Skip to content
PROOF // Fleet, Trucking & Travel Center Operations Regional carrier operating a multi-terminal trucking network plus company-run travel centers · HOS-regulated · driver-retention pressure
← All Proof

CHAPTER 03 · BUILD

Agents Shipped Inside the Existing Stack

The first system, and the two right behind it, shipped inside the terminal network's existing systems — no new TMS, no rip-and-replace. Each one is real and running.


THE AGENTS · 3 FOR THIS WORKFLOW

This load plan needed five agents working together — route, stops, fuel, hours-of-service, and a rest plan — because the work splits into five distinct jobs. Each is its own identity with its own scoped tools. Another workflow might need two.

01

Per-Load Route & Fuel Plan

Status Runs every load
Impact Manual build → reviewed plan
Team Automated, 1 human review
02

Travel Center Demand & Workforce

Status Daily ops brief per location
Impact Manual scheduling → reviewed brief
Team Automated, 1 human review
03

Driver Retention Signals

Status Wave 2 — in build
Impact Turnover-risk scoring
Team Automated, plus a review queue

IT DOESN'T STOP AT A REPORT

The Agent Takes the Action

A plan is one output. Most of what these agents do is take the next action across dispatch — a person approves anything that commits a truck or a carrier.

agent inbox — this morning
DATA VIEW

Build the load plan

Route, fuel stops, and an HOS-legal rest plan are planned together the moment a load is assigned.

Ran automatically

Tender the load to the carrier

Sends the tender to the chosen carrier once dispatch approves it.

Send the customer the ETA

Pushes the updated arrival time to the customer automatically as the plan changes.

Ran automatically

Book the terminal slot

Reserves the dock or appointment window against the planned arrival time.


PRODUCTION TRACE

Per-Load Route & Fuel Plan

Every step below runs against the plant's real data — the exact sequence, in order.

live.internal — this morning
DATA VIEW

41

Load plans generated

36

Plans accepted as-is

3

HOS conflicts caught before dispatch

2

Fuel-stop overrides

3 items need your judgment

L-4471 HOS clock leaves a 40-minute margin on the proposed rest stop
High
L-4483 Fuel plan recommends a stop outside the preferred network
Medium
L-4490 Route confidence 79% due to a weather advisory on I-40
Medium

Ingest

Automated

Load details, driver HOS clock, and network fuel prices pulled the moment a load is assigned — no new data entry for dispatch.

Five-agent plan

Automated

Route, travel-center stop selection, fueling strategy, and an HOS-compliant rest plan are built together, not as four separate decisions that fight each other.

Ground every claim

Automated

Every recommendation cites the exact HOS clock, fuel price, or network constraint behind it, not a general opinion.

Dispatcher review

Reviewer input

The full plan is one-click accept or send-back. Send-backs become training signal for the next load.

Load tracking

Automated

Plan vs. actual gets tracked through delivery — did the stop, fuel, and rest plan hold up.

REAL OUTPUT · TRAVEL CENTER DEMAND & WORKFORCE

One Example, Fully Processed

When a job calls for a written artifact, this is what the system produces — everything it finds, structured for the action it triggers next.

Terminal 12 — Daily Ops Brief

Travel center, I-40 corridor · Generated 4:15 AM for the 6:00 AM shift change · Local + network signals

DATA VIEW

Signals Flagged for Today's Shift

Signal Reading Threshold Zone Confidence
Fuel-island demand forecast +22% vs. yesterday Staffing trigger at +15% Fuel islands 93%
Weekend staffing gap 2 shifts short, Saturday PM Min. 4 staff per shift Restaurant & store 97%
Parking-lot occupancy trend Trending toward full by 9 PM 90% capacity Overnight lot 88%
Energy-cost anomaly Refrigeration load +14% ±10% of baseline Cold storage 64%
Store restock trigger 3 SKUs below reorder point Standard reorder rule Convenience store 95%

Shift Brief — for the Terminal Manager

Saturday's fuel-island demand is running well above forecast, and the restaurant/store schedule is two shifts short to cover it. The refrigeration energy anomaly is worth a look but isn't urgent yet. Everything else on today's board is a normal restock cadence.

Tough Calls — Shift-Change Briefing

Fuel-island staffing: pull a floater from the store to cover the demand spike, or the wait time will show up in reviews by noon.
Refrigeration energy anomaly flagged at 64% confidence — below the auto-log threshold. Worth a manual check before it's logged as a maintenance issue.
Overnight lot is trending toward full by 9 PM on a weekend — flag for the safety walk-through, not just capacity planning.

WAVE 2 — IN BUILD

Driver Retention Signals — What's Next

Drivers rarely quit over one bad week — it's a pattern of missed home time, pay variance, and unassigned miles that dispatch can't see until the resignation call. By then, the fix is too late.

The agent proposes which intervention to prioritize for a driver showing risk signals; a rules engine checks it against pay policy and contract terms. Nothing ships on an LLM's judgment call about compensation — the policy check is the check.

Worked example the system evaluates today in testing

A driver cohort out of Terminal 6 shows three risk signals in the same week: two missed home-time windows, unassigned miles trending down, and a pay-variance flag. Four intervention options scored by projected retention-risk reduction:

DATA VIEW
4 No intervention — wait for the next check-in cycle +6 pts turnover risk
3 Automated pay-variance explanation sent to driver +2 pts turnover risk
2 Dispatcher flagged for a personal check-in call -4 pts turnover risk
1 Home-time window restored next scheduling cycle -11 pts turnover risk

WHAT CHANGED

Time returned

~95% of manual planning time

Dispatchers got the time back for exception handling, not for building routine plans by hand.

Operating complexity

A 20-minute manual build became a 90-second reviewed plan

Where this stands

First system live in 30 days

CHAPTER 03 OF 5

UP NEXT · TEAM VIEW

See what actually changed for the people doing the work, role by role.

Continue to Team View