USE CASE / PROCUREMENT

Streamlining supply chain processes

Using AI to assist with what you buy, who from, commercials, RFPs, T&Cs, who’s RACI, who signs, performance tracking … lots of questions, lots of $.

FUNCTION: PROCUREMENT; INDUSTRY: MANUFACTURING

Supercharge paper based procurement processes

Enterprise and government use considerable resources in the purchasing process. AI can transform this workflow from the internal “we need to buy” trigger to starting performance of the contract.

    • Business Process Improvement project revealed considerable costs, cycle times, delays, errors, rework and value loss in the procurement process.

    • There was often uncertainty about what the business rules were re which person can make decisions about purchase categories and the contracting process.

    • Creating RFIs, RFPs, assessing bids and commercials was manual and often didn’t refer to historical data.

    • Ave 132 total labour hrs per contract until commencement of deliverables, and 11 weeks cycle time.

    • Largely adopt our Consulting approach to fully understand the problem, root causes, goals and relevant data.

    • Look at current state docs, rules and interview people in process re improvement areas.

    • Clean, structure and optimise data.

    • Confirm our hypothesis to solve problem with AI approach.

    • Rapid (<3 days) PoC to stakeholders. Use PoC feedback to iterate. Agile approach minimises risk, ensures tool evolves to meet the genuine user needs.

  • RFI/RFP doc generation & review

    Use public model to assist draft RFI/RFP templates, tailor questions by category, summarise vendor responses and highlight non-compliance.

    Bid response analysis

    Vision LM (VLM) extracts pricing tables, delivery timelines, and compliance statements from vendor submissions automatically.

    Bid assessment

    LLM based classification models trained on historical award data, and then score suppliers on cost, risk, quality, and other defined metrics. Use Power BIfor interactive dashboards.

    Vendor risk analysis

    Expert agentic AI team analyses vendor documents for compliance issues (e.g., sanctions, ESG policies, cyber posture, AML, Chain of Custody etc.) using Hugging Face NER pipelines and GPT-based RAG over vendor data.

    Internal approvals

    Using Power Automate, agentic AI team and Model Context Protocol (MCP) servers to process mine & task automate. Identify bottlenecks, predict approval delays and route workflows dynamically.

    Spend analytics

    Predict spend by category, supplier, or region, detect anomalies or non-compliant spend. Use classical statistical approaches combined with fine-tuned LLM for post-analysis and Power BI.

    Procurement Assistant chatbot

    Retrieval Augmented Generation (RAG) with text embeddings & our custom RAG fine-tuned LLM. E.g. “Show top suppliers by A, B and C.”

    • 70–80% reduction in manual labour from “we need to buy” until contract delivery start.

    • 55% faster cycle times from RFI to contract signed.

    • Full audit trail, risk visibility and decision consistency.

    • Accurate single source procurement spend forecast across whole group.

    • Labour average is 45hrs per contract (down from >130).

    • All FAQs are handled online by Q&A chat with only 12% going to human.

    • App developed to ensure real time data streams.

    • Fully transparent and auditable by functional leaders to inputs, process, outputs, assumptions and trends.

    • All data safely stored in client’s private AI infra tenant.