Clean spend data and sized savings, not another dashboard-only BI tool.
Spend Intelligence classifies messy card and invoice lines, highlights spend that bypasses contracts, generates evidence-backed savings opportunities, and answers questions like “top suppliers in Engineering last quarter” with tables and charts.
How it works
The same pipeline you see in the live module, step by step.
- 1
Ingest 12 months of spend
Load departmental spend with channels, suppliers, categories, and on-contract flags from your procurement record.
- 2
Classify unlabeled lines
Apply supplier category, description keyword maps, and confidence scores; Stellitron Intelligence reviews low-confidence rows.
- 3
Detect leakage
Find tail suppliers, off-contract buys where a contracted catalog item exists, and consolidation candidates in crowded categories.
- 4
Size opportunities
Estimate redirect, harmonization, and escalation exposure with formulas you can audit in the trace.
- 5
Answer in plain language
Parse intent for totals, trends, top-N, and breakdowns; return narrative, table, and chart spec.
Checks and rules
Deterministic logic runs on every action; optional AI enriches text when configured.
- Keyword map: travel, IT hardware, cloud, logistics, marketing services
- Tail spend redirect to contracted supplier catalog
- Off-contract rows where category has contracted items
- Consolidation when three or more suppliers share a category
- Payment terms harmonization on high-spend suppliers
- Price escalation exposure from active contract clauses
What you get
Artifacts land in the shared procurement record and activity log.
- Reclassified spend lines with confidence
- On-contract percentage and unclassified dollars
- Savings opportunity list with evidence and actions
- Charts filtered by department, category, and channel
- Copilot answers with query plan chips
Where teams use Spend Intelligence
Questions
Does it need my ERP?
The live demo runs on a shared procurement record (requests, POs, receipts, invoices, contracts, and spend). In production you connect your ERP or AP system via API or scheduled file exchange so matching uses your real PO and goods-receipt data. Until then, every rule runs the same way on the demo dataset.
Does it depend on an AI model to work?
No. Every decision runs through Stellitron's deterministic rules first: tolerance math, playbook comparisons, weighted bid scoring and classification maps, so results are repeatable and auditable. Stellitron Intelligence adds document reading, drafting and plain-language explanations on top, and the agents keep working if it is unavailable.
Who approves?
Agents recommend and trace; people approve. Intake routes to managers, category owners, Finance, and the CPO by amount and category. Invoices on exception stay on hold until AP approves, requests a credit note, or rejects a duplicate. Contracts, sourcing awards, and supplier blocks follow your owners in the app — the agent surfaces the evidence, not the signature.
Why is there no document upload for Spend?
Spend Intelligence works on transactional history already in your procurement record. Use Intake, Invoice, or Sourcing trials for document upload; Spend connects once those feeds exist.
How are savings estimates calculated?
Each opportunity type uses a documented formula — for example tail redirect applies a contracted discount assumption, consolidation uses a share of non-leader spend, and payment harmonization uses working-capital math. You can dismiss or launch sourcing from each row.