/ Grounded assistant · Procurement

Grounded procurement knowledge assistant

Designed and productionised a grounded enterprise Procurement assistant on Azure AI Foundry, using LangGraph for orchestration, ChatKit for the interface, PGVector for retrieval and integrations with MCP servers. Answers stay grounded in trusted enterprise documents, and the architecture was standardised into a reusable reference implementation.

/ Context

A Procurement team fielded a high volume of repetitive questions whose answers already existed in trusted enterprise documents. The assistant had to be something the team could rely on operationally, which put grounding and supportability ahead of conversational polish.

/ Role & decision scope

  • Designed the assistant architecture and productionised it.
  • Selected the platform and components: Azure AI Foundry, LangGraph, ChatKit, PGVector and MCP server integrations.
  • Made grounding in trusted enterprise documents the defining requirement.
  • Standardised the architecture into a reusable reference implementation.

/ Constraints

  • Answers have to be grounded in trusted enterprise documents.
  • The assistant had to be productionised, not demonstrated.
  • It needed to be supportable in day-to-day operational use.
  • The architecture had to be reusable beyond Procurement.

/ Architecture & key decisions

  1. D01

    Azure AI Foundry as the delivery platform

    The assistant was built and productionised on Azure AI Foundry, giving one platform for delivery rather than assembling a bespoke stack.

  2. D02

    LangGraph for orchestration

    LangGraph handles the orchestration between retrieval, reasoning and tool use, keeping the assistant's flow an explicit part of the architecture.

  3. D03

    PGVector for retrieval

    Retrieval runs on PGVector over the trusted enterprise document set that grounds the assistant's answers.

  4. D04

    MCP server integrations and ChatKit

    Integrations with MCP servers provide the assistant's access to enterprise systems, with ChatKit as the interface layer.

  5. D05

    Generalised into a reference implementation

    Rather than remaining a Procurement-specific build, the architecture was standardised as a reusable reference implementation for other assistants.

/ Trade-offs

Answer coverage versus grounding discipline
The assistant answers from trusted enterprise documents; grounding was a design priority, so coverage follows the trusted content rather than the model's recall.
Bespoke fit versus reusability
Procurement's content and configuration stay specific while the orchestration, retrieval and integration architecture was standardised into a reference implementation.
Demonstrable versus supportable
Design focus: supportability in day-to-day operational use, which is what productionising the assistant — rather than shipping a prototype — was intended to deliver.

/ Evidence & outcomes

Measured
Reduced inbound procurement support queries by 60%
Artifact
Production Procurement assistant on Azure AI Foundry, LangGraph, ChatKit, PGVector and MCP server integrations
Artifact
Reusable reference implementation standardised from the assistant architecture
Decision
Grounding in trusted enterprise documents as the defining design constraint

/ Related capabilities

/ Next step

Let's talk about the work.

Open to full-time Senior–Staff AI / agent platform roles (remote-friendly), as well as contract and consulting engagements. Response within two business days.