Freight Quote Automation via WhatsApp
Collects freight details via WhatsApp chat, calculates LTL quotes with commission using Warp API, and sends the final price back instantly.
ops and IT teams
What it does
Collect freight shipment details and deliver instant LTL quotes directly through WhatsApp. The system identifies the sender in HighLevel, uses an AI agent to gather missing logistics data via chat, calculates the final price with your commission, and sends the quote back to the customer automatically.
Step by step
- Configure the WhatsApp Business Cloud webhook to listen for incoming messages and route them to your application endpoint.
- Implement a database schema in HighLevel or your backend to store customer IDs, shipment origins, destinations, weights, and dimensions.
- Set up an HTTP client library to send POST requests to the Warp API with standardized JSON payloads containing logistics parameters.
- Define the exact commission logic as a deterministic function that applies percentage or flat fees to the base carrier rate before returning the final quote.
Where the LLM does the work
- Prompt the Google Gemini agent with dynamic instructions to ask clarifying questions when shipment details like pallet count or accessorial needs are missing.
- Instruct the LLM to format its internal state updates into structured JSON so Redis can reliably store and retrieve conversation context across turns.
- Generate natural language responses that explain pricing components clearly while maintaining a helpful and professional tone appropriate for logistics customers.
Watch out for
Redis memory keys must include unique session identifiers per customer to prevent quote data from bleeding between different users chatting simultaneously.
WhatsApp message templates require pre-approval for outbound quotes, so ensure your initial trigger uses a valid template ID to avoid message rejection.
Tools that fit
WhatsApp Business Cloud Service Receive and send messages
HighLevel Service Contact lookup and management
Google Gemini Chat Model LLM Conversational data collection
Redis Chat Memory Service Maintain conversation context
HTTP Request API Call Warp API for quotes
The agent brief
Everything your agent needs, including the gotchas. Copy it and go.
You are helping me build the following AI agent workflow. ## Goal Freight Quote Automation via WhatsApp: Collects freight details via WhatsApp chat, calculates LTL quotes with commission using Warp API, and sends the final price back instantly. ## Specification - What it does: Collect freight shipment details and deliver instant LTL quotes directly through WhatsApp. The system identifies the sender in HighLevel, uses an AI agent to gather missing logistics data via chat, calculates the final price with your commission, and sends the quote back to the customer automatically. - Trigger: Triggered by an event (Event · on new WhatsApp message) - Autonomy: Fully hands-off - Expected setup effort: a few focused days - Tools/services involved: - WhatsApp Business Cloud: Receive and send messages - HighLevel: Contact lookup and management - Google Gemini Chat Model: Conversational data collection - Redis Chat Memory: Maintain conversation context - HTTP Request: Call Warp API for quotes ## Known pitfalls, handle each one explicitly in your implementation 1. Redis memory keys must include unique session identifiers per customer to prevent quote data from bleeding between different users chatting simultaneously. 2. WhatsApp message templates require pre-approval for outbound quotes, so ensure your initial trigger uses a valid template ID to avoid message rejection. ## Reference implementation https://n8n.io/workflows/16385 (workflow template) Fetch and inspect this before building. If it matches my stack, adapt it; if not, rebuild the pattern with my tools. ## Process requirements 1. Before building: ask me which of the listed tools I actually use and what my platform is (n8n / Make / code / other). Do not assume. 2. Adapt the pattern to my answers; do not force the reference stack. 3. Address every pitfall above; tell me how you handled each. 4. Provide a test plan I can run before letting this touch real data. 5. Ask before any step that sends messages, modifies data, or spends money. Source: https://usecasesforagents.com/use-case/freight-quote-automation-via-whatsapp/ via usecasesforagents.com
Frequently asked questions
Can I use a different Messaging than WhatsApp?
Yes. WhatsApp is only the example messaging in this recipe. The same flow works with ClickSend API, Discord, Google Chat and LINE Messaging API. Swap the messaging connection and keep the rest of the setup as written.
Want this running in your business?
This is what I do. I design and build AI agents like this one, and keep them running. If you want it set up for your team instead of doing it yourself, get in touch.
Who it's for
Built for Ops-IT teams who need one more recurring task off a human's plate.