Six months. 600+ hours. 15+ specialist agents handling fire flow reports, proposals, contract review, plan QC, utility research, and more — in production today, on real projects with PE-stamped deliverables. This is the build that proved Firma AI’s architecture works end-to-end inside a live engineering firm.
Reco Prianto is a licensed civil engineer with 26 years of industry experience and the founder of two separate companies: Calichi Design Group — a four-office civil engineering firm operating in California, Oregon, and Hawaii — and Firma AI, the company deploying this technology across the AEC industry. He spent six months building Cael inside Calichi: 600+ hours, 15+ specialist agents, a production system handling Calichi’s full business. Not a prototype. Real projects. Real deadlines. A PE stamp on every output.
Calichi and Firma AI are separate companies. Reco built the system for Calichi. Firma AI exists to build it for yours. The person who built Cael is the person who will build your firm’s AI.
Licensed engineers spending the majority of their time on production work — reports, proposals, compliance documents, contract review — the same deliverables with the same structure on every project. High-value staff on low-variance tasks.
The discovery process surfaced the workflows where licensed engineers were spending time on work that didn’t require a licensed engineer.
Each bottleneck got its own agent. The orchestrator (the firm’s AI) routes incoming work, manages the fleet, and returns the deliverable to the project folder.
The system handles technical deliverables and business operations — because both kinds of work have the same bottleneck pattern.
These numbers are measured in production at Calichi. Not extrapolations, not best cases — the actual time the system takes vs. the manual baseline.
Across all 15 production agents: 10–15 hours freed per engineer per week. At a $150/hr billing rate, that’s $1,500–2,250 in freed billable capacity per engineer per week — not from firing anyone, from clearing the production backlog that was consuming senior staff.
This isn’t a chatbot wrapper. It’s mostly engineered code, with model calls only where judgment is needed — seven layers running together on every job.
Monitors the entire fleet. Handles failures, restarts, and escalations without human intervention.
Receives every incoming request, routes it to the right agent, and manages the job queue.
Each built for one workflow — its own prompt stack, output format, and QC criteria. None are generic.
Shared knowledge every agent draws on: firm config, standards, jurisdictions, templates, project history.
The execution and testing framework. Validates agent behavior before anything touches a real job.
Multi-agent QC gate checks every output before it leaves the system — format, completeness, and accuracy.
Every request runs through all seven layers. Every deliverable clears the QC gate. Nothing leaves until the system says it’s ready.
Your team emails the AI. The AI does the work. A finished deliverable comes back. This is exactly how a fire flow request runs through Calichi’s system today — from staff email to stamped-and-ready deliverable in under four hours.
The licensed engineer reads the delivery note, checks flagged items, and stamps only after independent verification. AI deliverables are PE-ready, not stamp-ready. The final 5–10% is the licensed engineer.
Scope, risk, edge cases, design trade-offs — the engineer decides. The AI surfaces inputs, methodology, and assumptions. The engineer interprets and decides.
The AI doesn’t talk to clients. It produces deliverables your team reviews and delivers. Your client relationships are unchanged.
Production pattern-work moves to the system. Judgment, design creativity, problem framing, and refinement stay with your team. That’s the shift.
Engineers spent most of their day on production — same calculation, same format, same compliance check, done the same way as last time. High-value staff on low-variance tasks.
Engineers write the request (10% of the work), Cael executes it (80%), engineer reviews and stamps (10%). Staff freed to focus on the work that actually requires a licensed engineer.
“AI does not replace humans — it supplements them. Employees now focus on framing problems and refining solutions over the mechanics of the solutions.”— Reco Prianto, P.E. · from the build
Calichi’s deployment took 6 months and 600+ hours because it was built from scratch. Firma AI deploys that proven architecture inside your firm in 2–3 weeks — configured to your identity, standards, jurisdictions, and workflows. The architecture is solved. The customization is what we do for you.