Hook: the agency can only staff an accurate, approved request. Production variability is upstream context. The screenshot is the redesigned prototype with sample data, not a measured outcome.

Patrick observed the work across departments, operators, agency managers, and directors. He redesigned earlier planning, allocation, time, and HR flows. The independent AI-native product and build are his. Three-month duration retained from the existing opening draft.

Keep this to a brief definition before explaining responsibilities. Brands place orders with a manufacturer; the manufacturer uses staffing agencies for temporary labor. Orient the audience to the relationship before moving to shared responsibilities. This illustrative factory photograph does not depict a ShiftForge customer, research participant, or verified temporary worker. Photo: Homa Appliances, Unsplash, _XDK4naBbgw, free under the Unsplash License.

Use the sequence to orient the audience. The product starts with labor demand and carries records forward. It does not configure production lines.

This is a qualitative synthesis of Patrick’s cross-organization workflow observations, not a time-and-motion study. Each step requires people to compare records, confirm commitments, or route exceptions across organizational boundaries. Traditional separate staffing, scheduling, time, and billing tools make a current cross-party status difficult to assemble. The examples illustrate why manual action accumulates; do not claim every incumbent lacks each feature or assign measured time costs to these rows.

These figures were already in the opening draft and earlier case-study files. Their source records, sample, and dates need confirmation. They describe reported baseline pain, not ShiftForge impact. Remove this slide from interview delivery if the figures cannot be substantiated.

Introduce the three core workflows. Start with plan demand, approval and agency allocation.

Follow the five-step planning flow from an AI-assisted draft through department approval, AI-assisted matching, agency assignment, and publication with a system lock. The agency publishes; the system locks the week. The full Plan interface comes next, followed by the opening details. The legend marks the primary action at each step; a recommendation is never itself an assignment or approval. Department heads manage their demand; permitted operations roles can manage across departments; agencies alone assign/unassign workers. A changed demand request reopens approval, and workers confirm assignment requests outside this captured state.

The video shows the Add to plan form filling multiple positions across three roles, selected weekdays, and Area 1. The shift requirement belongs to the scheduled opening, but a shift selector is not visible in this crop; do not point to one. Authorized department users manage their own demand; operations permissions may span departments. AI can prepare a draft addition, but the user confirms it, and each department approves its request before agency fulfillment. The visible Add to plan button is a human action, not an approval.

Why this interface: existing operators navigate datasets, not only conversation. The assistant can open across pages and use the current page, site, and relevant time period as context. This video shows a Plan-page example, not the limit of the interaction. Describe persistent memory as an opportunity if asked; the clip does not demonstrate it.

Climax: a recommendation does not equal a confirmed worker. The planner selects a worker and days, a manager approves the assignment, and the worker responds to the request. The modal shows the selection; manager approval and later worker confirmation by text or app are not shown in this capture. Agency users can assign and unassign workers; reassignment remains a human action. Immediate undo and permissioned audit amendments are part of the defined design; avoid implying they are visible in this modal. Video replacement: compare candidates, adjust days, select, undo.

Transition from planning and allocation into worked time, exceptions and human review.

Trace the five-step timesheets flow. Worker punches enter the record before the sequence shown here. System checks flag exceptions, and the assistant proposes a fix. The combined Resolve and Approve step represents supervisor resolution and manufacturer or agency approval of changes; it does not collapse their separate authority. The agency submits the approved time, then the invoice is generated from that record. The action colors show the primary responsibility. This is a proposed workflow, not measured runtime behavior.

The first captured prototype state opens filters over the worker timesheets table. Switch to the hours dashboard to show worked versus planned hours by area. These are sample end-of-week screenshots, not proof of a live data feed or a validated forecast. In the proposed workflow, hours update as shifts are logged; exception flags and an overtime forecast can prompt review before period close. Distinguish the dashboard’s 9.0 hours of logged overtime from a forward-looking forecast.

Read the difference between recorded 08:00 clock-in and scheduled 16:00 end. The scheduled end is the most likely proposed clock-out, not an observed event. The flag carries event date; Patrick describes age on exception flags. Supervisor confirmation supports the decision. The buttons allow approve, amend, reject. This is a defined default; do not imply an LLM must infer it.

Transition from approved time records into invoice reconciliation and the final send decision.

Trace the five-step reconciliation flow. The system drafts the invoice from approved hours and rates; AI flags issues; a supervisor resolves them; the agency sends the approved invoice to accounts payable; client AP marks it paid. The five stages are a design sequence, not a capture of one completed invoice transaction. A flag is a prompt to review, not a correction or approval.

Use the expanded Reconcile flag card as a concrete example of the authority boundary. The orange overtime exception is a system check; TimeEntry, Policy, and RateCard chips cite the source; the proposed adjustment is prepared for review; D. Marquez can reject, amend, or approve. The screenshot is an isolated captured prototype state and should not be described as a continuation of the invoice totals on adjacent slides. Rates are HR-managed by worker/position and overtime rules are organization-defined.

The two crops show different captured states. Do not animate them as a single uninterrupted transaction: the screenshots contain unresolved prototype totals. Left supports source inspection; right supports the final commitment gate. No claim that the time correction produced the shown invoice total. The dialog says the invoice cannot be edited after sending. Video replacement: verified source → resolved flags → correct total → send gate.

Honest non-result. No new testing or invented failure anecdote. The redesigned screenshots are prototype evidence, separate from the early working demo described in files. Ranking is being tuned. No claim of saved hours, lower overtime, fairness, or adoption.

Close on the unresolved product decision. These are proposed evaluation criteria, not completed research. If the model adds no decision-quality benefit, narrow its role to drafting and explanation. Patrick should supply a personal reflection or real iteration before rehearsing a final script.

Supporting source-of-record view. The capture shows roles/status/rates/hours. Patrick’s HR training-tag rule is described; do not claim a certification detail view is shown. Prototype records use sample data.

Gap identified: staffing tools know placements and rates; workforce tools know coverage and hours. Corrections and reconciliation sit between them. This is an internal competitive synthesis across 14 products: sourcing, scheduling, time, approvals, payroll readiness, invoicing, manufacturing fit, staffing OS fit, and agency economics. The four named vendors are representative examples; ShiftForge is the intended design target, not an incumbent measured in the same market scan. Staffing OS strengths: sourcing to invoicing, agency economics and payroll readiness; common gaps: manufacturing fit, UX and implementation. Manufacturing WFM strengths: scheduling, time compliance and labor-cost reporting; gaps: agency economics and staffing-specific invoicing. Recruiting CRM/SMB tools were also reviewed but had less scheduling or back-office depth. Scores on this slide are the presentation synthesis supplied by Patrick; the older archived CSV uses a different scoring scheme.

Core product decision: retain deterministic eligibility/rates/RBAC. AI may create reversible plan drafts and propose actions. Avoid calling it wholly read-only; source datasets are read access, while draft creation is a bounded write. Model advantage over rules/templates is not established.