AI freight agents
Let AI Agents Ship Your Freight
Warp's API and CLI are built for autonomous operation. AI agents can quote, compare, book, track, and manage freight without human intervention. Every endpoint returns structured JSON. Every CLI command outputs parseable data.
Structured JSON · Parseable CLI output · Webhook events · 20,000+ carriers
Why freight is the next AI agent frontier
AI agents are automating everything from code deployment to customer support to financial analysis. Freight logistics is next. Moving physical goods involves quoting, comparing rates, booking carriers, tracking shipments, handling exceptions, and settling invoices. These are all structured, repeatable workflows. Perfect for AI agents.
The problem until now has been that freight systems were not designed for machines. Traditional freight platforms use web portals that require human interaction. Rate requests happen over phone or email. Tracking updates come via EDI feeds that require custom parsers. None of this works for an AI agent that needs to make decisions and take action autonomously.
Warp's API changes this. Every freight operation is a simple HTTP request that returns structured JSON. The Warp CLI provides the same operations as shell commands. AI agents built with Claude Code, LangChain, CrewAI, or custom frameworks can plug into Warp and handle freight end to end.
What an AI freight agent can do
Quote and compare
Agent calls the quote endpoint with origin, destination, and cargo details. Gets back rates for LTL, box truck, truckload, and cargo van. Compares on price, transit time, and service level.
Book autonomously
Agent selects the optimal option based on business rules (cheapest, fastest, or best balance). Calls the booking endpoint. Gets back a shipment ID and tracking number.
Track and alert
Agent polls the tracking endpoint or listens to webhooks. Monitors for exceptions: late pickups, missed scans, route deviations. Escalates to humans only when intervention is needed.
Handle exceptions
When Orbit flags an issue, the agent receives a webhook event. It can rebook, notify stakeholders, or adjust downstream operations. No human needed for routine exceptions.
Settle and audit
Agent pulls invoices and documents via API. Matches charges to quotes. Flags discrepancies. Sends reconciled data to your accounting system.
Learn and improve
Agent tracks carrier performance data: on time rates, damage rates, communication responsiveness. Uses this data to make better booking decisions over time.
Integration patterns
Pattern 1: Claude Code as freight agent (terminal)
$ claude "Ship 8 pallets of electronics from 90210 to 10001.
Find the cheapest option with 3 day transit or less."
Claude Code: Querying Warp API for rates...
Mode Rate Transit
LTL $1,247 3 days ← Recommended
Box $1,890 2 days
FTL $2,340 2 days
Booking LTL option...
Booked: shp_01HGA2K9... | Pickup: April 7 | ETA: April 10Pattern 2: Python agent
import warp
client = warp.Client(api_key="warp_sk_...")
# Quote
quotes = client.quotes.create(
origin="90210",
destination="10001",
items=[{"pallets": 8, "weight_lbs": 4800}]
)
# Select cheapest within transit window
best = min(
[q for q in quotes if q.transit_days <= 3],
key=lambda q: q.rate
)
# Book
shipment = client.shipments.create(quote_id=best.id)
print(f"Booked: {shipment.id} | ETA: {shipment.eta}")Pattern 3: Webhook listener
@app.post("/warp-webhook")
async def handle_event(event: dict):
if event["type"] == "shipment.exception":
# AI agent decides what to do
await agent.handle_exception(event)
elif event["type"] == "shipment.delivered":
await agent.reconcile(event["shipment_id"])Build your freight agent
Why Warp's API is agent friendly
- -Structured JSON on every endpoint. No HTML to scrape. No PDFs to parse.
- -Explicit field names and enum values. AI agents can understand the schema from documentation alone.
- -Idempotent operations. Safe to retry without creating duplicate bookings.
- -Webhook events for real time state changes. Agents don't need to poll.
- -CLI with machine readable output. Terminal based agents can use shell commands directly.
- -Test mode for development. Simulate the full quote to delivery lifecycle without dispatching real carriers.
The network behind the API
- -20,000+ local 3rd-party carriers dispatched through the Warp driver app.
- -9,000+ box trucks and cargo vans.
- -50+ Warp operated cross-dock facilities across 12 markets.
- -Our AI backbone, Orbit, monitors every shipment for exceptions in real time.
- -All inclusive pricing. No fuel surcharges, no hidden fees.
Frequently asked questions
What AI frameworks work with Warp?
Any framework that can make HTTP requests. Claude Code, LangChain, CrewAI, AutoGPT, custom Python agents, Node.js agents. The Warp API is standard REST with JSON payloads.
Can an AI agent book freight without human approval?
Yes. The API supports fully autonomous operation. Many customers set business rules (max spend per shipment, preferred modes, required transit times) and let AI agents book within those parameters.
How does the agent handle exceptions?
Warp sends webhook events for exceptions like late pickups, missed scans, and route deviations. Our AI backbone, Orbit, flags these before your team has to chase them. Your agent can listen for these events and take action.
Is there rate limiting?
Standard rate limits apply for all accounts. Enterprise accounts get higher throughput limits. Contact Warp for details.
What does it cost to use the API?
No software fees. No API call charges. You pay when you ship with all inclusive per pallet pricing. No fuel surcharges or hidden fees.
Freight operations, fully autonomous.
Every endpoint returns structured JSON. Every CLI command outputs parseable data. Build AI agents that quote, book, track, and settle freight through Warp without human intervention.
Structured JSON · Parseable CLI output · Webhook events · 20,000+ carriers