Real shape, stand-in values
Names, numbers and dates that look right and match your real structure. None of them real.
Let coding assistants build on data that looks real and isn't.
Your AI coding tools work against convincing stand-in data generated from your real records. The structure behaves like production; the real values never leave. Self-hosted, on your own keys.
Book a demoTalk it through with us
Try the labsHands-on, synthetic data, no sign-up
Ready to try it on your own instance? Request a trial.
Self-hosted, on your own keys. No credit card.
Transcript (79 seconds)
Ascent product overview: five core features.
One: see every AI agent with access to your data, and its blast radius before it acts. Data repository by data repository, which read modes it's allowed, who armed each token, and how much it could reach: here, forty-one thousand two hundred records, thirty-seven percent of the estate, in plaintext.
Two: permissions with real granularity. Not just what can be accessed, but under what context: who is asking, agent, person or service; which data repository, record type and tags; and conditions like multi-factor authentication, signed requests, IP ranges, countries, days and hours.
Three: when an agent oversteps, it's refused in the moment, and the reason is written down in plain language. You decide what happens next with customizable response workflows: take action directly, freeze the data repository, revoke the token, alert, or push notifications to your SIEM.
Four: agents get what the task needs, and the rest stays out of reach. The same record reads four ways: redacted, anonymized, ciphertext, or plaintext, whether it's accessed by an agent, a human, or software, through the UI, the API, the CLI, MCP, or SQL. Every one is a separately permitted, separately audited read.
Five: when the auditor comes, you hand over an evidence pack built from the hash-chained audit log: signed, framework-aware, and verifiable by anyone who presses Verify.
Ascent. A modern data control plane so you can control what AI can see and do.
What you get
Your queries keep their shape
Your code connects through the standard database driver for its language. Queries, joins and writes work through it; transactions and schema migrations don't.
Assistants see less by default
An AI coding assistant connected through Ascent starts read-only and redacted. It sees more only when a person allows it.
Three steps, on the real product.
01
Bring your existing database
One command plans the move and a second runs it. Sensitive columns are found and encrypted on the way in.
02
Point your assistant at the stand-ins
Give the assistant an identity that only reads anonymized data. It builds against real-looking records that reveal nothing.
03
Ship the same queries
In production, the people and systems allowed to see real values see them; the assistant never did.