How Beghou Slashed Configuration Time 10x With AI

Beghou's engineers hand-edited 100+ metadata tables to make simple changes. An AI copilot now turns plain-language requests into validated SQL — configuring instances 10x faster.

10x

Faster to configure Arc instances

Implementation Time

Chris Taylor

CEO & Co-Founder

Fractional AI

Connect ↓

The Challenge

Beghou Arc instances are programmatically generated from 100+ interrelated metadata tables spanning 1,500+ columns. That flexibility meant even simple additions, like a search bar, required complex manual engineering across multiple tables and foreign keys, creating a scalability bottleneck as the client base grew.

What They Built

Fractional AI built an AI-powered copilot for Beghou Arc that translates natural-language configuration requests into validated SQL proposals. Engineers keep full control by reviewing every change before execution, while the copilot handles the most repetitive work.

A FastAPI service integrated with Arc's UI runs a low-latency GPT-4-mini agent with a read-only query tool to prevent unintended modifications. Metadata about the current page, grid, and datasource is dynamically assembled as context, and a containerized environment using MSSQL snapshots enables non-destructive regression testing. Temperature tuning (1.0 to 0.4) and parallel tool calling improved accuracy and cut reasoning steps.

AI Role

The copilot interprets an engineer's natural-language request, gathers live metadata about the current Arc page, grid, and datasource, and proposes validated SQL to make the change. A read-only query tool prevents unintended modifications, and the engineer reviews and approves every statement before it executes.

AI Model

FastAPI backend, GPT-4-mini agent, MSSQL, XML-based system prompts with execution traces, containerized MSSQL-snapshot evaluation environment

Infrastructure

Beghou Arc platform (100+ metadata tables, 1,500+ columns) • MSSQL database • FastAPI service integrated with the Arc UI • Containerized MSSQL-snapshot environment for regression testing

Integration Points

FastAPI service wired into the Arc UI • Read-only SQL query tool against the Arc metadata database • Dynamic assembly of page/grid/datasource metadata as agent context • Containerized MSSQL snapshots for non-destructive regression testing

Impact

Up to 10x faster configuration

Configuration tasks complete up to 10 times faster, in minutes rather than hours or days.

~50% fewer errors

Error rates fell by roughly 50% through temperature tuning from 1.0 to 0.4.

Fewer reasoning steps

Parallel tool calling cut reasoning steps from 6-7 down to 2-3 per request.

Technology Utilized

Implementation Complexity

Time Savings

Best Fit For

Best fit for software or platform teams whose highly configurable products require slow, manual database or metadata engineering for routine changes.

Chris Taylor

CEO & Co-Founder

Fractional AI

CEO & Co-Founder of Fractional AI, helping PE firms and portfolio companies implement AI workflow automations, product features, and diligence at scale.

Get an intro

Industry:

Healthcare & Life Sciences

Business Function:

Product & Engineering

Company Size:

Project Cost:

Cost not disclosed

Ownership:

Organization Type:

AI Pattern:

AI-Accelerated Custom Software

Conversational AI (Chatbot / Agent)

Value Type:

Time Savings

AI Model:

Frequently Asked Questions

How did Beghou make Arc configuration up to 10x faster?

By adding an AI copilot to its Arc platform that turns natural-language configuration requests into validated SQL proposals. A GPT-4-mini agent assembles live metadata context and proposes changes that engineers review before running, cutting configuration from hours or days to minutes - up to 10x faster.

What AI models and tools power Beghou's Arc configuration copilot?

The copilot runs a low-latency GPT-4-mini agent behind a FastAPI service integrated with the Arc UI, with a read-only query tool against the MSSQL metadata database. XML-based system prompts, temperature tuning, and parallel tool calling improved accuracy.

What results did Beghou see from the AI configuration copilot?

Configuration tasks completed up to 10x faster - minutes instead of hours or days - error rates fell by roughly 50% after temperature tuning from 1.0 to 0.4, and parallel tool calling cut reasoning steps from 6-7 to 2-3 per request.

How long did it take to build Beghou's AI copilot?

A specific build timeline was not disclosed. The work included model and temperature tuning and a containerized MSSQL-snapshot environment for non-destructive regression testing before rollout.

Who is this AI configuration copilot approach best for?

It is best suited to software or platform teams whose highly configurable products require slow, manual database or metadata engineering for routine changes.