Get a demo

Freight quote email parsing

Monitor your inbox for inbound freight quote requests, extract origin, destination, cargo specs, and service level, and output a structured table ready for quoting.

Get a demo

The prompt

I want to parse inbound freight quote request emails and pull out the key shipment details. Can you build me a flow that monitors my inbox, extracts origin, destination, cargo specs, and requested service level, and outputs a structured table ready for quoting?

Just copy and paste the prompt into a new Parabola flow to get started.

What Parabola builds

A workflow with six steps you can edit:

1. Monitor the inbox. The flow watches the shared quote-request mailbox for new inbound emails. It picks up requests from shippers, brokers, and logistics coordinators as they arrive.

2. Classify the email type. Rate request, RFQ, spot quote, or recurring lane inquiry. Each type routes to the right extraction template so the AI pulls the fields the quoting team actually needs.

3. Extract the shipment fields. Origin city and postal code, destination city and postal code, commodity description, weight, dimensions, freight class, requested service level, required delivery date, and any special handling notes. The AI step reads the email body and pulls every field it can find.

4. Normalize the data. State and country codes map to your canonical format. Freight classes get standardized. Service level codes align to your rate card naming. The output lands in the same columns every time.

5. Append accessorial flags. Liftgate, inside delivery, residential, limited access, hazmat. The extraction step flags each one so your quoting team knows what to include in the rate before they open the system.

6. Write the structured record. Push the row to your quoting table, your TMS, a shared Google Sheet, or a Slack channel. The quoting team sees a clean row instead of a wall of email text.

Why teams stop doing this manually

Quote requests arrive in plain English. A shipper writes 'I need to move a pallet from Dallas to Memphis, about 800 pounds, dry van, by Friday.' A broker sends a PDF attachment with a form. A logistics coordinator emails a forwarded chain with the origin buried in the third paragraph. The person opening the inbox reads each one, extracts the details, types them into a quoting tool, and moves to the next.

On a light day that is manageable. During peak season or after a key lane goes live, the inbox fills faster than any one person can process it. The backlog builds up during meetings. Quote requests from the afternoon sit unanswered overnight. Shippers who do not hear back within two hours move on to the next carrier.

The extraction work is high-effort but low-judgment. Reading an email and typing six fields into a row is exactly the kind of task that belongs in a flow. The quoting team's judgment goes into pricing, not parsing.

How it works

Step 1. Paste the prompt.

Open Parabola, paste the prompt in section 2, and let it ask follow-up questions about which inbox, which field set your quoting team uses, and where the structured records should land.

Step 2. Connect your data.

Inbox connector for the shared quoting mailbox. Destination connector for your TMS, your quoting sheet, or whatever system your team quotes from. Optional PDF attachment connector for requests that come in as forms.

Step 3. Run it on every inbound email.

The flow triggers when a new request arrives, extracts the fields, and writes the row. The quoting team works from a structured table instead of reading raw email.

Related prompts

FAQ

What if the shipper sends the request as a PDF form instead of plain email text?

The flow checks the body first and falls back to attachments when the fields are not in the body. PDF forms and Word attachments are parsed with the same AI extraction step that handles plain text.

Can the flow handle requests in different languages or formats from international shippers?

Yes. The AI extraction step handles format variation including non-native English and common international field name patterns. You configure the output to normalize into your standard format regardless of input language.

How does the flow deal with incomplete requests that are missing key fields?

Rows with missing required fields get flagged in a separate column. The quoting team sees which records need a follow-up before the system can generate a rate. Optional: the flow sends an auto-reply asking the shipper for the missing information.

Does this work with RFQ forms that come in as spreadsheet attachments?

Yes. Excel and CSV attachments parse through the same extraction pipeline. The flow maps the attachment columns to your output schema automatically.

How is this different from reading the emails manually and entering data by hand?

Manual entry is fine for a few requests a day. When you are handling 50 or more per day across multiple lanes, or when your team has to process requests from three different customer types that each format their request differently, manual entry becomes the bottleneck. The flow handles format variation and volume without adding headcount.
Every quote request, structured and ready to price.
Paste the prompt, point it at your shared mailbox, and let the extraction build the quoting table automatically.
Start for free