> For the complete documentation index, see [llms.txt](https://docs.finout.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.finout.io/ai-and-developer-tools/account-instructions/4-practical-patterns-for-setting-up-finout-account-instructions.md).

# 4 Practical Patterns for Setting Up Finout Account Instructions

Billy, Finout’s industry-leading AI FinOps assistant, is built to digest massive amounts of cloud spend data instantly. But because no two enterprise environments share the same billing model, one size doesn't fit all. That’s why we built[ Account Instructions](https://docs.finout.io/ai-and-developer-tools/account-instructions)—a powerful context layer that lets you define how your account works once so every team member gets answers built on your exact environment.

Rather than forcing engineers and finance leads to paste custom prompts, billing rules, or tag mappings into every query, Account Instructions store your organization's business logic directly inside Finout. It turns Billy from a smart AI assistant into a true extension of your FinOps team.

The best configurations aren't about controlling the AI—they are decisions your team already made informally, written down once so everyone gets the same accurate answers.

Here are four core patterns you want to consider when defining your Account Instructions:

#### Map Ownership Hierarchy (Who Owns This Line Item)

* The Pattern: Lay out your exact operational structure and point Billy to the specific Virtual Tags that define ownership for chargeback and showback.
* Example: "Our organization operates under a three-tier hierarchy: Business Unit -> Engineering Division -> Service Owner. Use Virtual Tags: Business Unit -> Team -> System."
* Why It Works: Answers the core question of "who owns this line item" immediately, routing cost allocation cleanly to team leads without manual tag looking up.

#### Translate Human-Speak into Database-Speak

* The Pattern: Connect everyday team shorthand to your actual Virtual Tags so Billy doesn't have to guess what you mean.
* Example: "When anyone asks about 'Project Phoenix' or 'Phoenix System', query the Virtual Tag Key 'App\_Name' with the value 'Phoenix\_Prod'."
* Why It Works: Saves your team from memorizing database keys like vt\_env\_prd\_019 just to run a quick cost check.

#### Enforce Financial Ground Rules & Reconciliation Logic

* The Pattern: Standardize default metrics, credits, and calculation logic so queries align with actual invoices.
* Example: "When checking for spend anomalies, compare against a 7-day rolling average. Always default to amortized cost and exclude one-off credits to ensure zero variance between invoice and bill."
* Why It Works: Guarantees that finance and engineering see identical spend numbers without discrepancy between reporting and actual billing.

#### Exclude Intentional Idle Resources

* The Pattern: Explicitly filter out secondary regions, failover clusters, or intentional standby assets.
* Example: "When scanning for idle assets, ignore us-west-2. That is our disaster recovery site and those resources are intentionally idle."
* Why It Works: Keeps optimization recommendations actionable by ignoring intentional infrastructure redundancy.

Getting Started Setting up Account Instructions takes under five minutes. Document the rules your team already uses today, add them to Finout, and ensure Billy answers every query using your exact financial and organizational context.

<br>


---

# 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.finout.io/ai-and-developer-tools/account-instructions/4-practical-patterns-for-setting-up-finout-account-instructions.md?ask=<question>&goal=<user_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.