Timekeeping, payroll and billing for a US nurse staffing company. Fifteen people open it every working day, and it is the system their pay runs through. The ground Time Doctor covers, built the other way round: no screenshots, and a clock the nurse cannot edit.
Payroll cannot be eventually consistent. A timekeeping bug is not a wrong pixel, it is somebody underpaid, so corrections are a reviewed workflow with an audit trail rather than an edit.
The roster syncs in real time. No "apply changes" button, because a button nobody presses is a roster that is quietly wrong.
The Ask AI agent is read-only by construction. It answers from SQL and Sheets and holds no write tool at all, so the worst case of talking it past its instructions is a wrong sentence, not a changed record.
Both halves of the system, live: the admin's dashboard and the nurse's Chrome side panel.The admin's dashboard, live. The nurse's side panel is minimised — Side panel in the title line brings it back. Invented nurses, hours and pay — neither signs in, and neither sends a request to the client's data.
Real-time multiplayer word battle. Up to eleven people in a room, five ELO tiers, an entropy-driven bot that fills a lobby rather than leaving someone waiting.
Counts devices that reached a game, not devices that opened the app. Guests playing solo or in practice are under-counted, since rounds without an account are not recorded per player — multiplayer is well covered.
—
| # | Mode | Code | Players | Winner | When |
|---|
Job-alert emails become a ranked shortlist. AI extracts and scores the roles; I decide which ones deserve an application.
Database snapshot · exported 2026-09-14 08:24 UTC · latest stored job 2026-09-14 02:13 UTC
Northstar Studio · Remote, Philippines
₱80,000–₱100,000 / month · Full-time
Build Python automations, integrate REST APIs and maintain SQL reporting pipelines. Looking for 2+ years of hands-on experience.
View job details ↗A new role matches your alert
Northstar Studio · Remote, Philippines
₱80,000–₱100,000 / month
Build Python automations, integrate REST APIs and maintain SQL reporting pipelines.
✓ Remote / Philippines eligible
✓ Salary range supplied
✓ New posting · no duplicate key
“Python automations”, “REST APIs”, “SQL”
Skills and experience judged against the profile. No stack inferred from missing text.
Skills 24 / 30 LLM
Experience 22 / 30 LLM
Salary 36 / 40 Code
| Role | Company | Score | Stage | |
|---|---|---|---|---|
| 1 | Integration Engineer | Harbor Labs | 76 | To apply |
| 2 | Operations Analyst | Cedar Works | 68 | New |
| 3 | Python Automation Developer | Northstar Studio | 82 | New |
Counts are real snapshot evidence. Replay is illustrative. Sheet stages cover a subset of stored jobs; source adapters are counted separately.
The engineering behind the page you are viewing: a lightweight frontend, a bounded AI assistant, and an explicit deployment boundary.
Hub status requests use a separate server-side probe. Provider credentials stay on the server.
Hand-written HTML, CSS and JavaScript. Project stories render before network requests. Small scripts add motion, navigation and data views.
Answers from approved portfolio material. A server-side model call, a rolling hourly spend cap, and no tools that can reach the filesystem or database.
An allowlist defines the public output. The build copies public files into dist; the assistant’s private material is maintained separately.
The VPS behind the products. Service reachability and a deployment map now have a dedicated sixth hub panel.
Public health and versions; restricted operational details. A read-only status endpoint is still to be built.
Open Backend / VPS with key 6. Host telemetry remains planned.
From scattered punches to a reviewable exception queue. A working automation system for a synthetic workforce across eight countries.
| Staff | Date / zone | Scheduled | Clock-in | |
|---|---|---|---|---|
| 1 | S-041 · Alex R. | 14 Sep · Manila | 09:00–17:00 | 09:04 |
| 2 | S-042 · Jamie D. | 14 Sep · Manila | 09:00–17:00 | 09:24 |
| 3 | S-043 · Morgan L. | 14 Sep · London | 09:00–17:00 | 09:02 |
Asia / Manila · 14 Sep 2026
late_minutes = 24
grace_minutes = 15
24 > 15 → true
late_arrival
Exception raised with schedule ID and punch evidence.
Schedule policy example, not a legal ruling.DEMO-042 · late_arrival
This sample is routine. The urgent branch remains idle.
Late arrival · +24 minutes
Scheduled 09:00 · clocked in 09:24
Evidence attached · DEMO-042
Scheduled: 09:00 Clock-in: 09:24 Variance: +24 min
1 / 1 exception reviewed
This replay is one record.
Historical detector evaluation is separate.
DEMO-042 · Jamie D.
late_arrival → Approved
Original punch: 09:24
Schedule: 09:00 · Asia/Manila
Historical benchmark, not a live KPI. A sliding window changes the result; the dated measurement keeps its denominator.
One Ubuntu droplet behind Caddy, running the APIs for four products. Everything this page does is a read.
DigitalOcean droplet · 1 vCPU · 1967 MB · 24 GB
1 vCPU
DO-Regular
839 / 1,967 MB
10 / 24 GB
Snapshot taken 2026-09-14 16:12 UTC. Host figures, the service states and the nightly-backup series are a dated reading, not a live feed · the four figures in the header strip are the live probe.