We're proud to be building the most robust AI operating system for high-stakes financial work with @OpenAI
Read more here: openai.com/index/v7/

Here's what's landed last week:
- Context Graphs queries 3x faster.
- Subagents, and cross-playbook collaboration
- Improved slide generation with native editing.
- More consistent template-following for workflow outputs.
- 10 new MCP apps with 1-click installs
- GPT-6 Astra

Music to our ears 👂

I trained an AI model to autocomplete my piano prompts.

Here’s what happens when I give it the first few notes:

Your AI shouldn’t start from zero every time a new file lands.
V7 Context Graph connects your firm’s documents, data sources, entities and relationships into one live, source-backed layer of context.
See it on your own data → bit.ly/3Rhyx0E

V7 Disclosure: Moderne Ventures is an investor in our company and a user of our product. No compensation was provided for this video.
From data room to investment memo. See how Moderne Ventures uses V7 Go to take due diligence from weeks to a day.

bit.ly/3Tfb00O

Insurance is a brutal test for AI.

SOVs, claims notes, broker emails, bordereau formats, risk reports, and useful context scattered everywhere.

John Somerset-Irving shows how V7 Go handles the messy bit most demos skip.

Watch here: bit.ly/4vvBBVm

V7 Go now connects to all your favorite apps via MCP Integrations

→ 2–3 click setup
→ Agents pick the right actions on its own
→ Results that look native to each app, not just a wall of text
→ Works at massive scale across agent tables

Learn more: v7labs.com

The agentic tax is real.

More flexibility often means more time and tokens spent deciding how to solve the problem.

Sometimes tighter workflows win.

V7 cofounder & CTO @SimEdw explains 👇

Insurance data is messy.

PDFs. Emails. Excel files. Slide decks. Phone calls. Images.

Most AI workflows struggle once formats start piling up.

John Somerset-Irving explains how V7 processes unstructured insurance data accurately and at scale. #InsuranceAI

"make it your use case. not one a vendor is pushing on you."our resident AI insurance expert John on where insurers should actually start with AI. 60 seconds 👇

Writing good business faster.

That’s the goal.

John Somerset-Irving explains how insurers are using V7 to reduce manual underwriting work, surface risk information faster, and fit AI into existing workflows without replacing core systems. #InsuranceAI

The AI industry spent 2 years trying to escape workflows and accidentally rebuilt them with 400x more tokens.

bit.ly/3PxKMFf

Sticking with the same model for every job is how you end up paying Opus prices for work Haiku could've done in its sleep.
Our co-founder and CTO @SimEdw on choosing the right one. in V7 Go you can swap models per step and benchmark them side by side 👇

The hard part of AI at work isn't the AI. It's trusting it.
Our co-founder Simon Edwardsson on how V7 Go solves that, in 32 seconds.

Why do LLMs hallucinate?

Our co-founder and CTO Simon Edwardsson explains, and shows how we fixed it at v7.

Most M&A teams aren’t short on data. They’re drowning in it.

The problem is stitching it together fast enough to make a decision.

CIMs, data rooms, expert calls, internal notes. All disconnected.

Featuring Abhishek Upadhyay (Cantor Fitzgerald):

bit.ly/3OrZ2Py

We’re done pretending AI slides are good.

They’re not.

So we built one that is.

Slides, powered by V7. Watch the keynote release ↓
bit.ly/4vJosIS

V7 Go accelerates 10-Q analysis by automatically extracting key financial metrics, surfacing QoQ changes, and flagging material developments across filings. Our AI agents deliver structured, source-cited outputs in minutes.

See the 10-Q agent in action: v7labs.com/automations/ai…

If you can explain how you work, AI can execute it.

The hard part is making that process clear.