Skip to content
From spreadsheets to a single source of truth
Engineering · HVAC
Web & App Development AI & Automation Consulting & Strategy

DYMM Ingeniería

From spreadsheets to a single source of truth

DYMM Ingeniería quotes, buys, installs and maintains HVAC systems for clinics, laboratories, offices and industrial plants in Colombia. Its whole process lived in Excel, SharePoint and email. In four months we built Dymm OPS: a nine-role platform that takes a job from the quote — priced with DYMM’s own cost analysis and assisted by AI — to the requisition, the purchase order, the scanned warehouse release and the work order on the technician’s phone.

Duration

Ongoing · since June 2026

Started

June 4, 2026

From spreadsheets to a single source of truth
12
Systems in production

Quoting, AI, purchasing, warehouse, tools, work orders, cost centers, supplier portal and more

9
User roles, one platform

From management and engineering to warehouse, field technicians and external suppliers

1,200+
Catalog items wired into quoting

Hundreds of them carrying DYMM’s full cost-analysis breakdown

66/66
Tables under row-level security

80 policies, isolation by organization and by supplier

The Challenge

DYMM runs a mature, certified process, but it lived in spreadsheets, SharePoint folders and email.

With demanding clients, every error in quantities, prices or traceability was a risk.

  • — Quoting depended on an expert Excel: material, accessories, labor, fixed costs, sales factor and the Colombian AIU regime were mastered by only a few people
  • — Purchasing had no check against the quote: requisitions were not matched to the approved quote or to stock already in the warehouse
  • — No traceability in the warehouse or tool room: what left, for which job, at what cost and who received it
  • — Scattered information and slow decisions: approvals by email, quality forms in folders, no dashboard and no audit trail per cost center
Our Solution

Twelve systems in production after roughly four months of construction, built around DYMM’s real way of working and still evolving with the team.

  • + Quoting engine · DYMM’s six quote types, its cost-analysis formula reproduced to the peso, the AIU regime with VAT only on profit, per-item currency with the official exchange rate, and branded PDFs
  • + AI inside the workflow · adjust a quote by conversation, a per-m² pre-design that learns from approved quotes, and a system assistant that knows the record you have open
  • + Purchasing against the quote and the warehouse · requisitions prefilled from the approved quote, overages justified and emailed to management, three-supplier comparison, purchase order, receipt and invoice
  • + Warehouse, tools and field work · releases in DYMM’s own format with five sign-offs, barcode scanning from a USB reader or phone camera, stock maintained by database triggers, and work orders on the technician’s phone
  • + Cost centers, supplier portal and audit · cost centers created automatically on quote approval with DYMM’s nomenclature, a portal where each supplier manages its documents and orders, and an audit log of every change
Selected Frames

Inside the build.

Brand, interface and system — shown as they shipped.

Requisition checked against the quote and the warehouse
PURCHASING · REQUISITION
Every line measured against the approved quote; what is in stock ships, only the gap gets bought
Warehouse release order in DYMM’s format
WAREHOUSE · RELEASE ORDER
DYMM’s own release format: project, materials, inventory trace and five sign-offs
Material release with barcode scanner on mobile
SCANNER · MOBILE
Scan, adjust quantities, register the release
AI pre-design per square meter by project type and spaces
AI PRE-DESIGN · PER M²
Project type, system and spaces in; airflows, items and a reference price that learns from approved quotes out
Technician work order on mobile
WORK ORDER · TECHNICIAN
The job, equipment, materials and tool scans in the field
Under the hood

The hard part is the rules.

Dymm OPS is not a website: it is the company’s operating system. The hard part lives in the rules — the cost-analysis formula, AIU with VAT on profit, quantity control against the quote and the warehouse, concurrent document numbering, stock by triggers and permissions by row.

66/66
Tables with row-level security
42
Database triggers
46
Versioned migrations
120
Server actions in 34 modules
148
End-to-end tests, desktop and 360 px mobile
82
Screens
01

A spreadsheet turned into a pricing engine

DYMM’s macro-driven cost analysis is reproduced exactly, including its round-up to the thousand, and the component breakdown of hundreds of catalog items was loaded from the original workbook — so the platform reproduces the list price.

02

The AI proposes, the engineer decides

In the quote editor, Gemini returns structured change proposals that are validated on the server. Prices for new items come from the catalog, not the model; the user ticks what to apply, and stale proposals are discarded if the quote changed.

03

Client lists matched to the catalog

The quote importer reads the customer’s own Excel, keeps their numbering and suggests catalog prices through fuzzy matching on tokens, trigrams, units and sizes, each with a confidence level.

04

What is in stock ships, only the gap gets bought

When a requisition is approved, each line is checked against inventory; the release order reserves stock, partial deliveries send the difference back to purchasing, and stock moves only through database triggers.

05

Numbering that survives concurrency

“Read the last code and add one” collided under simultaneous creation and broke past 999. Row-locked counters in the database fixed it, verified with twenty simultaneous creations.

06

Hybrid AI Coding

A senior WebMinds architect owns the design and every decision with DYMM, AI agents (Claude Code) accelerate implementation, and an independent end-to-end QA suite runs before every deployment. That is how twelve systems reached production in about four months.

The Stack

Technologies & Tools

The tech stack powering this solution

Server Actions
Next.js
End to end
TypeScript
Postgres · Auth · Storage
Supabase
Triggers · Row security
PostgreSQL RLS
AI in the workflow
Gemini
Email
Resend
Branded documents
React-PDF
148 E2E tests
Playwright
Hosting · Cron
Vercel
Claude Code
Hybrid AI Coding
The Impact

Beyond the numbers, we delivered a system that transformed how this client operates.

01

Quoting no longer depends on one expert

DYMM’s cost analysis, AIU regime and price list live in the platform. Any engineer produces a consistent quote, and AI helps adjust it without inventing prices.

02

What gets bought is what was quoted

Every requisition is measured against the quote and the warehouse: overages are justified and reported to management, and only what is missing gets purchased.

03

Traceability end to end

From the quote to the cost center, the purchase order, the signed warehouse release and the work order on the technician’s phone — with row-level permissions and an audit trail.

Timeline
  1. Apr–May 2026
    Process diagnosis, proposal approved, kickoff and design mockups
  2. Jun 4, 2026
    Construction starts: roles, cost centers, projects, quotes and the first AI features
  3. Jun 22, 2026
    Process session with management: quoting rebuilt around DYMM’s real method
  4. Jul 2026
    Six quote types, branded PDF, AI pre-design, full purchasing cycle, inventory, mobile work orders, tools, quality documents, supplier portal and AI assistant
  5. Aug–Sep 2026
    Role-by-role testing with the client, then exchange rate per item, quote importer, atomic numbering, scanner releases, cost-analysis formula and “Adjust with AI”
  6. Ongoing
    The platform keeps evolving with DYMM
Start Your Project

Ready to achieve similar results?

Let's discuss how we can transform your business with a tailored digital solution.

Hi! I'm Atlas