%20--%3e%3cstyle%20type='text/css'%3e.cls-0%20{fill:%23FF9900;}%3c/style%3e%3cpath%20class='cls-0'%20d='m117.3%2084h-14.1l39.2-79h-24.8l-20.3%2041.7-20.5-41.7h-3.8l-20.3%2041.7-20.8-41.7h-24.3l41%2083.3h8.2l18.2-37.7%2018.3%2037.8h23.7v2.8h10.7v-10.5h-10.6v3.3h0.2zm3.3-74.7h15.2l-28.9%2057.1-7.2-14.9%2020.6-42.2h0.3zm-69.3%2074.9-37-75h15.1l20.8%2042.4-5.8%2011%204.1%201.6%2016.9-33.9%207.2%2015.7-18.4%2038.1-2.9%200.1zm44.5-0.1-28.2-58.9%207.4-14.8%2029.6%2060.8-6.1%2012.9c0%200.1-2.7%200-2.7%200zm27.9%200.6v2.8h-3.1v-2.8h3.1z'/%3e%3c/svg%3e)
AI & AgentOps
Inventory, permissions, cost and risk for the models and agents now running in production.
On the roadmap — not available yet
This module is in design. Nothing described below can be switched on today. The same ground is covered now by our AI engineering, delivered by engineers rather than software.
Why this module exists
AI reached production faster than the controls around it. Most organisations cannot list which models they are calling, which agents hold credentials, or what those agents are permitted to touch.
What it is being built to surface
Descriptions of intent. No findings exist yet, because nothing is connected yet.
Model and agent inventory
What is deployed, by which team, calling which provider.
Agent permissions
What each agent can reach, and what it could reach if a prompt went wrong.
Tool and MCP governance
Which tools an agent may invoke, and who approved that.
Cost and behaviour
Token spend, latency, error rates and usage that suddenly changes shape.
What the module covers
- Model and agent inventory
- Agent permissions and tool/MCP governance
- AI security posture and architecture review
- Token usage, latency, errors and spend
Tell us what this would need to catch
We are designing this against real environments. If this is a problem you have, the fastest way to shape it is a conversation with the engineers building it.
Talk to an Engineer