SMB Agents AI
← All use casesRun the schedule

Plan tomorrow's technician routes in minutes

Dispatch planning takes minutes instead of an hour

Illustrative example — a composite of common setups, not a specific business's story.

Difficulty
Needs help
Setup time
1-2 days
Monthly cost
$20-$100
Impact
High

The short version

Each evening an agent reviews tomorrow's jobs, tech skills and locations, and proposes an ordered schedule for the dispatcher to approve.

What they did

Each evening an agent reviews tomorrow's jobs, tech skills and locations, and proposes an ordered schedule for the dispatcher to approve. The owner started with a small pilot: one workflow, a few days of supervised use where every output was reviewed before it went out, then gradually let routine cases run with lighter oversight.

Agent/tool used: ChatGPT with exported job list

How it went

In a typical rollout like this: dispatch planning takes minutes instead of an hour. Most of the value comes from consistency, the task happens every time instead of when someone remembers. Expect a week or two of tuning the prompt and rules.

Worth knowing

AI drafts can be wrong or off-tone. Keep a human approving anything customer-facing at first, don't paste sensitive data (card numbers, health records, SSNs) into general chat tools, and check each tool's data and privacy terms.

Copy-paste prompt

Here are tomorrow's jobs [paste: job, address, est. duration, skill needed, time window] and technicians [paste: name, skills, start location, hours]. Propose an assignment and order for each tech that respects time windows and skills and minimizes driving. Flag anything that doesn't fit.

Replace anything in [brackets] with your own details.

Step-by-step setup

  1. Write down how you handle this today, in 5-10 bullets.
  2. Connect or export data from ServiceTitan, Google Workspace.
  3. Set up ChatGPT with exported job list and paste in the prompt, filling in the [placeholders].
  4. Test it on 5-10 real past examples and fix anything that's off.
  5. Run it with you approving every output for one to two weeks.
  6. Once you trust it, automate the routine cases and spot-check weekly.

Published 2026-10-04. Want help setting this up?