Magnet AI Logo

The easiest way to get Gen AI into your CRM

Bring Generative AI powers to your business users to enhance productivity, operational efficiency and customer satisfaction.

 

 

Sign up for a AI workshop to explore the capabilities or get demo access to Magnet AI.

Magnet AI: Key Highlights

Magnet AI is a free and open-source solution that makes it simple for CRM

admins to bring Generative AI capabilities into their systems. 

No-code Configuration

Provides no-code configuration using Admin UI to build, test and evaluate AI features.

Integration with CRM systems

Integrates with Oracle Siebel, Salesforce, RightNow, and Fusion Applications.

Flexible Deployment

Magnet AI can be deployed to your Microsoft Azure, AWS, Oracle OCI or Google Vertex environment, as well as on premise (coming soon!).

How Magnet AI Works

With constant updates from LLM vendors and rapid development in the Gen AI field, it may be hard to keep up with the latest trends.

Understanding the difficulties our customers face with the flood of Gen AI news and the complexities of integrating AI solutions, we have developed an accelerator that brings cutting-edge Gen AI capabilities into your enterprise CRM.

Instruct

Prompt Templates

It all starts with the prompt. Magnet AI enablesIllustration admins to:

  • create prompt templates
  • choose the best-matching LLM or small model from a range of options
  • adjust LLM output diversity and format
  • preview, publish, and update prompt templates.

Prompt templates then become accessible directly via API (for example, to summarize a CRM record) or can be used as building blocks of more complex AI tools (for example, RAG flows).

Ground

Knowledge Sources

Knowledge Sources serve to ground the Gen AI inIllustration trustworthy, curated content aligned with business standards and policies. Supported content sources that can be connected to Magnet AI:

  • Sharepoint (pages, pdfs, videos)
  • Salesforce
  • RightNow
  • Confluence

With just a button click content is embedded into vector store and becomes available for semantic search, which ensures human-like understanding of user’s query.

Configure

RAG Tools

Retrieval-Augmented Generation (RAG) Tools use the power of Prompt Templates andIllustration Knowledge Sources to bring excellent and reliable Q&A experience to end users. Available features:

  • Define the Knowledge Sources that your RAG system can access to ground its answers
  • Control how content is retrieved and ranked
  • Shape response format and tone
  • Optimize LLM response for multilingual use cases
  • Adjust UI settings to ensure the best UX for your users
  • Preview and test before making your RAG tool live.

Assemble

AI Apps

When it’s time to make configured AI solutionsIllustration available for the end users, admins can get things ready for integration with just a few mouse clicks. Available features:

  • Create AI Apps
  • Connect AI tools like RAGs or custom code
  • Preview and test AI Apps before making changes live
  • Get the embed URL to use for integration into your CRM.

In this way AI Apps become ready for integration into Siebel, Salesforce or other CRM. Custom AI solutions developed outside of the Magnet AI ecosystem can also be incorporated into AI Apps via the custom code feature.

Measure

Evaluation

Due to the probabilistic nature of LLM-generated output, it is essential to be able to evaluate and compare produced output, especially in the enterprise CRM domain, where data consistency is critical.

Evaluation feature helps admins test RAG ToolsIllustration and Prompt Templates with sets of test data, so that Gen AI performance can be constantly improved. Available features:

  • Import or manually create test data for evaluation
  • Configure and launch evaluation jobs
  • Quick-launch evaluation from particular RAG Tool or Prompt Template
  • Download and view evaluation results

Automate

Coming soon: Agents

Combine Prompt Templates, RAG tools, andIllustration of the mobile phone and AI robot standing next to configurable API tools to design service-oriented agentic workflows and accelerate task execution from issue categorization to action selection, drafting a customer email and issue post-processing.

Allow human intervention when necessary to ensure optimal control.

Integration Options

Currently, Magnet AI Integrates with Oracle Siebel, Salesforce, RightNow, and Fusion Applications.
Salesforce partner badge
Magnet AI integrated into Siebel
Oracle Partner logo
Magnet AI integrated into Siebel

Take a moment to see Magnet AI

in action

Magnet AI Logo

Can now be deployed to your OCI environment!

We are leveraging Oracle Database 23ai and Oracle Gen AI Services to run Magnet AI in OCI.
Magnet AI can now be deployed to your OCI environment!

Who is involved in Magnet AI development?

Magnet AI is a free, open-source solution promoted and maintained by

a group of end customers, implementation partners and IT enthusiasts:

Ideaport Riga Logo
Siebel Hub Logo
intelligent_advisor
Magia_logo
The CX Consultants Logo

Implementation Costs

These prices are specifically for Azure or OCI resources. If you wish to deploy elsewhere, please contact us to discuss the costs.

Magnet AI

Magnet AI is a free and open-source solution deployed on your Azure or OCI instance

Free

€ 0

Azure or OCI Environment

Cost for running Azure/ OCI resources as such LLM API, vector store, and container app

Starting From

€ 80/month

Initial Consulting

Quick wins use case identification and solution setup delivered by a Magnet AI Partner

Starting From

€ 1500

Sign up for a free Magnet AI Workshop

Discover more of Magnet AI in action

We welcome CRM admins to join Magnet AI Workshop to explore its features and get access to admin area.

Photo of Juris Terauds-Chief Revenue Officer

FAQ

Can Magnet AI be deployed in GCP, AWS, or the private cloud?

Currently, Magnet AI can be deployed to the Microsoft Azure Cloud and Oracle OCI. In the coming months, we plan to make it available on another platforms, depending on the customer's interests. 

How do you integrate with a CRM system?

We integrate in two ways. First, the CRM system can invoke Magnet AI API, providing unstructured or JSON-formatted text as input and receiving the output as JSON. Second, Magnet AI Panel can be integrated into the hosting CRM UI natively or as an iFrame. When it comes to Magnet AI's mini-apps, they can read and update CRM data using standard REST services.

Does Azure OpenAI train on my data?

Azure OpenAI never trains its standard models on the data you pass to it via API. At the same time, the request and response data are stored in Azure for a certain period, and Microsoft employees can review this data to assess potential service abuse. Customers may request Microsoft not to store this data to achieve ZDR (Zero Data Retention). Read more about Azure OpenAI service data, privacy and security here.

Do you fine-tune foundational models?
No, we do not; so far, we have achieved our goals with prompt engineering. If you already have fine-tuned models in your Azure instance, you can leverage them in Magnet AI.
Do you support RAG?

Absolutely! On this webpage, we try to avoid technical terms such as RAG (retrieval augmented generation) and refer to it as Q&A flow or semantic search. While the RAG concept is very straightforward, there are various techniques to improve the results, and we are gradually implementing them in Magnet AI.

Can we develop custom AI mini-apps with specific functionalities unique to our business?
Yes, you can. While developing a specific AI mini-app requires custom coding, Admin UI can help you configure some parts (e.g., RAG and prompt template usage) and access the audit trail logs. Use our RAG, Email Processing, and SR Approver AI mini-apps as a foundation for your custom mini-app. 
Can Magnet AI integrate with other IT solutions or only with mainstream CRM platforms like Salesforce and Siebel?
Yes, you can leverage Magnet AI with other CRM, ERP, HCM or IT systems. See the integration question above for details.
How quickly can Magnet AI be integrated into our existing CRM system?

It depends on your use case. Assuming that you can set up Azure resources and provide access to your knowledge bases and CRM system API without delay, it will take just a couple of days to start testing RAG and prompt templates' API. Implementing and testing custom mini-apps might take from several days to several weeks.

Can we conduct a pilot program or proof of concept before we fully commit to Magnet AI?
Yes, of course. Please get in touch with Ideaport Riga or another Magnet AI implementation partner.
What Large Language Model do you use?

For prompt completion, we use Azure GPT-4 Turbo, GPT-4o, Cohere Command R+, GPT 4o-mini and for embeddings, Azure OpenAI Ada-002. Moving forward, we are enthusiastic about integrating more Cohere models because of their outstanding performance and their availability on both Azure and OCI. LLM space is very dynamic, and we keep monitoring it, paying close attention to Llama, Mistral, and Claude models.

How do you monitor Magnet AI?
We rely on Azure's capabilities to monitor Magnet AI's technical performance. Additionally, we developed the ability to analyse the usage of Q&A/ RAG/ Semantic search functionality and check mini-apps audit trail logs.
Can we use your Azure environment?
Being an ISO27001-certified company, Ideaport Riga is especially concerned about customer data security. Before allowing you to use our Azure environment, we want to understand what kind of data we will process. Usually, using our Azure environment for a POC is fine, but production deployment should be separately agreed.
Can I customise my copy of Magnet AI code or even fork it?
You can, as we have open-sourced Magnet AI under the MIT licence.
What kind of support can we expect after the initial deployment?

We have built Magnet AI Admin UI so that your current CRM administrator or maintenance team can operate it while implementing an increasing number of use cases. While Magnet AI's defects can be reported and most likely will be solved, the MIT licence does not provide any SLA. However, you can request premium support services from Magnet AI implementation partners.

What is the technical stack of Magnet AI?
We both leverage Azure services and have a decent amount of custom code. We wrote our backend in Python and used Vue.js for the front end.