IPS Aleso
Occupational health, booked by conversation
IPS Aleso runs pre-employment, periodic and exit medical exams for construction and staffing companies that send dozens of workers at once. Scheduling lived in spreadsheets and on one coordinator’s WhatsApp. We built Aleso One: a portal where each company books and manages its workers, a back office that runs the clinic day floor by floor, and a WhatsApp AI agent that answers, confirms and escalates by topic — on a multi-tenant backend with row-level security, audit and automations.
Duration
Ongoing · since May 2026
Started
May 31, 2026
Company portal, clinic back office, WhatsApp agent, notifications, scheduling, alerts and audit
Gemini with 8 tools over live data, a curated knowledge base and escalation by topic
92 policies and 6 roles: one company never sees another’s workers
Confirmations, 24 h and 2 h reminders, fasting reminders, changes and results
Aleso coordinates pre-employment, periodic and exit exams for companies that move many workers between job sites and contracts.
The schedule was built in Excel, patient communication went through one coordinator’s personal WhatsApp, and there was no reliable record of who had authorized each appointment — the root of billing disputes with client companies. Clinical results live in an external medical-records system with no API.
- — Manual scheduling in spreadsheets for several client companies, each with its own workers, job sites and rules
- — Patients asking the same questions all day — preparation, fasting, location, what to bring — on a single human WhatsApp
- — No traceability of who booked each appointment, the basis of billing disputes with client companies
- — Daily operation of a clinic with several exam rooms, capacity per time slot, holidays and services with their own hours
Seven coordinated systems, from the scope sign-off in May 2026 to formal delivery with role-based user manuals in September — and still evolving with a real client company in pilot.
- + Multi-company portal · each client company registers workers (one by one or up to 500 from Excel), books exams by service or package in three guided steps, reschedules, follows results and manages its own users
- + Clinic back office · the day panel grouped by floor, an eight-state appointment flow validated on the server, room and professional assignment on arrival, and bulk close of the day
- + WhatsApp AI agent · answers preparation, packages, hours and location, looks up, cancels and requests changes to appointments, reads images and voice notes, and escalates billing or service cases to the right internal line
- + Notification engine · confirmations, 24 h and 2 h reminders, a fasting reminder the night before and status changes, through a persistent queue with retries drained every minute
- + Multi-tenant security and audit · row-level security on every table, append-only audit of critical events and an exportable appointment log for billing
Inside the build.
Brand, interface and system — shown as they shipped.
Not a portal. A clinical operations backend.
Aleso One is a multi-tenant backend with an occupational clinic’s business rules, a conversational agent with real tools over that data, and automated processes that run every minute. The interface is the visible layer; by weight, backend and frontend are close to half and half.
Capacity per floor, not per doctor
Capacity belongs to the clinic at that hour, recalculated by a trigger on every appointment; reception assigns the room and professional when the patient arrives. A five-exam package uses a single arrival slot.
Colombian time as the source of truth
The servers run on UTC, so “already past” and “after hours” are computed in America/Bogotá. Nobody can book a slot that has passed, and each service keeps its own hours.
An agent that checks before it answers
The agent never invents dates or availability: it looks up the catalog, packages and calendar through its tools, answers before it escalates, and raises an alert if it ever commits to a date.
Urgent, not alarmist
In occupational health, “blood” or “pain” show up in ordinary questions. Keyword prefilters plus LLM confirmation catch real urgencies, frustration and sensitive data without flagging “does the blood test hurt?”.
A queue that never drops a reminder
WhatsApp and email go through persistent outboxes drained every minute by pg_cron, with race-safe row claiming, quadratic backoff, a dead-letter queue and per-appointment deduplication.
Hybrid AI Coding
Senior WebMinds engineering steered AI agents (Claude Code) for implementation, with an independent QA agent testing every change in the browser. Architecture, data model, business rules and every client decision were human: 44 use cases, 30 migrations and 7 systems in four months.
Technologies & Tools
The tech stack powering this solution
Beyond the numbers, we delivered a system that transformed how this client operates.
One schedule for every company
Client companies book and manage their workers in their own portal, with real capacity and the clinic’s rules, instead of spreadsheets and scattered messages.
24/7 care without burning out one person
The agent answers the repetitive questions with live data, confirms and reminds appointments, and escalates only what needs a person — to the right person for the topic.
Traceability that backs every invoice
Every appointment records who created it, when, and for which contractor and project, with Excel export. Billing disputes are now settled with data.
- May 20, 2026Scope approved: 44 use cases, mockups and business rules
- Jun 2026Multi-tenant schema with row-level security and audit, catalog and packages, floor-based scheduling engine
- Jul 2026WhatsApp subsystem with queue and pg_cron, AI agent with detectors, RAG and vision; first real message and first appointment in production
- Aug–Sep 2026QA rounds with the client, conversation memory, “answer before escalating” and per-service hours
- Sep 21, 2026Formal delivery with role-based user manuals; billing log and topic-based escalation right after
- OngoingPilot with a real client company and continuous product evolution
Ready to achieve similar results?
Let's discuss how we can transform your business with a tailored digital solution.