> For the complete documentation index, see [llms.txt](https://docs.revenium.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.revenium.io/track-and-control-costs/analyze-ai-tooling-spend/tickets.md). # Tickets See what coding assistant work costs for each engineering ticket, and find spend that carries no ticket. **In the product:** `https://app.revenium.ai/ai-assistants/tickets`, or **Intelligence > AI Assistants > Tickets**. Tickets shows what AI work costs for each engineering ticket, most of it from coding assistants, so you can use past ticket costs when planning similar work. Spend from agents that run with no person, such as a code review bot, is shown apart from spend by the people who used a coding assistant. This page covers what Tickets needs, how it works, and how to read it. ## What it needs * **A coding assistant** sending usage to Revenium. Without one, the page asks you to connect one. * **Revenium's Developer Cost Toolkit** for each engineer. Its ticket gate asks which ticket the engineer is working on at the start of a session and ties the work that follows to that ticket. Ticket attribution is available on paid accounts. Setup is available from your Revenium customer success manager; ask them to set it up for anyone missing it. * **Engineers who answer the ticket gate.** A session may show one short attribution line. An engineer can change the ticket at any point in a session, or say that no ticket applies, and the work that follows is charged to the new ticket or marked as opted out. How to do both is part of the setup available from your Revenium customer success manager. Until your team sends its first ticket, Tickets shows sample ticket costs instead of your own. With no coding assistant connected, the sample sits behind **You're viewing sample ticket attribution** and **Connect an AI assistant**. Once an assistant is connected, it sits behind **Your coding assistants aren't sending tickets yet** until the first ticket arrives. Either preview shows what you can compare once tickets arrive; its figures are sample data, not your team's spend. After your team has sent tickets, if spend arrives but none of it carries a ticket, the page shows **Turn on the ticket gate**. ## Reading the numbers ### Coverage: how much spend is tied to a ticket? The band at the top splits coding assistant spend into **Attributed to tickets**, **Opted out** (the engineer said no ticket applies) and **Unattributed** (no ticket and no opt-out), with the period's total spend, tickets touched and median ticket cost. A growing **Attributed** share means the ticket gate is working. ### Attributed: what did each ticket cost? **Attributed** lists spend by ticket. Open a ticket for its cost, active time, sessions, contributors and activity. Filter by work mode, person, assistant or repository to compare similar work. A ticket title appears beside its key when the session supplied one. One coding session can cover several tickets. Each ticket's **Sessions** card shows the part of that session's cost and active time that belongs to it, so the same session may appear on several ticket pages without charging its full cost to each one. ### Who did the work on a ticket? A ticket can carry AI work of two kinds, and the ticket keeps them apart: * **A person helped by a coding assistant.** An engineer working in Claude Code, Cursor or another assistant, in the terminal or the desktop app, appears by name under **Contributors**. * **An agent doing the work itself.** Spend from an agent that is not a coding assistant, such as a code review bot, has no signed-in person, so it appears as **Agents (no person)**. The **Tools** card on the ticket breaks spend down by the assistant or agent that sent it. Spend with no person and no agent name appears as **Unknown**. ### Unattributed: who needs the ticket gate? **Unattributed** shows spend and sessions with no ticket. **See who** on the coverage band takes you to the people behind it, and **Never sent a ticket** lists people to follow up with, with **Copy emails**. ## Limits * **No ticket gate seen** is a strong sign the gate is missing for a person, not proof. Revenium sees their session history, not whether the toolkit is set up for them. * A ticket key is attached when it takes the usual tracker form: a project key, a hyphen and a number, such as `PROJ-123`. A key in another form is not attached. * Ticket titles appear only when the session supplies one; the key is always shown. * With no assistant spend in the selected dates, there is nothing to show. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.revenium.io/track-and-control-costs/analyze-ai-tooling-spend/tickets.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.