Ingest every signal
Vessel positions, port congestion, EDI, rate feeds, and weather — normalized into one event stream.
AI agents that plan, book, reroute, and reconcile your freight — grounded in your contracts, your carrier history, and the systems you already run.
Every decision ships with its evidence, the options the agent rejected, and a one-click override.
Vessel positions, port congestion, EDI, rate feeds, and weather — normalized into one event stream.
Agents score every feasible plan against your contracts, SLAs, and carrier history.
Book, amend, file, and notify — directly in your TMS, ERP, and carrier portals.
Each result is checked against intent and written back to memory, so the next decision is sharper.
Agents audit every invoice, accessorial, and free-time clock against your contracts — then file the dispute for you.
$18.42M freight spend, Q3 · $10K per pixel
Auditing ~/invoices/2026-Q3
Portex keeps one context layer over your whole operation — contracts, rate cards, SLAs, carrier performance, and live network state. Versioned, permissioned, and queryable by every agent.
Context layer
v2,481 · synced 0s ago · 6 sources × 16 lanes
A typed SDK, policies in version control, and CI-gated deploys. Guardrails and spend limits are declarative — no prompt spaghetti.
Run every agent against 24 months of your own lane history. Policy violations fail the build in CI — not a shipment in production.
Replaying lane history
reroute-agent · SHA → RTM · portex sim --replay 24m
Fixing reroute policy
policies/reroute.py +6 −2
Two-way connectors with field-level mapping. Agents read and write where your team already works — nothing to rip out.
You decide what agents do alone, what needs a person, and what they never touch.
Set thresholds by spend, lane, or customer. Above them, agents propose and a person approves in Slack or Teams.
Budgets per agent, per lane, per day — enforced by the runtime, not requested in a prompt.
Every input, decision, and action is recorded and replayable — ready for finance, compliance, or a carrier dispute.
Tenant-isolated context, role-based permissions, and SSO. Your contracts and history never train shared models.
“We stopped staffing a night shift for exceptions. The agents catch a rolled booking before our forwarder even emails us — and they’ve already priced the alternatives.”
“The context layer is the unlock. Our agents negotiate with carriers using our actual contracts and our actual history — not a generic model’s guess.”
Agents earn autonomy lane by lane. Your team stays in control at every step.
Plug in your TMS, ERP, and carrier feeds. Read-only to start.
READ-ONLYAgents work your last 24 months. You see what they would have done — and what it would have cost.
SIMULATIONAgents propose on live freight. Your team approves every action.
HUMAN APPROVESSwitch on autonomy lane by lane, inside the guardrails you set.
AUTONOMOUSConnect one lane, replay its history, and watch agents work it — before they touch production.