In order to optimize the accuracy of an answer that an LLM generates, the inputs the LLM receives must be refined for comprehension. The clearer and more understandable the query, the better the output.

Specification

• 1.1

  Check for safety and relevance

• 1.2

  Optimize query comprehension

• 1.3

  Check for Workflows automation

• 1.4

  Check for Custom Answer

Once a query has been checked and optimized the next stage is to generate a response using the LLM. For this task, the Fin AI Engine™ has been designed to use a bespoke and enhanced retrieval augmented generation architecture (RAG for short).

Specification

• 2.1

  Optimize retrieval

• 2.2

  Integrate and augment

• 2.3

  Generate response

In the final step of the process, the Fin AI Engine™ performs checks to understand whether the output from the LLM meets the necessary response accuracy and safety standards.

Specification

• 3.1

  Validate the response

• 3.2

  Respond to customer

To calibrate and enhance engine performance, the Fin AI Engine™ has advanced integrated tools that help optimize answer generation, efficiency, precision, and coverage.

Specification

• 4.1

  Fin customization and control

• 4.2

  AI analytics and reporting

• 4.3

  AI recommendations

Intercom has implemented state-of-the-art security measures to protect Fin against a wide range of LLM threats, including those identified by the OWASP LLM Top 10. By consistently testing a variety of high-end LLMs, and deploying rigorous internal controls, security protocols, and safeguards, Fin is able to achieve the highest level of security and reliability while avoiding potential limitations and threats.

Specification

• 5.1

  Fin AI Security

• 5.2

  Regional hosting

• 5.3

  Compliance
• 5.4

  Third-party LLM data usage, transfer and storage