> ## Documentation Index > Fetch the complete documentation index at: https://docs.dualentry.com/llms.txt > Use this file to discover all available pages before exploring further. # Accounting Copilot: Agents Panel Reference > Reference for the Agents panel: navigation sections, composer controls, entity and accounting-basis scoping, and how it relates to other Copilot surfaces. The Accounting Copilot Agents panel is the persistent surface for conversational work in DualEntry. It holds your Copilot conversations, the connectors and skills those conversations can use, and the scheduled agents that run without you. Open it with the Copilot button in the top bar. The panel opens along the right side of the window and can be resized, so the record you are working on stays visible beside it. Close it with the **X** in the panel header. The panel is the only Copilot surface that carries navigation, which is why connectors, skills, and scheduled agents are created and managed here rather than from the **Cmd+K** command bar or the copilot embedded in a record. For how the three surfaces relate, see [How the AI Accounting Copilot Works](./ai-accounting-copilot). ## Navigation sections The Agents panel's navigation holds six sections, each a separate surface: your conversations, the artifacts they produce, and the connectors, skills, and schedules they draw on. The table below lists every section and what it contains. | Section | Contents | | ---------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | New Agent | Starts a new conversation with an empty composer. | | Scheduled Agents | Agents that run on a cadence. See [Scheduled Agents Reference](./scheduled-agents). | | Skills | Saved, reusable instructions invokable with `/`. See [Skills Reference](./skills). | | Connectors | Installed MCP connectors and the registry browser. See [How to Connect an MCP Connector](./connect-an-mcp-connector). | | Artifacts | Documents, reports, and files produced by your conversations. Artifacts are per-user: this list spans your own sessions, not your colleagues'. | | Settings | Your own Copilot preferences: response modifier tags, a custom preface added to your requests, and whether Copilot remembers details between conversations, including the list of what it has remembered. | Below the navigation, the panel lists your **Scheduled** agents and **Recents**. Scheduled entries carry a cadence badge such as **Recurring**. Each list has a **See all** link and a collapse control. Recents are conversations from this and prior sessions, titled from their first exchange. Closing the panel does not end a conversation. It stays in **Recents**, so reopening the panel and selecting it resumes where you left off. Each browser tab holds its own conversation context, so a conversation open in one tab does not interfere with a conversation open in another, and the panel in each tab tracks only what happened in that tab. ## Composer controls The composer is where you type a request in the Accounting Copilot. Three controls sit below the input: the **+** menu, the accounting-basis selector, and the entity selector. The two selectors change the numbers you get back rather than just the presentation. The **+** control is not only a file picker. It opens a menu that reaches most of the panel's navigation from inside the composer, so you rarely have to leave the conversation to pick up a skill, a connector, or a schedule. The menu holds six rows: | Row | What it does | | ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Add files or photos | Uploads documents and images to the conversation, where they become context for it. Accepts `.txt`, `.pdf`, `.doc`, `.docx`, `.csv`, `.xls`, `.xlsx`, `.png`, `.jpg`, and `.jpeg`. | | Skills | Opens a searchable list of skills, split into **Personal Skills** and **Built-in Skills**, and inserts the one you choose into the composer. | | Connectors | Opens a searchable list of connectors, split into **Team** and **User**, with a toggle that turns each connector's tools on or off for the conversation. | | Artifacts | Opens the Artifacts page. | | Settings | Opens your Copilot settings. | | Scheduled Agents | Opens the Scheduled Agents page. | Five of those six rows lead to a section of the panel navigation described above. The composer menu and the navigation are two routes to the same surfaces rather than separate features, so a skill or connector you reach one way is the same one you reach the other way. The other two controls are selectors. Both apply to the whole conversation rather than to the message you are typing, and neither can be pinned by a skill or set as an organization default: | Selector | Options | Default | What it sets | | ---------------- | ---------------------------------------- | ----------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | | Accounting basis | **GAAP**, **IFRS** | **GAAP** | The basis for every balance the conversation returns. Not configurable per organization, so an IFRS-first team sets it on each conversation. | | Entity | Any single company, or **All companies** | **All companies** | Whether queries run against one company or the consolidated view. In a multi-entity organization this is the control most likely to change an answer. | For what goes wrong when these are set incorrectly, see [How the AI Accounting Copilot Works](./ai-accounting-copilot). Submit with the arrow control or the keyboard. Below the composer, **Try Skill press /** indicates skill invocation from the same input. ## Suggested prompts New conversations in the Accounting Copilot open with suggested prompts as starting points, including a review of what needs attention today, close status, a summary of your recent activity, and a P\&L refresh. **See all suggestions** expands the full list. The two selectors apply to a suggested prompt exactly as they do to one you type, because they scope the conversation rather than an individual question. Suggestions are generated for you rather than drawn from a fixed list. DualEntry reads your own recent activity in the audit trail, roughly the last five days, and proposes the steps an accountant would naturally take next. Two people sitting down at the same moment see different suggestions, and someone with no recent activity sees a general starting set instead. A generated set is held for about four hours before it is rebuilt, so suggestions do not change between one conversation and the next within a working morning. Activity from the last few minutes may therefore not be reflected yet, which is worth knowing if you expect a suggestion to appear immediately after posting a batch. When generation is unavailable, the panel falls back to a fixed starting set rather than showing nothing. A generic-looking list is that fallback rather than a judgement that you have done nothing recently. ## Permissions and logging Every conversation in the Accounting Copilot inherits the permissions of the person running it. Role-based permissions determine which entities, modules, and records a user can open, and Copilot operates strictly inside that grant. See [user roles and permissions](../platform-configuration/user-roles-and-permissions) for the full model. Copilot cannot return a record you could not open yourself, and it reports that it cannot answer rather than estimating when data is out of scope or absent. Two people can therefore ask the panel the same question and get different answers, which reflects their roles rather than a fault in the assistant. Every prompt and response in the panel is written to the [audit trail](../platform-configuration/audit-trail-and-compliance), including prompts a scheduled agent runs while nobody is watching. For the fields each entry records and where to review them, see [How the AI Accounting Copilot Works](./ai-accounting-copilot). Connector tool calls are the exception to the permission model. A connector acts with the permissions of the credential used to authenticate it in the external system, which has no relation to the permissions granted to you in DualEntry. See [how to connect an MCP connector](./connect-an-mcp-connector). ## Related reading * [How the AI Accounting Copilot Works](./ai-accounting-copilot) * [Skills Reference](./skills) * [Scheduled Agents Reference](./scheduled-agents) * [How to Connect an MCP Connector](./connect-an-mcp-connector) * [Spotlight Search Reference](./spotlight-search) * [Audit Trail and Compliance](../platform-configuration/audit-trail-and-compliance)