Assistants

Your assistant's basic information:

• Avatar: the profile image. In the sidebar and favorites you only see the avatar – pick it as a clear distinguishing mark. Click it to adjust color and symbol.
• Name: short and concise so the task is instantly recognizable.
• Model: sets which AI model is used in the chat. Default is Best model – it selects GPT-5 and only switches to Gemini 3.5 Flash-Lite when the context window is exceeded, regardless of task type. For accuracy-critical tasks, pick a model manually instead. More under AI models.
• Description: explains the assistant's task and function – more detailed than the name, understandable to colleagues too.
• Default project: optionally assigns the assistant to a project; new chats then use that project automatically.

The Instructions section is your main lever for the assistant's behavior. Here you write the system prompt – the heart of your assistant. A good system prompt contains:

• The persona (the assistant's role)
• The task and how it should be solved
• Additional context
• The response format

Best practice – structure with ## sections. A prompt with clearly separated sections delivers noticeably better results than free-flowing text:

## Role
You are an expert in contract analysis.
 
## Task
Analyze uploaded contracts and identify risks.
 
## Rules
- Always answer in English
- Use the data pool for reference documents
- Use the Charts tool for visualizations

System prompts are merged in this order:

1. Personal instruction of the user (Preferences → Override System Prompt)
2. Predefined Organization Prompt (workspace level, maintained by workspace admins under Settings → AI & features → Chat – tone of voice, company principles)
3. Assistant prompt (this configuration – the specific assistant's role and task)
4. User input in the chat (the concrete request)

Keep each level focused – duplication leads to fuzzy answers.

The system prompt has no placeholder or variable syntax (for example, for the signed-in user's name) – it's passed to the model exactly as written. If the assistant should address the user's name or role, write that directly into the prompt or supply it in the chat. The curly-brace {{...}} syntax in the Prompt Library is a different, unrelated feature: it only applies to saved prompts and has to be filled in manually on every use – it doesn't auto-populate from user data either.

Top right, the Improve button optimizes your prompt automatically (structure, wording, completeness); Tips opens context-specific hints.

Here you equip the assistant with capabilities beyond plain answering. Five areas:

• Basic tools: built in and ready to use – calculator, charts, Memory, code sandbox, web search, image generator, and more.
• Connectors (Live): live-API connections to external services (Microsoft 365, Google Workspace, Jira, Confluence, HubSpot, Salesforce) as well as to databases and MCP servers released through an Outpost. They deliver real-time data and perform actions. Overview: All connectors.
• Custom MCP: connect your own MCP servers – for internal systems or special APIs. See Custom MCP Server.
• Databases: direct read access to structured data sources (PostgreSQL, MySQL, tables). See Connect databases.
• Request integration: missing a tool? Request it here.

A database or MCP service released through the Outpost shows up here under Connectors, not under Databases – the Databases tile connects MeinGPT directly, without an Outpost, to a database reachable from the internet. To release an Outpost service, see Outposts.

Retry behavior: if a single tool call fails, the assistant retries it automatically – a red mark on a single tool call is normal and doesn't mean the overall answer failed. Each retry attempt counts as its own step against the assistant mode's limit: if a tool keeps failing – for example because a connected service is currently down – that one tool alone can use up the entire step budget. The response then ends with the notice "Tool call limit reached" and an answer based on the results collected so far (details: "Maximum number of agent steps reached"), even though it can feel like an infinite loop while it's happening – the assistant reliably stops there at the latest.

Memory is one of the basic tools – detailed under Memory. For recurring procedures with your own instructions, templates or scripts, Skills are the next step.

Gives the assistant access to static company knowledge – in two ways:

• Upload files: individual documents via drag and drop. Good for manageable, assistant-specific sets.
• Connect a data pool (RAG search index): larger knowledge volumes via a pre-indexed search index, maintained by admins. Unlike connectors, data pools don't deliver live data but search a prepared knowledge base.

For most teams, the data pool runs on the MeinGPT Cloud and doesn't require a dedicated Outpost – more under Data Sources (RAG). A dedicated Outpost is only needed for on-premise setups, for example with special security requirements. Unsure whether to use a connector or a data pool? See the Integrations guide.

Two things are worth knowing before you upload larger sets: how long processing takes, and how the assistant treats Excel/CSV compared to Word.

Two optional levers at the very bottom of the editor:

• Conversation starters: predefined opening messages offered when the assistant is opened (e.g. "What is Apple's current stock price?"). Add as many as you like via Add another.
• Assistant mode: controls how many tool calls the assistant makes at most per answer. Default: up to 5 tool calls. Higher values help with complex tasks but cost more time and credits.

The Assistant check in the right sidebar checks live whether the basics are set: system prompt defined, description added, tools enabled, and knowledge sources linked. The detailed analysis also runs on Save.

There are several ways:

• Click the profile image under Favorites.
• Directly from the Preview top right on the editing page.
• Select it under My assistants and start with a conversation starter or your own message.
• In a general chat, pick an assistant via the model selector bottom right.
• In a running chat, type @ and pick the assistant (applies to that one message).

Clicking the card under My assistants starts a chat directly – the most common action.

Since an assistant is used far more often than edited, clicking the card is reserved for starting a chat. You reach the configuration via the three-dot menu (⋮) on the card → Edit assistant. The menu only appears if you have edit rights; for assistants shared as Can use, it isn't available.

Click the star on the card. Favorited assistants appear in the Favorites area of the sidebar with their avatar – the chat is start-able with one click.

In two steps: click the share icon (on the card or in the editor top right), then search for people or teams and choose the access type:

• Can use – use it, but can't view or edit the configuration
• Can view – view it, but can't use or edit it
• Can edit – use, change, and manage its shares

Workspace admins can also share with everyone in the workspace (org-wide is limited to Can use or Can view). The dialog shows all active shares; removing the workspace-wide share must be confirmed.

Assistants can be added via a shareable import link. Create links with the Assistant Creator↗. The import page supports the parameters c (compressed, recommended) and p (legacy). Details: Assistant Creator.

Workspace admins can pin shared assistants to the Apps area of the sidebar – they then appear there as standalone chatbot apps. Pin via the pin icon (📌) in the card header or the editor toolbar; unpin via the same icon or the context menu. Pinned assistants remain visible only to people who already have access to them – normal permission checks still apply. Pinned assistants can only be deleted after unpinning.

You'll find Delete in the three-dot menu (⋮) on the card. A confirmation dialog asks once more before the assistant is permanently removed.

If the assistant is pinned to the sidebar, the Delete entry is disabled – unpin it first via Unpin from sidebar (see above), only then can it be deleted.

A share (to people, teams, or the whole workspace) does not restrict deletion for you as the owner.

You can offer the same assistant to international teams in multiple languages without duplicating it: title, description, and conversation starters can be stored translated. On opening, the variant in the workspace's or user's language is shown. The system prompt is not translated; it applies as a single version to all languages.

Via the MeinGPT API you call assistants from your own applications or automations (e.g. Make). The AssistantID is in the browser URL in edit mode after /assistants/ (e.g. .../assistants/abc-123 → ID abc-123). Full reference: Assistants API.