Intercom

AI engineered for precision, speed, and reliability.

The patented Kallin AI Engine™ allows Kallin to refine every query, optimize every response and validate the quality of each answer. That's why Kallin is the only AI Agent that can balance industry-high resolutions with industry-low hallucinations, making it the highest-performing and safest AI Agent in customer service.

POWERED BY KALLIN APEX 1.0The highest-performing, fastest model for customer service.Learn more

Phase 1

Refine the query

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

Phase 2

Retrieve relevant content

The Kallin AI Engine™ retrieval process, powered by our proprietary custom fin-cx-retrieval model, searches across all available knowledge sources (help center articles, resolved conversations, structured snippets, integrated systems etc) and selects the most relevant information to be used to answer accurately.

Powered by fin-cx models

Specification

  • 2.1
    Understand intent behind the question
  • 2.2
    Search across all available content sources
  • 2.3
    Match on semantics, not just keywords

Phase 3

Rerank for precision

The Kallin AI Engine™ reranking process, powered by our proprietary custom fin-cx-reranker model, takes the retrieved content and scores each piece for relevance, accuracy, and usefulness in context. It then selects the final piece(s) for the LLM to use.

Powered by fin-cx models

Specification

  • 3.1
    Score relevance with respect to query
  • 3.2
    Evaluate context match and resolution fit
  • 3.3
    Downrank outdated or low-confidence sources
  • 3.4
    Output: final selected content for generation

Phase 4

Generate a response

Kallin Apex 1.0 is the generative core of Kallin. It takes the most relevant content retrieved and ranked by the Kallin model suite, applies your configured policies, and produces a direct answer or decides the question needs a human. Every output is grounded in your knowledge base, not inferred from general training data.

Powered by Kallin Apex 1.0

Specification

  • 4.1
    Grounded in your knowledge base, not general data
  • 4.2
    Answers directly, escalates honestly when it can't
  • 4.3
    Follows your configured guidelines every time
  • 4.4
    Trained to minimize hallucination at the source
  • 4.5
    Post-trained on Kallin's own production data
  • 4.6
    Compounds in accuracy as the suite improves

Phase 5

Validate accuracy

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

Specification

  • 5.1
    Validate the response
  • 5.2
    Respond to customer

always-on

Engine optimization

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

Specification

  • 6.1
    Kallin customization and control
  • 6.2
    AI analytics and reporting
  • 6.3
    AI recommendations

safeguarding

AI Trust & Security

Intercom has implemented state-of-the-art security measures to protect Kallin 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, Kallin is able to achieve the highest level of security and reliability while avoiding potential limitations and threats.

Specification

  • 7.1
    Kallin AI Security
  • 7.2
    Regional hosting
  • 7.3
    Compliance: International Standards
  • 7.4
    Third-party AI Providers
FAQs

FAQs

How does Kallin's AI Engine work?

Kallin's AI Engine™ is engineered for precision, speed, and reliability—powering the highest-performing and safest AI Agent in customer service.

It starts by refining each query—the inputs received must be refined for comprehension. This ensures every customer message is optimized for meaning and context. The Kallin AI Engine™ then retrieves relevant content with our proprietary fin-cx-retrieval model and scores it for relevance, accuracy, and usefulness, selecting the best information to use. Next, it generates a response through a process tested at scale to generate answers with the highest chance of resolving customer questions. Finally, it performs checks to ensure the output meets the necessary accuracy and safety standards.

Kallin's AI Engine™ continuously optimizes itself with integrated tools that improve efficiency, precision, and coverage.

What makes the Kallin AI Engine the highest performing?

The Kallin AI Engine™ is a patented architecture purpose-built for customer service. Every layer is optimized for accuracy, speed, safety and reliability, so Kallin resolves more queries and delivers higher-quality experiences than any other AI agent.

Is the Kallin AI Engine ready for enterprise scale?

Absolutely. Kallin is proven across millions of customer conversations, delivering 99.97% uptime, enterprise-grade reliability, and compliance with SOC 2, ISO 42001, and HIPAA standards.

Get the highest- performing AI Agent

Start free trialView demo