Assistants
An assistant in innoGPT is your dedicated AI agent for recurring tasks. You set it up once with a role, instructions, files, and tools—and then use it over and over again without having to explain the context from scratch every time. It’s ideal for anything where you need consistent results: corporate-style copywriting, code reviews, proposal creation, and research workflows.
1. Create an assistant
Open the section: Click on Assistants in the left sidebar (or use
Cmd/Ctrl + Shift + A).Create a new one: Click on “New Assistant” in the top right corner.
🚀 Get started faster with the Assistant Store: Instead of starting from scratch, open the Assistant Store by clicking the “Assistant Store” button. There you’ll find ready-made templates (Copywriter, Code Reviewer, Researcher, and many more) that you can install with a single click and then customize for your company.
2. The Interface
The Assistant interface consists of eight sections:
1. 🗂️ Function menu (tabs)
At the top, you’ll find the function menu with five tabs where you can configure your assistant:
General — Name, Description, Model, and Creativity
Prompt — the system instruction (your assistant’s “behavior”)
Files — Knowledge base: documents and folders the assistant is allowed to access
Integrations — Tools such as Outlook, SharePoint, web search, MCP Server
Reminder — What the assistant should remember across conversations
2. Icon
You can recognize your assistant in the overview by its icon. Click on the circle to select an emoji or your own image.
3. Live Preview
On the right side, you’ll see a live preview of the assistant as your users will see it later—including the name, avatar, and configured welcome field. Changes are applied immediately.
💡 Practical tip: Configure settings in the left pane and test changes in real time on the right—this way, you’ll always know exactly how the assistant looks and works for your users.
4. Name
The name displayed for the assistant. Choose something short and descriptive—it appears in the assistant list and in every chat.
💡 Examples: “Surfboard Consultation,” “SEO Copywriter,” “HR Bot,” “Contract Reviewer”
5. Description
A short description that appears below the name. Helps you and your team quickly identify the assistant—especially if you have many assistants.
6. Model
Choose the AI model for your assistant:
Fixed model (e.g., GPT-5, Claude, Gemini)—predictable behavior, consistent responses
Smart—innoGPTt automatically selects the best model for each query
💡 Tip: Start with Smart if you’re unsure. For specific use cases (e.g., coding only or reasoning only), a fixed model is worth considering.
7. Creativity
Use the creativity slider (values 0 to 1) to control how freely the assistant responds:
ℹ️ If unsure: Set the value to 0.5 — works for most use cases.
8. ▶️ Test the assistant
Click on "Test Assistant" (top right) to open the assistant in a test chat. This lets you try out changes immediately.
3. Prompt
Instructions: Here you define your assistant’s behavior—its “system prompt.” Specific, short instructions work better than long wish lists. Here you can find a template for an assistant prompt.
You can also improve the prompt with AI, in which case a prompt schema is used directly:
Form fields: Predefined input fields to give the AI more context, which users can submit with a single click—ideal as a starting point.
✍️ Best Practice: Give your assistant one clear role, not ten. “Code reviewer for our Python services” works better than “all-purpose helper for development.” Specialized assistants deliver better results. Describe which tools and integrations your assistant can and should use.
4. Files
File Management: Upload documents (PDF, Word, Excel, Markdown, and more) that the assistant should use as a knowledge base. You can see the processing status right next to each file.
Enter a web source to be crawled and made available to the AI assistant
Synchronize your knowledge base
Link your own vector database
⚠️ Note on file size: We deliberately recommend a few curated files instead of many large ones—otherwise, the risk of hallucinations increases. For very large knowledge bases, it’s better to use the workspace’s Library/SharePoint.
5. Integrations
Enable functions: Selectively unlock tools that the assistant is allowed to use—e.g., web search, code interpreter, image generation, Canvas, or MCP Server.
The same tools are available as in the normal chat. You can find an overview at in the tools collection.
💡 Rule of thumb: Only enable what the assistant really needs for its role. Fewer tools = more focused, faster answers.
✨ Skills
Preconfigure skills that are automatically activated when users chat with this assistant.
Skills are reusable sets of instructions or workflows. If you set up one or more skills here, they’ll be automatically active in every conversation with the assistant—the user doesn’t have to trigger them individually.
When is this useful?
Your assistant should always follow a fixed pattern (e.g., “QBR Preparation Guide,” “OKR Writing Guide”)
Specific formatting or tone skills should always be applied
You want to automatically provide domain-specific knowledge (e.g., “omega-technology-diepholz”) for every chat
💡 Example: A “Sales Assistant” with the “Professional Email Templates” skill enabled automatically provides appropriate email structures—without the user having to manually call up the skill.
🧩 Apps
Select the apps this assistant needs. Connected apps are automatically activated during chats.
Here, you link external MCP services that you’ve already connected in innoGPT—e.g., Outlook, Google Calendar, Notion, Google Sheets, Gmail, Google Drive. The assistant can then access these apps directly without the user having to activate them for each chat.
🔗 MCP
Select your own MCP server, whose tools are automatically available when chatting with this assistant.
If your workspace has configured MCP servers, you can specify here which ones your assistant is allowed to use automatically.
When is this useful?
Your assistant should be able to access a specific tool directly (e.g., “Get me all open Jira tickets in Project X”)
Specialized assistants for a specific system (Featurebase Assistant, GitHub PR Reviewer, …)
💡 All apps and MCPs must be configured and authenticated in the settings before linking.
🌐 APIs
Select Custom Actions whose endpoints are available as tools when chatting with this assistant.
Custom Actions are your own API endpoints that have been set up in your workspace—e.g., internal microservices, your own database APIs, or third-party interfaces. Here, you select which of these actions the assistant is allowed to call directly.
Typical use cases:
📊 Retrieving data from internal systems (CRM, ERP, BI tools)
🏷️ Triggering workflows (orders, tickets, approvals)
🔍 Lookups in proprietary data sources
⚠️ Setup requirement: Custom Actions are configured at the Workspace level by admins.
🤝 Subagents
Select which other assistants this assistant is allowed to delegate tasks to.
With sub-agents, you can connect your assistants into a team: Your main assistant can pass on subtasks to specialized sub-agents—just like a project manager who distributes work to specialists.
How to use sub-agents:
Enter here which other assistants are available as subagents
In the chat, type "
@" or the assistant will automatically load the sub-agentYou or the main assistant can specifically address a sub-agent
When is this useful?
Complex workflows involving multiple specialties (e.g., a “Project Manager” assistant delegates to a “Research Assistant,” “Copywriter Assistant,” or “Reviewer Assistant”)
Modular architecture instead of an overloaded mega-assistant
Reuse of proven assistants in other contexts
💡 Real-world example: A “Content Manager” assistant delegates to an “SEO Copywriter” for blog introductions, to an “Image Generator” for cover images, and to a “Translator” for the English version—all from a single chat.
🎯 Which integration to use and when?
3.5 Reminders
Add reminders: Save information that the assistant should remember permanently (e.g., company context, preferred formats, wording rules). You can also have reminders added directly in the chat—just tell the assistant: “Remember this.”
Reminders also update automatically
4. Share assistants
Sharing within the workspace enables team collaboration and ensures that all colleagues have access to your specialized AI assistants.
Select an assistant: Open the assistant you want to share.
Access the share option: Click Share in the top-right corner.
Add people: Enter the names or email addresses of the people who should have access.
The people must be members of the same workspace.
Set access rights:
Viewer → can only use the wizard
Editor → can also edit the wizard
General access: Decide whether only invited people or everyone in the workspace should have access.
Save: Confirm the changes.
5. Frequently Asked Questions
What is the difference between an assistant and a project?
An assistant is a persona with a fixed role (What can it do? How does it react?). A project is a context container for related chats and files on a specific topic. You can combine both: use a specialized assistant within a project.
What is the difference between assistant files and knowledge?
Assistant files are tied to that specific assistant. The Library/Knowledge is the workspace-wide knowledge base and is available to any assistant or chat with Library access. Rule of thumb: General company knowledge → Library. Specific specialized knowledge → Files.
Can an assistant call upon other assistants?
Yes, via sub-agents—configurable in the assistant settings. This is how you delegate subtasks to specialized assistants.