Every clause scored against your playbook, not a generic risk label.
Paste or upload agreement text and the Contract Agent segments clauses, extracts numbers (notice days, caps, escalators, SLA), compares each position to Stellitron’s playbook, suggests redlines, and tracks renewal and notice deadlines on active agreements.
How it works
The same pipeline you see in the live module, step by step.
- 1
Segment and classify
Split the agreement into clauses by type: renewal, liability, payment, escalation, SLA, data protection, governing law, and more.
- 2
Extract terms
Pull notice periods, liability cap months, annual escalator percentages, net payment days, and SLA targets from the text.
- 3
Score vs playbook
Rate each clause low through critical based on your standard positions — for example escalator above 3% or cap under 12 months of fees.
- 4
Propose redlines
Generate suggested replacement language for medium- and high-risk clauses with word-level diff against the original.
- 5
Track renewals
Surface end dates, auto-renew flags, and notice deadlines; draft renegotiation or non-renewal letters when windows are active.
Checks and rules
Deterministic logic runs on every action; optional AI enriches text when configured.
- Annual price escalator vs 3% playbook cap
- Liability cap vs 12 months of fees
- SLA uptime vs 99.9% target
- Renewal notice period vs 60-day playbook
- Payment terms shorter than Net 45
- Missing termination for convenience or data-protection clause on SaaS
What you get
Artifacts land in the shared procurement record and activity log.
- Clause cards with risk level and playbook position
- Redline suggestions with accept or dismiss
- Contract risk score (0–100)
- Obligation checklist with owners and due dates
- Renewal notice drafts with clause references
Where teams use Contract Agent
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.
Where does the playbook come from?
The demo ships with Stellitron’s sample negotiating positions (escalators, caps, notice, SLA). In deployment you replace those rules with your legal and procurement standards; scoring and redlines follow the same engine.
Does it replace legal review?
No. It prioritizes what to read first, documents why a clause is high risk, and drafts starting language. Counsel and procurement still decide what to sign.