✨Schedule from promptLivePro
Build a schedule from a sentence
Describe the week in plain English — coverage needs, who's off, who prefers what — and PeopleBridge drafts the schedule. You tweak, you publish.
How it works
Claude Sonnet 4.5 reads your roster, availability windows, time-off requests, and historical preferences. Returns a draft schedule as a structured payload that hits the same validation pipeline your manual schedules do — no special path, no hallucinated shifts.
In practice
"Cover Friday dinner rush + weekend, give Maria Tuesday off, prefer evening folks after 5pm" → 7 days × 14 shifts drafted, 0 conflicts, 0 overtime risk.
⚡Conflict detectionLivePro
Every conflict caught before you publish
Overlaps, time-off violations, double-booking, coverage gaps. Red, yellow, green — at a glance, before a single notification goes out. Part of Pro, alongside overtime warnings before publish (see the overtime predictor below).
How it works
Runs server-side on every shift insert and update. The same validation pipeline that catches manager mistakes catches AI-suggested mistakes. Conflicts are explained in plain language, not just flagged.
In practice
Pre-publish: "Overlap: Maya R. already on 11a–7p, cannot also take 2p–10p. Time off: Jordan T. has Sunday approved off."
🎯Smart open-shift rankingLivePro
Open shifts go to the right person first
Drop an open shift — PeopleBridge ranks candidates by availability, hours worked so far this week, acceptance history, travel distance, and skill match. The most-likely "yes" gets first dibs.
How it works
Explainable scoring: each candidate shows why they're ranked where they are. No black box. You see the inputs, you can override the ranking, you can flip back to FCFS at any time.
In practice
Open shift Fri 2–6 pm → Top candidate: Marcus (rank 1, 92% match) — Available Fri afternoons, 18h this week (capacity), 4/4 last accepts, 2 miles from location.
💰Labor watchLivePro
Labor cost watch with anomaly alerts
Set a target labor percentage of revenue. PeopleBridge watches it daily against Toast sales data and alerts you when you're trending hot before the pay period closes — not after payroll.
How it works
Daily cron job compares projected hours × wages against actual sales pulled from the Toast integration. Threshold is per-location. Notifications go to the owner via Zoho email + in-app push.
In practice
Watters Creek labor at 34.2% of sales this week vs target 28%. Suggested: drop Sunday 7–11p shift (saves ~$180, low historical traffic in that hour band).
📍Smart clock-inLivePro
Smart multi-location clock-in routing
Float staff who cover multiple stores get auto-routed to the closest geofence at clock-in. No more "I punched in at the wrong location" payroll fixups.
How it works
On clock-in tap, the device GPS is matched against every store geofence the employee has access to. Closest match wins. Manager override always available. Each punch is tagged with its actual location for cost-center allocation.
In practice
Sarah covers Frisco South + Watters Creek. Punches in at 9:58 AM. GPS shows she's 240ft from Watters geofence (radius 300ft) and 2.3 miles from Frisco. Auto-routed to Watters. No tap required.
🔔Smart re-notifyLivePro
Smart re-notification — only when it matters
Employees don't see every push notification. PeopleBridge re-notifies only when the message is urgent (shift starts soon, manager approval needed, time-off response) and the recipient hasn't opened the app.
How it works
Presence-aware suppression: if the recipient's tab is focused on the relevant chat or page, skip the push entirely. If they've been inactive 30+ minutes, re-notify once at the urgency threshold. Otherwise, in-app badge only.
In practice
Shift starts in 30 min and Marcus hasn't clocked in or opened the app. → Push + email fires once. If he was already in the app on the schedule page 5 min ago, → no push fires.
📄Doc extractionLivePro
Document extraction on onboarding
New hire uploads a driver license photo and a voided check during onboarding. PeopleBridge extracts the data automatically: name, address, DOB, license number; routing and account numbers from the check.
How it works
Claude vision API reads the document, returns structured fields, populates the W-4/I-9/direct-deposit form. Employee reviews + corrects before submit. Original document stored encrypted in Supabase Storage with masked-display in the UI.
In practice
Illustrative example: the new hire photographs their license and a voided check, reviews the pre-filled W-4, I-9 and direct-deposit fields on their phone, fixes anything that looks off, and submits — no re-typing from paper.
⏱️OT predictorLivePro
Overtime predictor before publish
Pre-publish warning when an employee is on track to cross 40 hours that week — fix it before the schedule goes out, not after payroll runs.
How it works
Sums projected weekly hours across all locations for each employee and compares them against the weekly 40-hour overtime threshold. Flags borderline cases (38-40h) so you can decide vs. preventing. The Overtime Watch report shows who's tracking toward 40 hours during the week.
In practice
Pre-publish flag: "Jordan at 38h. Adding Sun 3–11p (8h) pushes to 46h → 6h at 1.5× = $87 in OT wages. Move shift to Tue instead? (Tue Jordan currently at 0h)."
📈Demand forecastLivePro
Demand forecasting from POS history
Staffing recommendations for next week based on your own POS sales for each weekday and hour. Shows what you should staff before you publish what you are staffing.
How it works
Averages the last 4 weeks of hourly POS sales (Toast, Square or Clover) for each weekday, hour and location, divides by your sales-per-staff-hour target ($80 by default, adjustable), and compares the result with scheduled coverage. Gaps show as soft warnings; you decide.
In practice
"Saturday 12–1p averaged $410 in sales over the last 4 Saturdays. At $80 per staff hour that suggests 6 people; you have 4 scheduled."
📊Drift detectionLivePro
Drift detection between Toast & schedule
Spots when actual clock-ins drift away from published schedules — chronic late starts, early-outs, no-shows, ghost punches. Highlights patterns instead of just exceptions.
How it works
Daily comparison of time_entries vs. shifts table. Patterns are surfaced at the employee × day-of-week level: "Marcus is 12 min late on average for Friday opens (8/10 weeks)." Not just "Marcus was late today."
In practice
Weekly drift digest: 3 employees with >10 min average lateness on a specific shift, 2 employees consistently clocking out before scheduled end. Actionable on the spot.
📝Weekly digestLiveFree
AI weekly operations digest
Monday morning summary email: labor % vs. target, overtime trend, top 3 drift patterns, time-off requests pending, anomalies in clock-in or sales. One scroll, no dashboard required.
How it works
Claude synthesizes the previous week's data into a plain-English briefing. Numbers are pulled from the same RPCs that power the Insights page; the AI just narrates them. Always opt-in per owner.
In practice
"Week of May 26: Labor at 29.4% (target 28%, $340 above). Two OT flags hit (Jordan, Maria — Sun). Three open shifts unfilled at McKinney. 4 time-off requests pending your review. Tip pool reconciles to penny."
🌎Auto-translateLivePro
Auto-translate for multilingual teams
Messages, announcements, and schedule notes auto-translate per recipient's language preference. Manager writes in English; back-of-house reads it in Spanish.
How it works
On-the-fly translation via Claude when the recipient's profile language differs from the message author's. Both original and translated text are preserved; recipients can toggle between them. Part of Pro.
In practice
Owner sends announcement "Tomorrow is Memorial Day — we open at noon" in English. Maria's profile is set to Spanish; her notification reads "Mañana es Memorial Day — abrimos al mediodía." Tap to see original.
💬Ask PeopleBridgeLivePro
Ask PeopleBridge — questions in plain English
Owners and managers ask questions about their own business — "Who's close to 40 hours this week?", "Who was late this pay period?", "What was labor % of sales last week?" — and get a straight answer from live data.
How it works
Claude answers by calling read-only lookups for hours, overtime, shifts, attendance, time off and (owners only) sales. Every lookup runs under the user's own login, so a manager only ever sees their own locations, and pay rates stay owner-only. It can't change data and never sees SSNs or bank details.
In practice
"How much overtime did we have last week?" → "6.5 hours across 2 people: Jordan 4.0h (Frisco), Maria 2.5h (McKinney). Both from Sunday closes."
✅Payroll reviewLivePro
Payroll review before you export
One click before export checks the whole pay period: missed clock-outs, 12-hour entries, overlapping punches, no-shows, staff with no pay rate, and weekly overtime. Each problem comes with a one-tap fix.
How it works
Rule checks run on the period's actual punches and shifts (overtime per Monday–Sunday week). Fixes open the normal audited edit dialog — a missed clock-out is pre-filled with the scheduled end time. An optional AI summary tells you what to fix first.
In practice
"Fix before export: Ana never clocked out Mon Oct 19 (shift ended 5:00 PM) · Bo has no hourly rate — 4.0h would export at $0. Check: Ana 5.0h overtime, week of Oct 12."
AI features FAQ
Which AI features are free, and is there per-prompt billing?
The Free plan includes the Monday AI digest email. Every other AI feature on this page — schedule from a sentence, Ask PeopleBridge, payroll review, auto-translate, smart open-shift ranking, labor alerts and the rest — is part of Pro. There is no per-prompt billing and no metered AI usage on either plan. Free is $0 forever for 1 location and up to 10 employees; Pro is $2 per employee + $10 per location, per month.
What AI model does PeopleBridge use?
Claude from Anthropic: Claude Sonnet 4.5 for most workflows (schedule-from-sentence, weekly digest, auto-translate) and Claude Opus for Ask PeopleBridge and the payroll review summary. Claude vision API for document extraction. Server-side validation pipelines for conflict detection, OT predictor, and demand forecasting — those use deterministic logic, not LLMs, so they're fast and explainable.
Are AI suggestions automatically applied to my schedule?
No. AI suggests; you are in control of every decision. Every AI output — drafted schedule, conflict resolution, open-shift ranking — surfaces in the UI for you to review, edit, and approve. Nothing is published, notified, or paid out automatically based on AI alone.
Do I need to be technical to use the AI features?
No. Setup is self-serve: describe your business in a sentence or two and the AI setup assistant fills in your industry, timezone, first location and positions, then the setup wizard lets you check each step, and you can import your team from a CSV export of your old app. The AI then works from your own data (schedules, timesheets and POS sales) with nothing to configure. On Pro, you can also ask PeopleBridge questions about your business in plain English. Stuck? Email info@peoplebridge.app.
Is there a free trial of the AI features?
There's no time-limited trial. The Free plan includes the Monday AI digest and never expires (1 location, up to 10 employees, no credit card). The other AI features come with Pro at $2 per employee + $10 per location, per month, and unlock as soon as you switch.
Where does my data go when I use AI features?
AI calls hit Anthropic's Claude API directly from our backend. Anthropic does not train on API-tier data. Your data does not leave the request-response cycle. Document extraction images are encrypted at rest in Supabase Storage with row-level security and masked display in the UI.