IT operations agents
PlannedTicket triage, access requests and runbook execution with approvals.
Andiamo Enterprise · IT operations
Planned work: a request is read against the systems it touches, a change is written out in full, and the person who owns that system decides.
How the work would run
Who the work belongs toThe team that runs internal systems and answers the requests that land in their queue, alongside the owners who have to sign off on a change.
Andiamo Enterprise is a planned product line. Steps marked for approval are designed to wait for a person, and the status beside each step is taken from the registry entries it would lean on.
Ticket
PlannedAndiamo Enterprise is planned, so this is the shape of the work rather than software you can run. A request for access, a fault report or a routine change lands in the queue the team already uses. The work starts by reading it: what is being asked for, which system it touches, and who owns that system. Nothing is acted on at this point.
Triage
PlannedBefore anything is proposed, the records, the ownership and the permissions the task would need are gathered into one packet. Context assembly is a Lamiak Core part, built for selected workflows and in development; the packets are not yet kept for anyone to read back, which is one of the reasons this line is not offered.
Change
PlannedThe agent describes what it would do, in which system and why, in the terms the owner of that system would use to judge it. The proposal is the unit of work; the action waits behind it. Where policy says so, a person approves before anything changes.
Decision
PlannedA person decides on the exact change, and that decision is recorded with who made it and when. Approvals and decision records are a Core part in development, exercised in testing and not yet switched on in a live product, so the record this step depends on is not something you can inspect today.
Feedback
PlannedAn edited or rejected proposal says where the work was misread, and that is the part worth keeping. Recording how people respond to suggestions, including their edits, is a Core part in development and captured in a few places today rather than as one stream. Routing each step to a model or to plain code by task, cost and data sensitivity is the one piece in pilot: it runs in our own engineering operations.
Where each step stands
What this leans on
The agents for this domain are planned: designed, and not built. Underneath them sit the Lamiak Core parts they would rest on. Most of those are in development, exercised in testing; model routing is the one in pilot, running in our own engineering operations. The full list is on the product page.
Ticket triage, access requests and runbook execution with approvals.
Agents that propose actions inside your systems, with a person approving and a record of each decision.
Selected actions wait for an owner or admin to approve or reject them, and each decision is recorded with who decided and when; not yet switched on in a live product.
Gather the records and permissions an agent needs for a task into one packet before it acts; built for selected workflows, and packets are not yet saved for review.
Route each step to a model or to plain code based on task type, cost and data sensitivity. Running in our own engineering operations.
Record how people respond to AI suggestions, including edits and rejections, and whether they found them useful; captured in a few places today, not yet as one feedback stream.
Before it ships