Deployment
Your environment. Your data.
TraceStone runs inside your company, next to your agents and the tools they use. Nothing sensitive leaves your environment.
- Runs in your environment
- Your rules, enforced
- Payloads stay in your workspace
Where it runs
Runs where your data lives.
You choose where it runs. Your agents keep their framework, and your auditor gets proof, not your data.
- Your own servers Run it next to the systems your agents already use.
- Your private cloud Run it inside the private cloud you already control.
- A hybrid setup Mix your servers and your cloud, as your teams need.
- Your agent framework No new framework to learn. It works with the one you use.
Ways to connect
Pick your setup. Block or observe.
Each way keeps signed records of what your agents do. The gateway and the embedded check can also stop an action before it runs.
Start with the log collector. Move to the gateway when you are ready.
Your environment
-
Security gateway
Put TraceStone in front of your agents' tool calls. It can block.
-
Embedded check
Call TraceStone from your agent's own code. It can block too.
-
Log collector
Send records after the fact. Start by observing, with almost no changes.
Getting started
Start small. Grow when ready.
Prove it on one of your agent workflows first. Then cover about five with a yearly licence.
- A 6–8 week pilot One of your agent workflows, inside your environment.
- Observe first The log collector keeps signed records, with almost no changes.
- Then enforce Move to the gateway, and actions are checked before they run.
- A yearly licence After the pilot, cover about five of your workflows.
- Pilot one workflowStart with the log collector Pilot · 6–8 weeks1 workflow
- Turn on enforcementActions checked before they run When you are readyLog collector Security gateway
- Grow with a yearly licenceAfter the pilot YearlyAbout five workflows
Where does our data go?
Nowhere new. TraceStone runs inside your environment: your servers, your private cloud or a hybrid setup. It works with any agent framework.
How do we connect our agents?
Three ways: a security gateway in front of your agents' tool calls, an embedded check in your agent's code, or a log collector that records after the fact (it cannot block, but keeps signed records). You can start with the log collector and move to the gateway later.
How do we start?
With a paid pilot of 6–8 weeks on one of your agent workflows, inside your environment. After the pilot, a yearly licence covers about five workflows.