IT operations
Agents can now grant access and change cloud settings. Who checks them?
IT agents act on the systems everyone else depends on. LeafCraft gives them narrow access, a checker for every change and a cost limit before work runs.
What's changing in IT operations
Agents grant access and change settings
Service desk and cloud agents now act on identity and infrastructure.
Non-human identities multiply
Every agent is an identity. Shared logins make them impossible to audit.
Cloud cost agents can spend
An agent that resizes a cluster at night can cost more than the engineer it replaced.
Two risks the layer removes
The agents you can't see, and the model that gets retired.
Agents you don't know about
In IT operations, agents arrive through vendor updates and team pilots. LeafCraft finds all of them, gives each an owner, and brings it under your rules or removes it.
A model that gets retired
An agent built straight on one model has to be rebuilt and re-approved when that model is retired or repriced. On LeafCraft you switch the model for that agent in config and keep everything else. Months and a budget, saved.
- The model is retired or repriced
- Prompts, tests and sign-offs rebuilt
- Months of work, a new approval cycle
- The history stays with the old tool
- Pick another model for that agent
- Switching is a config change
- Test it against your own record first
- Rules, limits, owner and memory stay
Why it matters now
In IT operations, the agents arrived before the rules did.
IT operations runs the agents other teams depend on, and the agents that other teams bring. The layer gives every agent its own login and only its role's access, routes changes by blast radius to named engineers, caps what an agent may spend, and records every grant, change and incident step.
The core infrastructure
What LeafCraft runs for IT operations.
One team
Agents triage, request and remediate within their limit. Named engineers approve changes above it. No agent approves its own change.
How it works02Your rules
Every agent has its own login and only the access its role needs. Changes escalate by blast radius to the people you name.
How it works03Your memory
Every access grant, change and incident step on the record, with who or what did it and why, open to audit.
How it works04Your budget
Cloud and model spend per agent and per task capped before it runs, and reported next to the work it paid for.
How it worksAI and people, one team
Your IT operations team, with AI on the org chart.
The agent prepares the case. Your person makes the call and writes why. A separate audit agent checks the decision against your rules.
What changes for you
How it helps your people
Who it helps around IT operations.
Industries where it runs
Leaders who ask first
Questions teams ask
Do agents get admin access?
No. Every agent has its own login with its role's access. A tool that is not on its list is refused before it runs.
Can we stop all agents during an incident?
Yes. One switch pauses the whole operation across every server and cancels work in progress, until you resume.
Where does it run?
In your own cloud account on AWS, Azure or Google Cloud, in your own Docker or Kubernetes setup, or on-prem.
Bring one IT operations process.
We'll map who does the work, who decides and who checks, set the cost limits and show you the record.