supplyceLog in
AGENTIC PROCUREMENT

Procurement that runs itself.
Under your control.

supplyce is an agent fleet for source-to-pay. Named agents handle intake, sourcing, negotiation and invoicing inside guardrails you set — every action audited, priced and reversible.

13
named agents
0–6
autonomy ladder
30+
MCP tools
7
self-driving demos
RUNS ON YOUR STACK — NO RIP-AND-REPLACE
Two-way ERP syncMicrosoft Teams & CopilotMCP · Claude / ChatGPT / CopilotPunchOut · cXML + OCIE-signatureSSO · SCIM · MFA
THE PLATFORM

One loop, source to pay.

Eight areas, one governed flow — agents do the work, your policies decide what needs a human.

Intake

Describe it. It's a requisition.

Free text, an emailed quote or an uploaded PDF becomes a structured, policy-checked request — with per-field confidence you can see.

Catalog & Punchout

Buy from catalogs you control.

Hosted catalogs with carts and preferred-supplier controls, plus real PunchOut round-trips over cXML and OCI.

Sourcing & e-Auctions

Run competitive bids in minutes.

AI-drafted RFx with weighted scoring and award recommendations; live reverse auctions with anti-snipe protection.

Autonomous Negotiation

Let the agent haggle.

Round-by-round negotiation inside your target and walk-away limits — with a dry-run simulator and a full transcript.

Suppliers & Risk

Know every supplier. Watch every risk.

360° records, onboarding gates, maker-checker bank changes, continuous sanctions/PEP screening and 4th-party concentration maps.

Contracts

Contracts that read themselves.

Clause extraction against your playbook, e-signature lifecycle, obligations that become tasks, renewals that never surprise you.

Invoices & Payments

Touchless from PO to payment.

Three-way match with tolerances, duplicate detection, payee re-screening before money moves, payment runs with full audit.

Spend Analytics

Ask your spend a question.

A governed spend cube with natural-language queries, savings pipelines with verification, budgets that actually block.

THE FLEET

Meet the agents.

Thirteen named agents in three classes — autonomous where the blast radius is small, collaborative where judgment matters, ambient where vigilance never sleeps.

Autonomous

Act within hard boundaries — negotiation rounds, clean-invoice clearing, tactical sourcing.

Collaborative

Prepare and recommend — approval briefs, award scoring, contract analysis. You decide.

Ambient

Watch continuously — risk screening, renewals, budget sweeps. They wake you only when it matters.

13 NAMED AGENTS
Intake AgentTriage AgentSourcing AgentNegotiation AgentAward AgentApproval AgentContract Analyst AgentOnboarding AgentScreening AgentRisk AgentRenewal AgentSpend Analyst AgentSupplier Care Agent

Autonomy with brakes.

Autonomy Ladder 0–6

A per-action dial from 'disabled' to 'execute'. You set the floor, per agent, per category.

Kill-switch & run caps

Any agent, any tool — off in one click. Daily run caps and cost budgets enforce restraint.

Honest economics

Every run shows its model, tokens and real dollar cost. Simulated output is always labeled sim.

EVERY RUN, PRICED:⚡ claude-sonnet · via OpenRouter1,842 tokens$0.03executed
GOVERNANCE

Built so you can prove it.

Four named primitives make agent autonomy auditable — not a promise, a mechanism.

Action Tokens

Agents cannot write to your systems of record without a workflow-issued token. No token, no write — enforced in the write path.

Tamper-evident Audit

Every action lands in an append-only, hash-chained audit log per tenant — searchable and exportable.

Agent Evals

A golden-dataset regression gate scores every agent, re-runnable live from the console. Agents that grade themselves.

Run Traces

Every agent run is a URL: plan, tool calls, confidence, tokens and cost. Trust what you can trace.

Plus the enterprise baseline: multi-tenant isolation, RBAC + fine-grained authorization, SSO (OIDC), SCIM, MFA, maker-checker on sensitive changes, segregation of duties, EU (Frankfurt) hosting. SOC 2 and ISO 27001 certifications are on our roadmap.

SEE IT RUN

The platform demos itself.

Seven self-driving walkthroughs drive the real product — real routes, real clicks, real agents, honest model and cost chips. Nothing staged.

~7 min

A day run by agents

The flagship: a full day of procurement where a human decides exactly twice.

~5 min

Supplier discovery

The agent searches the open web, runs outreach, reads replies, recommends. You convert.

~4 min

Autonomous negotiation

A bounded haggle inside human guardrails that banks real savings.

~4 min

Sourcing RFx

A competitive bid scored by the agent — price, delivery, quality, risk.

~3 min

TPRM sentinel

The risk agent that never sleeps: sanctions, PEP, adverse media, 4th parties.

~3 min

Fleet evals

Agents graded against golden datasets, re-run live. Green means trusted.

~4 min

Touchless 3-way match

A clean invoice clears itself; a price variance is caught and explained.

GET IN TOUCH

See supplyce on your own spend.

Tell us about your procurement flow — we'll run a real request through the agent fleet and show you every decision it makes.

OR WRITE TO CONTACT@VERTICALISE.COM