With the new AI summaries, Meisterplan provides concise project overviews. Instead of gathering information manually, the system generates AI‑powered project summaries that are based on predefined or custom prompts. These prompts can also be shared with others. This gives you a quick understanding of a project's status. You can also copy the generated summaries when needed and use them for external status reports.
- Prerequisites
- Where to Find
- What data is taken into account?
- How AI Summaries Work
- Frequently Asked Questions
Prerequisites
To use AI functionality, go to Integrations > Meisterplan AI in the left sidebar and switch on Meisterplan AI.
Required User Rights
- To activate Meisterplan AI, your user group needs the Configure Meisterplan AI right under System Administration > System Administration.
- To use Meisterplan AI, your user group needs the Access AI Summaries right under Views & Areas > AI Functionality.
Where to Find
Select a project in a view such as the List or the Portfolio Designer. Then, open the Information Panel on the right side and click the AI icon:
You will see a preconfigured default view with a preselected prompt, allowing you to immediately generate an initial AI‑generated response.
What data is taken into account?
The AI uses various project data to generate a response. This includes:
- All project fields of the respective project
- Project KPIs, such as budget values, capacity utilization, completion level, and project priorities
- Project Change Log within a custom date range
- Project and allocation comments within a custom date range
How AI Summaries Work
Learn below how the feature works and how to add, share, or edit prompts.
General tips for creating prompts and a collection of sample prompts can be found here.
Adding, Editing, and Deleting Prompts
To create a new prompt, open the dropdown menu, and select Add New Prompt:
You can edit or delete any prompts in your list, whether they are preconfigured prompts, ones you've created yourself, or shared prompts. If you modify and save a prompt, the change applies to all users who have access to it. If you delete a prompt, it is removed for everyone.
Date Range for Project Change Log and Comments
Enter your prompt in the text field and select a date range within the prompt configuration. This determines the period for which the AI will include project and allocation comments as well as the project change log in its response to your prompt. Then, click the arrow next to Save and select Save as New Prompt.
Sharing Prompts With Other Users
Provide a name for the prompt and specify which user group and/or individual users you want to share it with:
Generating and Copying Responses
Click Generate to receive an AI-generated response to your prompt:
Please note: AI-generated responses may be incomplete or contain errors. The results might not include all the desired information or may be inaccurate. Therefore, review the suggestions carefully before using them further.
You can copy the generated text with a single click and paste it directly into Meisterplan (e.g., in the project description) or into external tools:
This saves you time when creating project status updates and reports.
Frequently Asked Questions
Question: What type of AI language model does Meisterplan use, and which datasets is it based on?
Answer: The AI Summaries feature uses a generative language model (Large Language Model, LLM) from Anthropic’s Claude family. Currently, the Claude 4.5 Haiku model is being used. The model is deployed as a Managed Foundation Model via Amazon Bedrock.
The training data consists of a mix of licensed data, human-created training examples, and publicly available texts. Specific individual datasets are not disclosed by the provider. A detailed description of the training data is available from Anthropic in their official System Card.
---
Question: What data was used for training purposes?
Answer: The training data for the AI model used comes exclusively from the AI provider Anthropic. It consists of a mix of licensed data, human-created training examples, and publicly available texts. The training data for the Claude Haiku 4.5 model comes from sources extending to July 2025. Information generated after this date is not part of the training dataset and therefore cannot be reliably reflected in the model's knowledge (source).
Project or customer data from Meisterplan is not used for training purposes and is not incorporated into either the training or further development of the AI models.
---
Question: Where is the AI hosted?
Answer: The AI Summaries model provided by Anthropic is operated via AWS Bedrock. Request processing takes place within the infrastructure provided by AWS and exclusively in the configured AWS region, either in the United States (Oregon region) or within the European Union.
AWS documents that user inputs and the model outputs are not shared with the model providers (source).
---
Question: How are biases in AI models ("hallucinations") checked?
Answer: To reduce biases and "hallucinations", several measures are combined. The AI is used in such a way that it relies exclusively on the explicitly provided project data. This reduces the likelihood of unfounded or speculative statements.
Furthermore, the model provider Anthropic has specifically trained the AI to be cautious in situations of uncertainty. The goal is for the model to recognize missing or unclear information and communicate it transparently, instead of generating false or fabricated content. This approach is part of their "Constitutional AI" training and is verified through regular evaluations and tests.
Anthropic explicitly points out that outputs may be incorrect, incomplete, or misleading and should not be used as a factual basis without independent verification (source).
---
Question: How do you ensure that no harmful or discriminatory content is generated?
Answer: To generate AI content, an established AI model (Claude from Anthropic) is used. It has integrated safety and alignment mechanisms. The model is trained according to the "Constitutional AI" approach.
In this approach, the AI is guided by a written "constitution" that defines binding principles for generating responses. These include, among others:
- No discrimination or derogatory content towards protected groups
- Avoidance of racist, sexist, or hateful language
- Respect for human dignity and equality
These principles are an integral part of the training and evaluation process and serve to systematically prevent harmful, discriminatory, or inappropriate output (Source, Safeguards and harmlessness).
---
Find more details on data security in our Trust Center.