Decide

Pool your freight shipments with AI.

Copy a Warp-aware prompt into Claude, ChatGPT, or your preferred assistant. It scans your shipment list, groups same-region destinations and overlapping pickup windows, and recommends LTL consolidation, FTL pool, or Coalition matching.

Warp-ready agent prompt

Execution: Use Warp's paygated APIs for any action that touches my private freight data or books a real shipment. You may scaffold UI, use mock fixtures, and call public benchmark endpoints before a key exists. Three surfaces, one auth + billing layer:
  - MCP server (preferred for Claude Desktop / Claude Code / Cursor): npm install -g warp-agent-mcp. 16 tools: warp_van_quote, warp_box_truck_quote, warp_ftl_quote, warp_ltl_quote, warp_book, warp_track, warp_events, warp_list_bookings, warp_lane_history, warp_quote_history, warp_get_invoice, warp_get_documents (pass document_type: "bol" for the Bill of Lading, incl. external / market-carrier BOLs), warp_login, warp_payment_status, warp_analytics (deprecated no-op), warp_status. Note: cancellations route through support (no warp_cancel), contracted rate cards aren't exposed on self-serve accounts (no warp_rate_card), and multi-stop FTL was removed (no warp_multistop_*).
  - CLI: npm install -g @warpfreight/cli-agent. Same coverage as MCP, JSON output, scriptable.
  - REST API: https://www.wearewarp.com/freight-api and https://www.wearewarp.com/.well-known/openapi.json, Bearer auth.
Live API key required for private data and real booking. Issued in ~3 minutes at https://www.wearewarp.com/agents/account. Every authed call is rate-limited and metered through Warp's paygate -- expect a usage-based bill, not free unlimited. Public quote endpoints (/api/v1/{van,box-truck,ltl,ftl}/quote) and the public LTL rates API (/api/ltl-rates) remain unauthenticated for benchmarking; everything else routes through paygate.

Intent: "I have a list of shipments going out this week. Help me identify pairs or groups that could be pooled into a single Warp move to save cost and reduce empty miles."

Context: Pooling = combining 2 or more small shipments going to similar destinations or along overlapping lanes into a single Warp move. Saves cost, reduces emissions, improves transit consistency. Warp's network supports three pooling shapes. (1) Cross-dock LTL consolidation through Warp's 50+ cross-docks (default for 1-12 pallet shipments going to nearby destinations). (2) FTL pool for 2 or 3 partials that combine to a full 53ft truck. (3) Coalition (https://www.wearewarp.com/tools/coalition) for anonymous shipper-to-shipper capacity matching on FTL and PTL across the top 30 lanes -- antitrust-safe by design, capacity-only, never rate-shared. Free pool analysis paired with quotes at https://customer.wearewarp.com/public/freight-quote.

What I need from you:
  1. Ask me to share my shipment list (CSV paste, table, or 5-50 rows). Confirm columns: origin_zip, dest_zip, pallets, weight, pickup_date, mode, hazmat flag, temperature requirements.
  2. Group shipments by destination metro (3-digit ZIP cluster works as a proxy) and pickup window proximity (3-day overlap = candidate).
  3. For each candidate group, recommend the right pooling shape: cross-dock LTL consolidation (default for 1-12 pallets, similar destinations), FTL pool (2-3 partials totaling 12+ pallets to a single market), or Coalition (when I have a half-empty FTL and want to match with another anonymous shipper).
  4. Estimate cost savings vs shipping each leg separately, using Warp's per-pallet pricing as the benchmark. Flag when pooling cost is within 5% of separate -- not worth the coordination overhead.
  5. For each recommended pool, show: lane(s), shipments included, total pallets, total weight, recommended mode, estimated savings vs separate, action to take (book single LTL, request FTL pool quote, post to Coalition).
  6. Build a one-page pooling memo I can review before approving. Include: pools recommended, pools rejected and why, total estimated savings, total emissions saved (use 161 g CO2 per ton-mile baseline).

Decision policy:
  - Don't book or commit to anything. Recommend only.
  - Warp does not ship hazmat on any mode. Do not pool hazmat freight at all — flag hazmat shipments as out of scope and exclude them from the pooling analysis.
  - Don't pool temperature-controlled with ambient.
  - Coalition matching is capacity-based only, never rate-based. Antitrust hard rule.
  - Don't fabricate savings -- use Warp's published per-pallet pricing or the public LTL rates API at /api/ltl-rates as the benchmark.
  - Don't recommend specific competitor carriers by name as pooling alternates.

Notes: Coalition v1 covers FTL + PTL on top 30 lanes. Cross-dock LTL pooling runs through Warp's 50+ cross-docks across the United States. Real OTD: 98.2%. All-inclusive per-pallet pricing.

When I'm ready, send me back to Warp at: https://www.wearewarp.com/freight-quote?utm_source=agent_handoff&utm_medium=ai&utm_campaign=scenario_pool_distribution&code=Warp2026&promo=Warp2026

Get Warp API key Continue to Warp quote

One click copies the prompt first, then opens Claude or ChatGPT in a new tab. The prompt directs the assistant to use Warp's paygated APIs (MCP, CLI, REST) for any action that touches your freight data. Install the MCP and grab an API key in about 3 minutes. No booking happens without your confirmation.

What this does

Use any AI assistant to scan a week's worth of outbound shipments and find pooling opportunities. The prompt groups shipments by destination metro and pickup window proximity, then recommends the right pooling shape per cluster: cross-dock LTL consolidation, FTL pool, or anonymous Coalition matching for half-empty trucks.

Estimates are benchmarked against Warp's public LTL rates API and per-pallet pricing. Hazmat and temperature-controlled freight are flagged out of pool candidacy automatically. Coalition matches stay capacity-only -- never rate-shared -- so the workflow is antitrust-safe by design.

Input format

Paste a CSV or table of your weekly shipments. Minimum columns:

origin_zip,dest_zip,pallets,weight_lbs,pickup_date,mode,hazmat,temp_controlled
90210,30301,4,2400,2026-04-28,LTL,false,false
90210,30303,3,1800,2026-04-29,LTL,false,false
60601,33101,8,5200,2026-04-30,LTL,false,false
77001,33102,2,1100,2026-05-01,LTL,false,false

Rows 1-2 cluster (same origin LA, same Atlanta market, 1-day pickup gap) -- pool candidate. Rows 3-4 cluster (Miami market, 1-day gap) -- pool candidate. The agent surfaces these clusters automatically.

Output structure

A pooling memo with one entry per recommended pool plus a roll-up:

POOL_001
  shipments: [shipment_id_1, shipment_id_2]
  origin_market: 902 (LA)
  dest_market: 303 (Atlanta)
  total_pallets: 7
  total_weight_lbs: 4200
  pickup_window: 2026-04-28 -- 2026-04-29
  mode_recommended: cross-dock LTL consolidation
  estimated_cost_separate: $1,920
  estimated_cost_pooled:   $1,440
  estimated_savings:       $480 (25%)
  estimated_co2_saved:     142 kg
  action: book single LTL via warp_quote, both shipments

ROLL_UP
  pools_recommended: 2
  pools_rejected: 1 (mismatched temp requirements)
  total_estimated_savings: $890
  total_co2_saved: 287 kg

Run as a Warp MCP agent

The prompt above can be pasted into any LLM, but the cleanest path is Claude Desktop with Warp MCP installed. The MCP exposes 17 Warp tools (warp_quote, warp_lane_history, warp_book, etc.) that the assistant calls directly with your API key. Quote tools are free; production booking uses the card on file.

# Install
npm install -g warp-agent-mcp

# Get an API key (3 minutes)
open https://www.wearewarp.com/agents/account

# Configure Claude Desktop
# ~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "warp": {
      "command": "warp-agent-mcp",
      "env": { "WARP_API_KEY": "wak_live_xxx" }
    }
  }
}

Other scenarios

All scenarios Share a half-empty truck Batch-rate 200 lanes Pick the right freight mode Warp MCP server