A Spaid engineer pulls 6–12 months of dispatch history, uses AI-powered pattern analysis to map which techs win on which job types, and builds assignment rules from outcomes — not gut instinct or who’s available.
Field service scheduling software and route optimization tools solve the wrong problem. Drive time and availability are easy to measure — but dispatch is a skill-match, job-type, and outcome-feedback problem. Your ServiceTitan or Housecall Pro data already contains 6–12 months of dispatch outcomes. Nobody has analyzed it. Operators who apply skill-match rules from outcomes report skill-match dispatch reducing callbacks by 25–35% within 90 days.
Dispatch decisions are made dozens of times per day with incomplete information. The outcomes — callbacks, margin, customer satisfaction — are tracked in the FSM. The connection between assignment decision and outcome almost never gets made.
Some techs close 40% more effectively on diagnostic calls than installation. Others are the inverse. Without a skill-match layer, dispatch assigns based on availability — and generates unnecessary callbacks and low-margin outcomes on the wrong assignments.
3× callback rate variance by tech on specific job typesRoute optimization tools focus on travel time and miss the bigger issue: job clustering by type. Sending a commercial tech through a residential-heavy zone costs more in outcome variance than in drive time.
$150–$300 per avoidable truck rollDispatch assigns jobs. Jobs get completed. Outcomes go into the FSM. Nobody connects the assignment decision to the GM, callback rate, or customer score outcome. The same bad patterns repeat daily — making dispatch inefficiency a direct revenue leak that compounds every week.
No assignment decision ever reviewed against outcomeRoute optimization reduces drive time. Dispatch intelligence improves outcomes. They’re not the same problem, and solving the wrong one is expensive.
Minimize drive time. Don’t factor in which tech wins on which job type, callback probability, or skill-to-job match.
Sends the veteran tech to every job — burns capacity and doesn’t develop the bench. Can’t scale.
Sends whoever’s closest and available. Outcome variance is high, root cause is invisible.
Works well with 10 techs. Breaks down at 30+. Not trainable, not consistent, not scalable.
Which techs win on which job types. Which assignments generate callbacks. Where geographic clustering breaks down. Built from your data.
Each tech’s proficiency by job type used to score dispatch decisions — not availability, skill match.
FSM API connector surfaces which assignment patterns produce the best margin, lowest callbacks, and highest close rates — turns intuition into a system.
Callback rate by assigned tech, margin per dispatched job, job-type mismatch flags — flagged before they compound.
Six months of dispatch history. Assignment rules from outcomes. Skill-match scoring from the knowledge graph.
Analyzes historical job assignment data across all techs — callback rate by tech and job type, GM per assignment, first-call resolution rate. Identifies which tech-to-job-type combinations produce the best outcomes and builds explicit assignment rules from the findings. Accurate dispatch intelligence requires cross-system data — FSM and telephony combined.
Pulls job assignment history, completion data, callback flags, and invoice amounts from your FSM. Creates a full-outcome view of every dispatch decision over 6–12 months — the dataset needed to build real assignment intelligence.
Operational knowledge graph documents each tech’s performance by job type — not self-reported, derived from outcomes. Used to score dispatch decisions in real time: this tech on this job type has a 12% callback rate vs. this tech who has 3%.
Tracks callback rate by assigned tech, margin per dispatched job, and job-type mismatch rate daily. Flags patterns before they compound. Identifies when assignment rules are drifting — dispatcher ignoring the skill-match layer, volume spike creating availability-only decisions.
Our Full-Operation Audit (Days 1–30) maps every revenue leak — field and back of house. If we don't identify at least $200,000 in recoverable annual revenue, we refund Phase 1 in full. You keep all audit deliverables.
After kickoff, we ask for about 30 minutes a week of your ops leader's time.
We'll start with a recent export or sample call data from your FSM and call system, show you the biggest leaks, and scope the engagement. Full access happens only if you proceed to the audit.