Site manager
- Behaviors
- Planning, assignments, leading the on-site crew
- Goals
- Keep the plan current; run the week at high operational efficiency
- Pain
- Missing timesheet data, delayed invoice approval
ShiftForge AI
View PresentationAgentic AI to handle routine workforce tasks so operators can focus on decisions that require approval.
Overview
Operations teams spend significant time fixing records of what took place and don't have the visibility to make adjustments in real time.
Three problems came up each week: staff re-entered timesheet details by hand, invoices were delayed while teams checked purchase orders and receipts, and approvals waited in email.
Reconciling two sources by hand
Meticulously comparing these timesheets and correcting inconsistencies costs a lot of time.
Invoices that stall
Payment is held up until the PO, a receipt, and a timesheet agree, meaning workers are paid before the agency gets compensated.
Approvals in an inbox
The next action lives in someone’s email, so exceptions surface days after they cost money.
Design goals
- Auto-build the plan — let AI match work orders to POs and draft invoices, so a week stands up without hand-keying.
- Give every task an owner — assign clear tasks so invoices don’t get lost and exceptions get caught early.
- Show overtime before it happens — at the moment of assignment, not on the invoice.
Research
Not one vendor fit both sides of the problem.
I compared 14 workforce products to see how well each worked for factories and staffing agencies. None worked well for both.
| Vendor | Category | Staffing fit | Mfg fit | Hybrid |
|---|---|---|---|---|
| Bullhorn | Staffing OS | 5 / 5 | 1 / 5 | 2 / 5 |
| TempWorks | Staffing OS | 4 / 5 | 2 / 5 | 2 / 5 |
| Shiftboard | Mfg WFM | 1 / 5 | 5 / 5 | 2 / 5 |
| UKG WFM | Mfg WFM | 2 / 5 | 4 / 5 | 3 / 5 |
| ShiftForge | Orchestration layer | 4 / 5 | 4 / 5 | 4 / 5 |
What that gap costs, every week
~4 hrs
of a coordinator’s week, reconciling timesheets by hand
15–30%
of invoices need a rate or overtime correction
3–5 days
to resolve a billing dispute over email
Users
Plans and invoices are processed by two roles that oversee labor operations.
Plant supervisor
- Behaviors
- Data-driven calls on the floor, leading shifts
- Goals
- Operational efficiency and quality assurance
- Pain
- Backfilling positions fast, unexpected overtime
“If a temp worker goes into overtime, I don’t find out until the invoice comes.”
“We approve time in one system, then re-enter it in another to generate the invoice.”
Design Challenge 01
How could an agent take over for routine weekly tasks without impeding operator decision-making?
Each week, teams add workers, assign shifts, fill open roles, and check invoices across two systems. Basic automation can handle routine cases while an agent flags exceptions that need attention.
The AI constraints I designed around
Made-up references
The agent sometimes cited time entries that did not exist. The app now checks every reference against real data before showing it.
Version drift
The same question got different answers from different model versions, so I locked the answer to a fixed shape the app validates every time.
Over-narration
The agent wanted three paragraphs where one sentence would do. Length is capped in the prompt and again in the app.
Fake confidence
It would confidently invent what it did not know. I gave it a way to say “I don’t know” — and made that the only option when it isn’t sure.
Cost per use
Paying a vendor per question added up fast, so for the pilot the agent runs on the customer’s own machine on a free open-source model.
Multi-agent design
I gave each of the three agents one job, a set response format, and a clear point where a person takes over.
| Agent | Input | Output | Approval boundary |
|---|---|---|---|
| Reconciliation Agent | This week’s time entries and rate cards | 3–5 typed flags with citations and proposed resolutions | Plant supervisor approves any flag that affects billing |
| Coverage Agent | Next week’s demand and the current roster | Coverage flags, ranked candidate suggestions per open shift | Coordinator dispatches, supervisor confirms |
| Workspace Assistant | The active surface plus the palette query | Free-form chat scoped to the current view | Never moves state, only proposes |
The two surfaces I redesigned
Planning
Standing up next week's coverage
Timesheets
Reviewing the week and catching overtime
My design process
Research
- Conversations with staffing coordinators and plant supervisors
- Mapped weekly workflows and pain points
- Identified primary users and jobs to be done
Scope
- Mapped user jobs to features, grouped by role and approval boundary
- Ranked by impact and effort, cut to what could ship as v1
UI design
- Pulled references from operations and fintech tools
- Studied approval and reconciliation patterns in adjacent products
Prototyping
- Several rounds of HTML mockups, low-fi to high-fi
- One shared shell across planning, timesheet review, and reconciliation
- Handed off to build with Claude Code in Next.js
Key Solution
The five capabilities that make it work.
Assign work without lifting a finger
When a shift needs coverage, the system ranks available workers by certification, availability, cost, and distance. It gives the supervisor a shortlist and explains why each person was suggested.
Human approval when it matters
Overtime, missing punches, geofence issues — all flagged automatically with a proposed fix attached. Nothing touches pay or a worker’s record until a named person clicks approve.
Take action before it’s too late
The moment a worker crosses the overtime threshold it is flagged — not discovered a week later when the invoice lands and there is nothing left to plan around.
Check invoices against real records
Before the agent writes a word of an invoice, it retrieves the real timesheet, rate card, and policy behind that line, and shows what it looked up. It can’t invent a number it can’t point to.
Keep track of how it all happened
Every flag carries its evidence. Every approval is logged with who, when, and why. Every action can be reversed by a person with the right permissions.
Impact
Operational efficiency with less manual work
~80%
less planning setup, with auto-built plans
0
surprise overtime
0
chasing exceptions
Invoice Turnover
- Current
- ~3 days
- Forecasted
- 24 hours
3× faster · 48 hours saved per cycle
Slow invoice turnover requires chasing down workers, manual corrections, and cross-checking two systems.
Invoices Requiring Corrections
- Current
- 15–30%
- Forecasted
- 0%
Zero rework · clean on first pass
Corrections are needed today because hours are keyed in manually across two systems, so mismatches and data-entry errors slip through unchecked.
Average Overtime per Worker
- Current
- 3.8 hrs/wk
- Forecasted
- 3 hrs/wk
21%+ less · 0.8+ hrs saved per worker weekly
Unintended overtime occurs when workers near overtime cover for unexpected lapses in coverage.
Next Steps
Find design partners and run simulations to refine the product.
I will continue testing the product with staffing agencies and manufacturers.
