The FourKites Knowledge Center

EDI 214 (Transportation Carrier Shipment Status Message) and EDI 990 (Response to a Load Tender) are standard electronic data interchange formats used for carrier-shipper communication. EDI 214 transmits shipment status updates (picked up, in transit, delivered). EDI 990 transmits carrier acceptance or rejection of a load tender.

Every enterprise technology leader faces the build-vs-buy question for supply chain AI agents. The prototype is seductive: a working agent in a week using LangChain or CrewAI. This framework examines five problems that emerge between demo and production, and provides criteria for when to build internally versus when to buy a platform.

Loft is FourKites' multi-agent orchestration platform where AI agents operate, workflows are built, and every decision is recorded with a full audit trail.

Agent Communication Channels are the modalities through which supply chain AI agents reach carriers, suppliers, customers, and enterprise systems: Email, SMS, System-to-System API, Portal/UI, EDI, and Voice.

Generic AI agent platforms (LangChain, CrewAI, AutoGen, and consulting-led custom builds) consistently fail in production supply chain environments because they lack network intelligence, cross-boundary orchestration, and decision memory.

Decision Intelligence is the discipline of using data, analytics, and AI to improve the speed and quality of operational decisions, encompassing the capture of decision context, the evaluation of alternatives, the execution of the chosen action, and the measurement of outcomes to inform future decisions.

Supply Chain Network Intelligence is cross-company operational data aggregated from hundreds of enterprise shippers, thousands of carriers, and millions of facilities, creating intelligence patterns that no single company's data can produce alone.

Cross-Company Intelligence is the layer of supply chain insight that emerges only when operational data from multiple enterprises is aggregated: carrier behavior patterns, facility benchmarks, lane performance distributions, and exception resolution precedents that no single company could observe alone.

When deploying AI agents in supply chain, 80% of every workflow should leverage proven patterns from the network (pre-built AOPs validated across Fortune 500 deployments) and 20% should be customized to the customer's specific business rules, escalation paths, and integration requirements. This framework explains why this ratio matters and how to apply it.

Outcome as a Service is a commercial model in which an enterprise pays for measurable business outcomes delivered by AI agents, rather than software licenses, seats, or modules.

Generative UI is the dynamic creation of user interfaces by an AI system based on the user's role, context, and current operational state, replacing static dashboards with adaptive views that are generated, not configured.

The Supply Chain AI Flywheel is the compounding intelligence cycle in which more data feeds better intelligence, better intelligence feeds smarter agent decisions, agent decisions generate decision traces that enrich the data, and the system gets stronger with every shipment processed.

AI explainability in supply chain is the ability to provide human-understandable explanations for every AI-generated prediction, recommendation, or action, answering not just 'what did the AI do' but 'why did it do that' and 'what information informed the decision.'

AI workflow automation is the use of artificial intelligence to execute multi-step business processes autonomously, replacing manual task sequences with agent-driven workflows that gather data, reason on intelligence, take action, and record outcomes without human intervention for routine operations.

An Outcome Advisor is a FourKites specialist who helps enterprise buyers identify which supply chain outcomes apply to their operation and designs the deployment path to deliver them.