AI reasoning models from OpenAI is now live in V7 Go. We've integrated the entire GPT-5 family - GPT-5, GPT-5 Mini, and GPT-5 Nano - giving you enhanced intelligence and flexibility for your AI agents and workflows.

GPT-5's advanced reasoning and significant reduction in hallucinations means your expert agents can now tackle more complex documents with greater accuracy. When paired with our AI Citations feature, you get a higher level of trust and verifiability.

For our users, this translates to:

• More reliable outputs for structured data like JSON and Collections

• Deeper analysis in Cases, as your AI can now handle difficult problems with improved reasoning

To get started, simply select a GPT-5 model of your choice from the tool list in your AI property settings. For now, GPT-5 models coexists with legacy models, allowing you to continue using and updating existing workflows and projects.

Accessing and managing knowledge in V7 Go is now smarter and more seamless. With the new Hubs feature, you can create a dataroom by uploading a set of files. This allows you to transform scattered documents into a single, searchable knowledge base.

Upload your SOPs, internal policies, or project files to a Hub. Concierge will automatically analyze and index every document. You can then select which knowledge hub to use, ask questions (like “How do we process bugs?” or "Can you show all CapEx approvals from Q4?") and get a consolidated answer—even if the information is spread across multiple files. No more digging through folders or opening documents one by one.

Knowledge Hubs are fully integrated with Cases, letting you search and retrieve information from across your entire Hub using natural language. Whether you’re onboarding a new team member, preparing for a financial audit, reviewing contracts, or just need a quick answer, Hubs bring all your knowledge together in one place.

Create a Hub, upload your files, and start asking questions. Concierge will do the rest and deliver fast, accurate answers from across your organization’s knowledge. Hubs meet you where you work, making it easier than ever to find what you need, when you need it.

Managing your cases in V7 Go just got easier. The new Case Status Indicators provide clear, real-time feedback on your case progress, so you always know when your attention is needed.

A purple pulsing dot signals that a case is processing—typical for actions like knowledge hub searches or multi-entity runs that may take a little longer. A yellow dot highlights unread updates specific to you, automatically clearing once you open the case.

You can now queue multiple actions and return to them when they're ready, making it simple to manage several tasks in parallel without losing track.

Starting today, Go users can connect to Microsoft SharePoint to manually import their knowledge into Go.

They can use this integration to:

• Import files into Agents

• Import files and folders into Cases

Soon, we're going to make both our Google Drive and Microsoft SharePoint integrations sync data automatically into Go.

More integrations are coming soon, and we're actively collecting user requests. If there's a specific integration you'd like to see, let us know by filling out this form.

Organizing agents in V7 Go is now more intuitive and secure. The new Folders feature lets you structure your workspace to reflect divisions, teams, and workstreams, with granular permission controls for each.

Folders make it easy to navigate and manage large volumes of work, ensuring that each team's work remains private and accessible only to the right users. For example, if you’re working on Legal Contracts in one audit, you won’t see or access Bank Statements in another.

Folders are fully integrated with Go. It's a familiar, scalable way to keep your workspace organized as your operations grow. Create folders, set permissions, and start organizing your agents.

Managing Cases in Go just got even easier. With the new Email to Cases feature, you can now start a Case by simply sending or forwarding an email—no need to log in or upload attachments manually.

Send or forward an email (with any attachments) to chat@concierge.v7labs.com. Concierge will automatically create a new Case, process your request, and run the right analysis for you. The full email thread is included in your case, so all your context and previous discussions are preserved. You’ll receive a response from Concierge in your inbox. You can continue the conversation by replying directly.

No more manual uploads. Forward emails as you review your inbox—cases will be ready for you in Go when you log in. Keep the conversation going by replying to Concierge’s email. Email to Cases meets you where you work, making it faster and easier to get help from Concierge—right from your inbox.

V7 Go's AI agents for tasks like CIM triage and contract review are already a hit and they make complex work simpler for many of our customers.

Now, we're making V7 Go even more powerful. We've expanded our agent template library with a new lineup of specialized AI agents, built by our AI solution engineers and industry experts. These new agents are ready to tackle complex workflows in:

• Insurance: Including new capabilities for Slip Ingestion.

• Tax & Accounting: Featuring tools like the US (IRS) Tax Claims Agent for automating validation.

• Real Estate: With a new agent designed for analyzing Offering Memorandums.

• Investment Operations: Including a new Data Room Agent to structure and analyze documents for financial due diligence.

• Many more: Ranging from competitor research to distributor agreements processing.

These 40 specialized AI agents can be used out-of-the-box or customized to fit your exact needs. If you want to request a specialized agent for your use case, let us know.

V7 Go now includes a new property type: Auto. This feature lets you describe a desired property in natural language, and V7 Go will suggest the best configuration, including the property type, the AI model best suited for the task, the inputs, and the expected output structure.

For example, if you enter:

I need a single-select property that classifies companies based on their funding round

Auto will recommend a Single Select property with classification logic, propose label values (e.g., Seed, Series A, Series B), and select the necessary input sources.

Auto property does not create the property immediately. Instead, it provides a pre-configured suggestion, allowing you to review and modify all aspects before saving. Automatic property configuration speeds up agent setup while preserving full control over how results are computed and structured.

V7 Go now supports the full GPT‑4.1 family: GPT‑4.1, GPT‑4.1 Mini, and GPT‑4.1 Nano. These models bring stronger reasoning, faster responses, and lower costs across a wide range of tasks.

To keep V7 Go agents running on the best available models, we are also refreshing the full model lineup. The GPT‑4.1 family is available now, with additional models from OpenAI and Google coming soon:

Now live:

• GPT‑4.1 replaces GPT‑4o

• GPT‑4.1 Mini replaces GPT‑4o Mini

• GPT‑4.1 Nano is newly added for high-speed, lightweight tasks

Coming soon:

• OpenAI o3 will replace o1

• OpenAI o4-mini will replace o3-mini

• Gemini 2.5 Pro will replace Gemini 1.5 Pro

Agents powered by GPT‑4.1 are more accurate at following detailed prompts, produce cleaner outputs, and handle longer interactions more reliably. While V7 Go already supports long documents through Knowledge Index and RAG, the expanded 1 million-token context window makes GPT‑4.1 a strong fit for cases where agents need to reference large, complex source documents directly.

Key improvements:

• Agents now understand structured input requirements, edge-case logic, and negative instructions like “don’t include X.”

• GPT-4.1 is 26% cheaper per request on average than GPT-4o, while GPT-4.1 Nano is the fastest, most efficient option for low-latency tasks like classification. Especially relevant for users who use V7 Go with their own API key.

• All 4.1 models can now handle up to 1 million tokens—ideal for agents reviewing large filings, contracts, or due diligence packs without missing context buried deep inside.

V7 Go now offers a conversational approach to AI document analysis through two new features: Cases and Concierge. This update makes interacting with the platform more intuitive and accessible to all users on your team, regardless of their technical background.

You may have noticed that Projects in V7 Go are now called Agents. This change reflects their specialized ability to solve domain-specific tasks using AI through multi-step reasoning, advanced retrieval capabilities, web search, and app integrations. Concierge serves as your AI assistant to communicate with these Agents and delegate tasks to them. Each conversation with Concierge is saved as a new Case and creates a persistent record that you can reference or continue later.

The example above shows Concierge analyzing a CIM document. When a user asks, "Can you triage a CIM document?", the AI assistant identifies and suggests the appropriate Finance CIM Triage agent. After the document is uploaded, the agent extracts key information (such as financial metrics, company description, and background details) and determines whether the triage result is a pass or a fail.

To explore more examples, watch this short tutorial video:

All extracted information is linked to the source via interactive hyperlinks that open the document at the relevant section. This design enables users to verify each data point without manually searching through the document. A collapsible sidebar on the right displays the extracted data alongside its source references, making verification simple and intuitive.

With Cases and Concierge, users can trigger workflows through simple chat messages, use multiple agents in one conversation, attach documents from various sources, ask follow-up questions, and verify AI outputs through interactive references.

The table-style view remains available for setting up agents, automations, and properties. To access it, click the "Configure agent" button that appears when you hover over agents on your V7 Go platform homepage. You’ll also notice that behind the scenes, V7 Go adds a new row each time a specific agent is run via Concierge.

We've created a new, unified panel for managing both your workspace-level files (Library tab) and integrations (Integrations tab), such as Google Drive. This centralized hub allows you to select all files or data sources for use as inputs or references inside your V7 Go projects.

• The Library is now a subsection within Knowledge Hub.

• The Library tab includes new search and sort functionalities for easier file management.

• When editing a prompt, you can inject and mention a file by typing @ or selecting it from the input list

• When selecting an empty File property inside a project, you can choose to:

  • Import a file from your computer

  • Use a file from the Library

  • Connect to Google Drive

At launch, Google Drive is the first available integration. More integrations are coming soon, and we're actively collecting user requests. If there's a specific integration you'd like to see, let us know by filling out this form.

V7 Go now supports Claude 3.7 Sonnet, Anthropic’s latest model with enhanced reasoning and coding capabilities. When selecting models and setting up your projects, you can now choose whether a specific V7 Go property should be calculated using standard Claude 3.7 Sonnet or Claude 3.7 Sonnet with thinking mode enabled for deeper analysis. This addition improves accuracy in instruction-following and multimodal understanding. It also provides greater flexibility and precision to optimize your AI workflows.

Reasoning models, from Deepseek to o3, have taken the world by storm.

Compared to traditional LLMs like GPT4o and Claude Sonnet 3.5, o3 has explicit step-by-step deduction baked into the training process, making it superior for tasks requiring complicated logical reasoning.

o3-mini can now power all property types in V7 Go, including Collections, Numbers, JSON and more.

In addition, we’ve added Gemini Flash 2.0, a powerful workhorse model with low latency and a large (1m) context window.

The Number Property enforces the output of numeric values, making it easier to work with data such as integers, percentages, and currency values.

Common prompts might be:

• Extract the revenue from @company in the @pitch deck. Include only the revenue for the last year. Output in $.

• What percentage of costs in the @CIM come from salaries?

• What is the net income in the @earnings report?

In addition, you can format decimals, negatives, separators, and alignment from the property configuration menu.

Stay tuned, as over the next few days, we’ll be adding both reasoning and AI citations to the Number Property.

Users can now recompute specific property values for individual fields without recalculating an entire property column. If a field produces an error or the output isn’t satisfactory, simply click on the field and select the Recompute option. You can also select a range of values, right-click, and recalculate multiple fields at once.

Until now, you could access and analyze web data in V7 Go by submitting specific URLs. With the new Web Search feature, it is now possible to ask questions directly in your prompt and pull in relevant information from the web.

• V7 Go will automatically use the most effective search queries and visit multiple pages.

• Perfect for data enrichment and accessing current information like stock prices.

• Get results as text, structured JSON, or Select/Multi-select properties.

Note: Source URLs and citations will be automatically displayed in the reasoning tooltip for full transparency in an upcoming update. In the meantime, include "list sources" in your prompt to view reference links in the output.