CHATBOTS

Pre-trip budget estimator from a webhook form

A pre-trip planning form submission triggers a full-trip reimbursement simulation across flights, hotel, meals, and ground transport.

CategoryChatbots
Enginesim
Difficultyadvanced
Triggerwebhook
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerPre-trip form submitted via webhookHTTP webhook
  • ActionLoad city-tier rates and role caps from AirtableAirtableAirtable
  • ActionBuild per-category trip budget with the modelOpenAI
  • LogicTotal envelope and flag uncovered legs
  • ActionWrite estimate to the trip recordAirtableAirtable
  • OutputEmail the budget envelope to the employeeGmailGmail

What it does

Before an employee books a trip, they submit a short form (destination, dates, traveler level, purpose). The workflow simulates the entire trip against policy and returns a per-category spending envelope — the nightly hotel cap for that city, daily meal allowance, allowable flight class, and ground-transport limits — so they book inside policy on the first try.

When to use it

Ideal for organizations with city-tiered travel caps and frequent business travel. It replaces the back-and-forth of "is this hotel too expensive?" with a concrete budget delivered before booking.

How it works

  1. 1A pre-trip form posts its fields to an HTTP webhook, starting the run.
  2. 2City-tier rates and role-based caps are pulled from Airtable.
  3. 3The model assembles a category-by-category budget for the trip's length and traveler level.
  4. 4A logic step totals the envelope and flags any leg that has no covered option (e.g., no compliant flight under cap).
  5. 5The estimate and per-category caps are written to the trip record and emailed to the employee.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect HTTP webhookTrigger any URL on agent actions.
  2. 2
    Connect AirtableBases, tables, views, automations.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Connect GmailRead, draft, send, label.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.