Agent Overview

Agent Name: Geotab Ace

Goal: Deliver customized fleet data insights using natural language

Version: 0.6.0-rc7 on production

Base Model: Gemini-1.5-pro (Official model card)

Developed By: Geotab AI Engineering team

Date of Release: February 2025

How can I use this product? Ace is embedded in MyGeotab. Also, as an end user you just have to:

  • Log into MyGeotab
  • Go to the beta features tab under Options
  • Switch the Ace Beta feature on and click Save on top
  • Go to the side navigation and find Ace
  • Start using 🤓
Intended Use

Geotab Ace is a Generative AI (GenAI) assistant that enables users to interact with complex fleet datasets through natural conversation, democratizing data access by removing technical barriers.

Target users: Fleet managers with access to MyGeotab.

Out-of-scope uses: This system will only answer questions and give information related to fleet management.

Supported languages: All languages supported by Gemini (list).

Features

Purpose-built for fleet management: Integrated with the MyGeotab platform, Ace allows fleet managers to access performance data and actionable insights through simple conversations.

Automated SQL generation and data retrieval: Ace translates natural language questions into precise SQL queries for Google BigQuery, delivering customized information that meets each user's specific needs.

Context-aware retrieval: The agent prioritizes retrieving relevant, up-to-date information directly from the user's fleet database rather than relying solely on pre-trained knowledge.

Agent Description

Inference Process

Query processing: When a question is received from the user, it passes through the embedding model to generate a vector representation. This vector is used to search the Vector Database for a semantically similar question, its SQL query, interpretation, and category. If the user's question is irrelevant to fleet management, the large language model does not generate a SQL query.

Context Enhancement: The system combines the original question with the relevant retrieved examples to create enriched context. This combined information is then sent to the large language model (LLM) for SQL query generation.

Iterative Refinement: The generated SQL query created by the LLM is sent to Google Big Query (GBQ) for execution. If an error occurs, the system re-prompts the LLM with the error information and attempts again, continuing this process until successful data retrieval occurs.

Logging: All interactions, queries, and system operations excluding the customer's data are recorded in the logging database for monitoring, debugging, and analytical purposes.

Core components

AI Foundation: The agent is built around Google's Gemini 1.5 Pro AI, which processes natural language and converts it to SQL queries. Rather than modifying the AI model itself, the system leverages it within a Retrieval Augmented Generation (RAG) framework to enhance performance and accuracy.

Vector Database: Contains 343 frequently used fleet management questions with corresponding fields: Question text, Reference SQL query, Interpretation details, and Category classification

Embedding Model: A fine-tuned version of OpenAI's text-embedding-002 converts questions into vector representations, enabling semantic matching between user queries and the sample database.

Google Big Query: Serves as the primary data repository for all fleet information. The system sends generated SQL queries to Big Query, which executes them and returns relevant fleet data.

Firestore: Functions as the conversation storage system, maintaining records of user questions within each session, generated SQL queries, and query execution results

Data as a Service (DaaS): Geotab's DaaS platform provides the distributed infrastructure backbone for the system. This enables the application to operate across multiple computing environments while maintaining consistency and performance.

GenAI Gateway: Geotab's centralized Generative AI platform provides standardized API access to various Large Language Models (LLMs). This gateway facilitates seamless integration of AI capabilities into Geotab's product ecosystem and development workflow.

Orchestration Service: Coordinates the overall workflow between system components, ensuring proper sequencing of operations.

Data sources

Geotab's data that Ace can access includes:

Vehicle Identification and Grouping:
  • Which vehicles belong to which groups or categories.
  • Basic information about each vehicle, such as its display name and most recent activity.
Vehicle Performance:
  • Distance traveled.
  • Driving time.
  • Fuel or energy consumption.
  • Other details specific to electric vehicles.
Vehicle and Fleet Safety:
  • Harsh driving events (e.g. sudden braking).
  • The likelihood of collisions.
  • How safe a vehicle or fleet is compared to similar ones.
  • Suspected vehicle collisions.
Detailed Vehicle Diagnostics:
  • All possible measurements and readings that the vehicle's systems can provide.
  • Which component of the vehicle is reporting each measurement.
  • What type of failure a measurement represents.
  • The actual recorded measurements.
  • Fault data, and exception events.
Electric Vehicle (EV) Specifics:
  • Which vehicles are electric (including different types such as hybrids and fully electric).
  • Summarization of driving data for plug-in electric vehicles, segmented by ignition-based trips.
  • Assessment of how suitable non EV vehicles are for replacement with EV's.
  • EV charging data, including when and where vehicles are charged.
Rules and Exceptions:
  • Rules that have been set on MyGeotab (e.g. seatbelt must be fastened while ignition is on)
  • Exceptions occur when a rule (predefined or custom) has been broken (e.g. seatbelt is not fastened despite ignition being on)
Driver Data:
  • Driver identification number in the database, driver's full name, and activation period, and their timezone.
  • Number of trips, duration of trips, distance traveled, stop duration, etc. for each driver on a daily basis.
  • All the groups each driver is in.
  • Driver-level crash risk predictions, benchmarks and ranks. (Predictions are made based on the most recent 7 days.)

Technical specifications

Deployment Environment: Cloud-based, DaaS

Updates and Maintenance Plan: Weekly on Thursdays

Recommended Hardware: 4 vCPUs, 14GB RAM

Scaling Support: Ace supports horizontal scaling with Kubernetes clusters

Constraints & limitations

Data Access: Currently, Ace does not have access to geospatial data.

Knowledge Constraints: Ace is intentionally constrained to content relevant to fleet management.

Chat History: Currently, chat history is not available for the user to view.

Response Speed: The average response time for a predefined question is about 10 seconds. This increases to 36 seconds for questions that are not predefined.

UI Limit: Text input cannot exceed 500 characters for one message.

Responsible AI Considerations

Explainability and transparency

The agent generates its chain-of-thought, reasoning process, and SQL query to the user. This documentation and the Ace Whitepaper are efforts towards Geotab's commitment to transparency in its responsible AI practices.

User controls and safeguards

Guardrails have been added to restrict irrelevant topics to fleet management and enforce compliance. The RAG-based architecture grounds the responses as much as possible to prevent hallucination. Responses are filtered to reduce harmful outputs, using Gemini's built-in safety filters. Audit logs track and review generated responses for quality control.

Proprietary and user data handling

Ace, as an agent, is responsible for generating and executing queries. Although users receive answers based on their own data, Ace does not have access to it. Results are stored in a bucket with access granted solely to the user interface for display to the customer. User data is not sent to any third party large language model, and is exclusively handled within Geotab's systems.

Evaluation Metrics

Relative relevancy

This metric indicates how closely the LLM-generated SQL query aligns with the expected query.

Execution score

Evaluates the performance of our SQL generation by comparing the results of the generated queries against the expected query results. The score considers both the accuracy of the data retrieved (matching rows and columns) and the completeness of the results (missed or additional rows).

Table match accuracy

Shows how accurately the LLM-generated SQL queries match the correct database tables. It directly measures the SQL's success in targeting the correct tables based on the input query.

Number of SQL attempts

Tracks the number of SQL queries the LLM generated before producing a final result. A higher number of attempts could indicate difficulty in understanding or constructing the correct query.

Feedback

Feedback Mechanism: Users can provide feedback on the Ace interface using a thumbs-up or thumbs-down rating system. The AI Engineering group performs a weekly manual analysis of the feedback.