Introduction

What is Motific?

Motific is a Saas platform empowering IT, security, and compliance teams to deliver Generative AI capabilities to their organization’s internal teams with control over sensitive data, security, responsible AI (Artificial Intelligence), and cost. Motific also enables teams to monitor the usage of the GenAI applications in their organization.

With just a few clicks, central-IT and security teams in organizations can provision GenAI assistants and abstracted APIs for Large Language Models, that are customized with Retrieval-Augmented-Generation (RAG) on organizational data sources, for out-of-the-box use or for GenAI applications. Motific includes built-in policy controls:

  • For sensitive data such as personally identifiable information (PII), corporate data and intellectual property.
  • For protection against security risk such as prompt injection, adversarial content and access control.
  • For responsible AI such as content safety.
  • Cost controls such as token budgets to all user inputs and ML model responses flowing through the assistant or abstracted API.

Motific also provides audit trail and key metrics tracking of all user requests for consolidated monitoring.

Who can benefit from Motific?

Motific can benefit any organization wishing to harness the power of Generative AI applications for productivity enhancement, in a secure, trusted and controlled environment.

Key sectors identified as high-imapct beneficiaries of Generative AI are Financial, Healthcare, Marketing and highly data-focused organizations.

Policy and decision makers

The personas like CXOs, VPs and Directors in IT, Security, Compliance, and Data teams who are responsible for business compliance, defining strategic direction to AI deployment, reviewing evaluations of GenAI deployment approaches and approval of GenAI policy controls for the organization can benefit from the PII, content, data loss prevention and security policies that can be defined and applied to apps via Motific.

Administrative users

Central IT, Security and Data Operations teams are responsible for providing employees within the company with access to GenAI services. Their objective is to ensure policy control effectiveness and compliance, fast and frictionless GenAI end-user experience, visibility & analytics of business & operational metrics and security of GenAI connected systems and data, all of which is embedded in Motific.

End-users

Knowledge workers and managers in business functions such as Marketing, HR, Sales, Customer Support, Finance etc., can benefit from Motific’s ability to add data-sources and knowledge bases. These functions can leverage Gen AI assistants to boost productivity in a compliant manner with the backing of their business data.

Application developers

Application developers can use the provisioned abstracted APIs in their business applications to interact with LLMs or RAG configs in a consistent and compliant manner.

Key features

Security and compliance

Personally Identifiable Information (PII) protection

Motific detects, classifies, controls and produces analytics reports on PII entities flagged going in and out of LLMs. The following PII entities can be protected through redaction and blocking: Social Security Number (SSN), Credit card number, Phone number, Physical address, Person name, Email address.

LLM (Large Language Model) security

Prompt injection detection, Data Loss Prevention (DLP), and RAG data poisoning can be detected in prompts and defined actions are taken to mitigate the security risks.

Toxic content prevention

Motific detects, classifies, controls and produces analytics reports on inappropriate and harmful content going in and out of LLMs that violates company’s harmful content policies. The following toxic content categories are prevented from inputs and responses: hate, self-harm, violence, and sexual. Enterprises can identify content prohibitied by their usage policies, and Motific’s inbuilt controls can take appropriate action to warn or block that content.

Cost compliance

Enable cost control mechanisms for individual applications or teams, to enable optimization of LLM usage budgets. The following control mechanisms are implemented in Motific: threshold warnings, suspension of usage, prompt rerouting to cheaper LLMs.

Shadow GenAI detection

Monitor, detect and control usage of unauthorized LLMs and GenAI services using integrations such as Cisco Umbrella solutions.

LLM (Large Language Model) gateway

Motific supports the closed-sourced and open-sourced models. Motific provides hassle free integration with industry leading Large Language Models (LLM) like Azure OpenAI, Mistral and AWS (Amazon Web Services) Bedrock.

Motific is continously adding support for more industry leading models.

Common LLM adapter

Standardized interfaces are provided that integrate all approved LLM models by unifying their APIs and request protocols to enable simplified consumption by enterprise business clients. The LLM Adapter also facilitates the consumption of RAG resources.

LLMs from the following services are supported:

  • Azure OpenAI models
  • Mistral
  • Amazon Bedrock models

LLM access control

Granular definition and access management for each enterprise connected LLM (i.e., third-party or self-hosted) is possible with Motific. It provides access control configurations to control approved integrations and communications between LLMs and other GenAI services by applying rules of connection and communication to approved APIs, IP addresses, data systems, third-party plugins and connectors.

App access control

Definition and enforcement of policies to ensure that only authorized individuals, groups/roles or applications can interact with provisioned vended APIs and assistants.

From an end-user perspective, Motific enables RBAC where the same RAG infrastructure is shared across different individuals and teams.

Prompt intelligence

Motific has a distinctive approach to gathering and presenting information and patterns related to the prompts sent via a Motif to the LLMs. With Motific, you can now accurately measure the time saved by users when they utilize the Gen AI assistant for a task. Time-saving is demonstrated through various tasks that users typically engage in, such as reading, writing, searching, or reviewing for specific details. These metrics allow you to discover how Gen AI assistants enable productivity within your organization.

Moreover, Motific offers model optimization options, allowing you to compare the performance of your chosen AI model with other providers based on parameters like delay, cost, and quality of replies.

Motific provides detailed information in easily understandable graphical representations of prompt trends for tasks that users may perform with the Gen AI assistant, such as brainstorming, content generation, Q&A, and data analysis.

Some of the graphs include:

  • Tasks most frequently requested by users via your Gen AI assistant.
  • Token usage patterns for various tasks, indicating the tasks that consume the most tokens.
  • Gen AI cost trends per task.
  • Time savings per task.

Configuration & Monitoring

  • Policy configurator: Policy definition templates for individual system control plugins to enable definition and review of policies for individual security and compliance controls.

  • Abstracted API console: Abstracted APIs enable teams to connect their GenAI apps with Motific.

  • Testing console: Testing tools (prompt library and accuracy benchmarks), to check the performance of policies applied to newly vended APIs and assistants.

  • Observability dashboard: IT admin dashboard to view real time activity, configure alerts and notifications, generate reports and capture logs. For each of the above visibility and insights mechanisms, Motific provides the following details to the IT administrators with different mixes and matches across some of the following items: Violations of defined policies, input and output tokens used, most utilized LLMs, most active applications.

RAG system

RAG integration in AI assistants and abstracted API for data connectors such as:

  • SharePoint
  • Websites

How does Motific work?

There are two main course of actions that can be taken with Motific by two personas:

  1. Provisioning an assistant or abstracted APIs with LLMs of choice, knowledge bases attached, policy, usage and cost controls by IT-Admin. Provision

  2. Using the assistant by an end user in a compliant manner. user-flow