Skip to content

Commit 9ec18a0

Browse files
Merge pull request #9762 from tswarmerdam-mx/single-agents-how-to-new
How to Build an Agent + Prompt Engineering update
2 parents 0384130 + 45e5a5c commit 9ec18a0

File tree

19 files changed

+951
-533
lines changed

19 files changed

+951
-533
lines changed

content/en/docs/marketplace/genai/_index.md

Lines changed: 9 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -40,27 +40,27 @@ If you are new to GenAI, follow the steps below:
4040

4141
## Architecture and Components {#architecture}
4242

43-
To help you get started, the following sections list the available GenAI components and models.
43+
Supercharge your applications with Mendix's Agents Kit. This powerful set of components puts cutting-edge GenAI capabilities at your fingertips, helping you make your Mendix apps smarter. Explore our collection of components and models as listed on this page. Please note that the toolkit supports the full spectrum of generative AI implementations, from straightforward text generation to complex agentic AI.
4444

45-
### Mendix Components
45+
### Mendix Components
4646

4747
| Asset | Description | Type | Studio Pro Version |
4848
|-------------------|---------------------------------------------------|----------------------------------|------------|
49+
| [Agent Builder Starter App](https://marketplace.mendix.com/link/component/240369) | See an example of how to build an agentic Mendix app. Use the Agent Builder from Agent Commons to build your support assistant. | Starter App | 10.21 |
50+
| [Agent Commons](/appstore/modules/genai/genai-for-mx/agent-commons/) | Build agentic functionality using common patterns in your application by defining, testing, and evaluating agents at runtime. | Common Module | 10.21 |
4951
| [AI Bot Starter App](https://marketplace.mendix.com/link/component/227926) | Lets you kick-start the development of enterprise-grade AI chatbot experiences. For example, you can use it to create your own private enterprise-ready ChatGPT-like app. | Starter App | 10.21 |
52+
| [Amazon Bedrock Connector](/appstore/modules/aws/amazon-bedrock/) | Connect to Amazon Bedrock. Use Retrieve and Generate or Bedrock agents. | Connector Module | 10.21 |
5053
| [Blank GenAI App](https://marketplace.mendix.com/link/component/227934) | Start from scratch to create a new application with GenAI capabilities and without any dependencies. | Starter App | 10.21 |
51-
| [GenAI Showcase App](https://marketplace.mendix.com/link/component/220475) | Understand what you can build with generative AI. Understand how to implement the Mendix Cloud GenAI, OpenAI, and Amazon Bedrock connectors and how to integrate them with the Conversational UI module. |Showcase App | 10.21 |
52-
| [RFP Assistant Starter App / Questionnaire Assistant Starter App](https://marketplace.mendix.com/link/component/235917) | The RFP Assistant Starter App and the Questionnaire Assistant Starter App leverage historical RFPs (or question-answer pairs) and a continuously updated knowledge base to generate and assist in editing responses to RFPs, offering a time-saving alternative to manually finding similar responses and enhancing the knowledge management process. | Starter App | 10.21 |
53-
| [Support Assistant Starter App](https://marketplace.mendix.com/link/component/231035) | Learn how to combine common GenAI patterns, such as function calling and RAG to build your support assistant. Connect it to a model like Anthropic Claude via Mendix Cloud GenAI or Amazon Bedrock or use an (Azure) OpenAI subscription. | Starter App | 10.21 |
54-
| [Agent Builder Starter App](https://marketplace.mendix.com/link/component/240369) | See an example of how to build an agentic mendix application. Use the Agent Builder from Agent Commons to build your support assistant. | Starter App | 10.21 |
54+
| [Conversational UI](/appstore/modules/genai/conversational-ui/) | Create a Conversational UI or monitor token consumption in your app. | UI Module | 10.21 |
5555
| [GenAI Commons](/appstore/modules/genai/commons/) | Common capabilities that allow all GenAI connectors to be integrated with the other modules. You can also implement your own connector based on this. | Common Module | 10.21 |
56-
| [Agent Commons](/appstore/modules/genai/genai-for-mx/agent-commons/) | Build agentic functionality using common patterns in your application by defining, testing, and evaluating agents at runtime. | Common Module | 10.21 |
56+
| [GenAI Showcase App](https://marketplace.mendix.com/link/component/220475) | Understand what you can build with generative AI. Understand how to implement the Mendix Cloud GenAI, OpenAI, and Amazon Bedrock connectors and how to integrate them with the Conversational UI module. |Showcase App | 10.21 |
5757
| [MCP Server](https://marketplace.mendix.com/link/component/240380) | Make your Mendix business logic available to any agent in your enterprise landscape with the Mendix MCP Server module. Expose reusable prompts including the ability to use prompt parameters. List and run actions implemented in the application as tool. | Common Module | 10.21 |
58-
| [Conversational UI](/appstore/modules/genai/conversational-ui/) | Create a Conversational UI, manage prompts or monitor token consumption in your app. | UI Module | 10.21 |
5958
| [Mendix Cloud GenAI Connector](/appstore/modules/genai/mx-cloud-genai/MxGenAI-connector/) | Connect to Mendix Cloud and utilize Mendix Cloud GenAI resource packs directly within your Mendix application. | Connector Module | 10.21 |
6059
| [OpenAI Connector](/appstore/modules/genai/openai/) | Connect to (Azure) OpenAI. | Connector Module | 10.21 |
61-
| [Amazon Bedrock Connector](/appstore/modules/aws/amazon-bedrock/) | Connect to Amazon Bedrock. Use Retrieve and Generate or Bedrock agents. | Connector Module | 10.21 |
6260
| [PgVector Knowledge Base](/appstore/modules/genai/pgvector/) | Manage and interact with a PostgreSQL *pgvector* Knowledge Base. | Connector Module | 10.21 |
61+
| [RFP Assistant Starter App / Questionnaire Assistant Starter App](https://marketplace.mendix.com/link/component/235917) | The RFP Assistant Starter App and the Questionnaire Assistant Starter App leverage historical question-answer pairs (RFPs)) and a continuously updated knowledge base to generate and assist in editing responses to RFPs. This offers a time-saving alternative to manually finding similar responses and enhancing the knowledge management process. | Starter App | 10.21 |
6362
| [Snowflake Showcase App](https://marketplace.mendix.com/link/component/225845) | Learn how to implement the Cortex functionalities in your app. | Showcase App | 10.21 |
63+
| [Support Assistant Starter App](https://marketplace.mendix.com/link/component/231035) | Learn how to combine common GenAI patterns, such as function calling and RAG to build your support assistant. Connect it to a model like Anthropic Claude via Mendix Cloud GenAI or Amazon Bedrock or use an Azure OpenAI subscription. | Starter App | 10.21 |
6464

6565
Older versions of the marketplace modules and GenAI Showcase App are available in Studio Pro 9.24.2.
6666

content/en/docs/marketplace/genai/concepts/_index.md

Lines changed: 8 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -92,7 +92,7 @@ In this case you will have to index and store your knowledge yourself, and index
9292

9393
An example of how this can be done with OpenAI is described in [RAG Example Implementation in the GenAI Showcase App](/appstore/modules/genai/rag/).
9494

95-
## The ReAct Pattern (Function Calling) {#react}
95+
### The ReAct Pattern (Function Calling) {#react}
9696

9797
Another way to provide the LLM with additional information and capabilities is to use function calling, also known as tool use. With function calling you can make specific microflows available to the LLM. While evaluating the prompt, the LLM will, optionally, ask to execute a particular microflow. The Mendix application will execute this microflow and return additional information for the LLM to add to the prompt being processed.
9898

@@ -102,8 +102,13 @@ See [Function Calling](/appstore/modules/genai/function-calling/) for more infor
102102

103103
This pattern is supported both by [OpenAI](https://platform.openai.com/docs/guides/function-calling) and [various models available on Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html#conversation-inference-supported-models-features).
104104

105+
105106
## Agents and Assistants {#agents}
106107

107-
Some vendors of generative AI solutions have the concept of an "Agent" or "Assistant" which can combine prompts, RAG, and ReAct in a single call. You can also specify multiple steps which the agent should follow, and ask the agent to create the prompts or API calls needed for those steps.
108+
The agent concept combines prompts, RAG (Retrieval Augmented Generation), and ReAct patterns in a single call. These components of agent-based logic are all supported by our Agents Kit. Using LLMs, business logic can be enriched by enabling AI agents to reason and autonomously execute actions while being grounded in domain-specific knowledge. With Mendix's Agents Kit, agents become a seamless part of your application's logic.
109+
110+
For an overview of the components that help you get started, refer to [the Agents Kit overview](/appstore/modules/genai/#architecture).
111+
112+
In addition, you can integrate agentic behavior in a Mendix app by leveraging external agents through cloud infrastructure providers. In this case, the Mendix app does not store the agent definition. Instead, it only calls the external agent. For example, [Agents for Amazon Bedrock](https://aws.amazon.com/bedrock/agents/) provides this functionality for Amazon Bedrock. You can find out how to use this in your Mendix application in [Invoking an Agent with the InvokeAgent Operation](/appstore/modules/aws/amazon-bedrock/#invokeagent) section of the *Amazon Bedrock* module documentation.
113+
108114

109-
For example, [Agents for Amazon Bedrock](https://aws.amazon.com/bedrock/agents/) provides this functionality for Amazon Bedrock. You can find out how to use this in your Mendix application in [Invoking an Agent with the InvokeAgent Operation](/appstore/modules/aws/amazon-bedrock/#invokeagent) section of the *Amazon Bedrock* module documentation.

content/en/docs/marketplace/genai/concepts/agents.md

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -65,6 +65,10 @@ Start from the [Agent Builder Starter App](https://marketplace.mendix.com/link/c
6565

6666
Read more about [Agent Commons](/appstore/modules/genai/genai-for-mx/agent-commons/) in the GenAI reference guide.
6767

68+
### GenAI Showcase App
69+
70+
Check out example implementations of the previously mentioned patterns and multi-agent systems in the [GenAI Showcase App](https://marketplace.mendix.com/link/component/220475).
71+
6872
### Additional Information
6973

7074
Read the blog post on [Multi-agent systems in a Mendix app](https://www.mendix.com/blog/how-multi-agent-ai-systems-in-mendix-can-train-you-for-a-marathon/)

content/en/docs/marketplace/genai/how-to/_index.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -36,7 +36,7 @@ Generative Artificial Intelligence (GenAI) transforms business applications, emp
3636

3737
* Basic documentation on [GenAI Concepts](/appstore/modules/genai/get-started/) is an essential resource for anyone beginning their GenAI journey.
3838
* The [GenAICommons](/appstore/modules/genai/genai-for-mx/commons/) module as a prerequisite for all GenAI components.
39-
* The [ConversationalUI](/appstore/modules/genai/conversational-ui-module/conversational-ui/) module that offers UI snippets for chat, token consumption monitoring and prompt management.
39+
* The [ConversationalUI](/appstore/modules/genai/genai-for-mx/conversational-ui/) module that offers UI snippets for chat, token consumption monitoring and prompt management.
4040
* The [Mendix Cloud GenAI Resource Packs](/appstore/modules/genai/mx-cloud-genai/resource-packs/) to learn how to quickly access GenAI capabilities from a Mendix app.
4141
* The [OpenAI](/appstore/modules/genai/openai/) provides essential information about the OpenAI connector.
4242
* The [Amazon Bedrock](/appstore/modules/aws/amazon-bedrock/) provides key information about the AWS Bedrock connector.

0 commit comments

Comments
 (0)