AI Systems That Run The Work
AGENRYX
All case studies
Live client systemAI & Automation

Quartz Project Services

A Teams assistant grounded in the firm's SharePoint library

Leo AI answers project questions and generates working documents inside Microsoft Teams by searching the construction firm's own SharePoint files.

Live system map
Quartz Project Services

How the work moves

One connected path from request to result.

Client

Quartz Project Services

Agenryx system

AI & Automation

Operating change

Staff ask in Teams and receive a grounded answer in the same thread

Live

Client system operating in Microsoft Teams

2

Independently deployable services

1

Grounded SharePoint search tool

01 · The challenge

What the client needed to resolve

The problem before Agenryx.

Project knowledge and templates live across a large SharePoint library. Finding the right source, reading it and turning it into a useful draft interrupts delivery teams and produces inconsistent starting documents.

The change

From bottleneck to working system.

Before

Manual and fragmented

Project knowledge and templates live across a large SharePoint library. Finding the right source, reading it and turning it into a useful draft interrupts delivery teams and produces inconsistent starting documents.

Agenryx built

One connected workflow

A two-service Railway deployment: a Node and TypeScript Teams bot plus a Python and FastAPI MCP server, each containerised independently and joined by a local Compose setup for development and diagnosis.

Resolved

A clearer way to operate

Staff ask in Teams and receive a grounded answer in the same thread

02 · What we built

The system behind the experience.

Architecture and workflow

A Teams webhook calls a separate MCP service. That service searches and fetches SharePoint content through Microsoft Graph, gives the retrieved material to a headless document agent and returns the answer or generated file links to the originating thread.

What shipped or was designed

A two-service Railway deployment: a Node and TypeScript Teams bot plus a Python and FastAPI MCP server, each containerised independently and joined by a local Compose setup for development and diagnosis.

03 · Product walkthrough

See how the workflow moves.

Select a step or let the walkthrough advance automatically.

agenryx.system/quartz-leo-ai
System in action

The work enters one clear workflow

Project knowledge and templates live across a large SharePoint library. Finding the right source, reading it and turning it into a useful draft interrupts delivery teams and produces inconsistent starting documents.

One source of truth
Clear ownership
Visible status

04 · What changed

The value is in the operating change.

Staff ask in Teams and receive a grounded answer in the same thread

Document requests reuse the firm's own SharePoint templates

Generated files return through signed download links instead of email attachments

Technology used

Microsoft TeamsSharePointMicrosoft GraphMCPFastAPITypeScript

Start with what you need

What would you like us to build or improve?

Next case study: Fromental