New updates and improvements
V7 Go

This new property type lets you link data between projects. You can pull information from V7 Go source projects based on conditions you set.

References unlock:

• Dynamic referencing. Pull in matching data from other projects automatically. For example, you can analyze Gong call transcripts involving a specific participant in one project, and then sum the deal values attached to those calls in a different one.

• Manual matching. Need complete precision? You can manually filter and select specific matches for nuanced use cases.

• Quick previews: Hover over matches for instant previews and snap to the source project in one click.

Whether it's enriching a project with relevant customer interactions or linking supporting documents to financial models, References help you connect all necessary data points with ease. Best of all, your data stays in sync automatically.

To see Reference Properties in action, check out this 90 second walkthrough.

File Bundles are now live in Go. This functionality is built for use cases where you need to work with a unit of data (a company, a checklist, an email with multiple attachments) which includes multiple files, such as:

• Company analysis where a single company consists of a pitch deck, accounts files, and interview transcripts

• Financial reports with supporting documentation and regulatory filings

• Insurance claims with policies, damage photos, written reports, and scanned forms

For instance, say you’re working with a company profile that consists of multiple files: simply add the pitch deck PDF, financial CSVs, and any other relevant documents into a single bundle/collection. This allows you to group multiple files under one cohesive unit.

Additionally, you can apply filters to specify which files within a collection/file bundle should be analyzed with AI. For a quick walkthrough, watch this 90 second Loom.

If you have any questions or a relevant use case, as always, reach out to us.

We've made several updates and added new functionalities that will make your V7 Go projects easier to manage and set up. These include:

• CSV previews. Inspect the contents of your uploaded CSV files directly within V7 Go.

• Sorting. Sort entities in ascending or descending order to group single-select classification results or find highest and lowest values with ease.

• Markdown formatting. AI outputs in entities now support markdown formatting for text and code.

Stay tuned for more updates!

The File Splitter splits PDFs and Excels into collections of individual pages or sheets.

Historically such splitting was generally done as a pre-processing step with code, but this is now available within Go natively, no code required.

This unlocks a deeper level of page by page or sheet by sheet analysis. For instance, you can turn an Excel file into a collection of sheets, run models over the individual sheets, and then aggregate these answers back up into a summary of summaries.

Since PDFs are split into pages represented by JPEGs, this also unlocks the native multimodal understanding of the latest foundation models, which can power tasks like reading charts or images from pages.

V7 Go now supports Excel file exports. Download a complete V7 project, and preserve your structure by saving each view as a separate sheet in the .xlsx file.

Benefit from easier data analysis and authorized sharing outside the V7 Go platform, the ability to add custom charts and reports without additional data manipulation steps. As well as using formulas and Excel functionalities on your V7 Go outputs and creating comprehensive backups in a widely-supported file format.

The template library has been redesigned with a focus on industry-specific solutions. You'll find in-depth templates for sectors such as finance, law, and logistics for data extraction and analysis tasks.

These project templates will help you explore V7 Go's capabilities and serve as great starting points for your projects. Feel free to try them out and use them in your workflows.

Explore new templates here.

You can now enable AI citations for JSON properties. This feature allows you to track the source of AI-generated insights within JSON structures, adding an extra layer of transparency to your data processing.

We've integrated OpenAI's latest model series, o1 and o1 mini, into V7 Go behind a feature flag. These models are pre-trained for chain-of-thought reasoning, making them ideal for complex tasks in data analysis, coding, and mathematical problem-solving.

These models prioritize accuracy over speed, taking more time to "think" before responding. While o1 outperforms GPT-4o in reasoning, it may not be suitable for all tasks. Please note the current rate limits of 100 requests per minute may cause errors, and they have higher token costs compared to GPT models.