Manual business processes
Employees copy data between email, spreadsheets, forms and business software — every day, by hand.
From business process analysis to production-ready automation. I find the bottleneck, design the system, direct the agents that build it, and stand behind what I control. Agents write the code. I own the outcome — the part we wrote into the contract.
Agents write the code.
I own the outcome.
Ownership here is concrete, not a slogan. I sign for what I control and what we write down: the design, the tests, the delivery, and how the flow behaves in production. Spec Machine is my internal exoskeleton — a machine that remembers every failure, with a human who signs off. I do not promise your revenue or your market, and I do not hide who typed the code.
You do not need to know whether this is AI, automation or custom software. You need the problem to stop.
Employees copy data between email, spreadsheets, forms and business software — every day, by hand.
Invoices, orders, reports and forms need repetitive manual review before anything can move.
CRM, ERP, accounting software and internal tools do not talk to each other, so a person is the integration.
The company experiments with AI, but there are no reliable workflows, permissions or audit trail.
Management has no timely view of delays, errors, costs and performance — answers arrive too late to act.
Off-the-shelf software does not fit how the business actually works, and nobody is building the missing piece.
Not sure which one is yours? That is where we start. Write one paragraph about the process and I will tell you what is worth automating — and what is not.
A machine alone cannot promise anything. A person with a system can promise, prove and sign.
A junior delivers something that runs on their laptop. I deliver FOR UPDATE SKIP LOCKED, a dead-letter queue, retries with jitter and a test for every path. That is why the pilot can carry a money-back guarantee at all.
You see 200 invoices a month. I see PDF → OCR → classification → database → report, with no human in the loop. That is why Company Intelligence maps the process first and picks technology second.
No Kubernetes for three webhooks. Postgres, a rule book and a Docker sandbox on a VPS do the job. Only the Saboteur gets an expensive model, because that is the one that has to break bad architecture. Result: about $0.004 per run, not $0.15.
There is no “the AI said so”. Every design passes at least three ADRs, plus idempotency, quiet hours, opt-out and 50 recorded incidents. If it does not pass, the job is needs_human — not done. That is why you get no duplicates and no flaky automation.
Business Analyzer, Solution Architect, Builder that writes SQL, zod contracts and the workflow, tested in an isolated container, and a Scoper that hands you the quote with dates. You talk to one person and get the whole chain.
Spec Machine is not an autopilot — it is an exoskeleton. I find the company and understand the process; the machine maps it and finds where time leaks. I ask the questions; the machine searches 50 incidents so we do not repeat the mistake from 22 October. I make the call; the Saboteur is there to break it if it is weak. I sign; there is an approve button, never an auto-deploy.
Webhook that answers in 300 ms, idempotency that actually works, DLQ with replay. The lead that arrives twice is not a second lead.
Architect, historian, saboteur, builder, scoper. Every decision cites the rule and the incident that paid for it — not “best practice”.
Trace per job, cost per stage, retry counters, dead letters. When it breaks at 3 a.m. there is a log, not a guess.
What the problem was, what I built, what my role was, and how you can check it yourself. Anything not measured is not claimed.
The command center is not a mockup: it runs on the same database as the swarm, and every number below is read from it.
Every ADR cites the rule and the incident that paid for it — [R01 + C1]. If the model ignores history, the job stops and waits for a human instead of inventing advice.
Idempotent webhook, outbox with 1s/5s/25s/125s backoff, dead letters with replay.
13 modules, 6 interactions, zero console errors — on a fresh database, from scratch.
The thing your team still does by hand. One paragraph.
Input, output, success criteria, price, start time. Same day.
Progress notes instead of questions. I ask once, in writing.
Code, schema, tests, a 2-minute Loom, 14 days of fixes.
Twelve questions. You get the risk level, the articles that apply (5, Annex III, 50) and the controls you are still missing. It is the same classification I run before quoting an evidence pack.
Async-first by default: written updates, no status meetings. Calls and workshops when the project actually needs them — I do not avoid people, I avoid unnecessary meetings.
We look at the process as it runs today: tools, people, bottlenecks and what the business actually needs.
You get a written solution architecture: scope, timeline, acceptance criteria and a cost estimate before anything is built.
I develop, integrate and test against those acceptance criteria — with tests, logs and a recording of it running.
Monitoring, documentation, maintenance and the next improvement, in a monthly plan.
I understand the process before I pick the technology. If the answer is a form and a rule, I say that instead of selling an agent.
Analysis, architecture, development, integration, delivery. One person responsible for the whole chain, not a handover between three vendors.
Tests, logs, error handling, security and documentation are part of the delivery — not a later phase nobody buys.
You talk to the person who designs and builds the system. No account manager, no translation layer.
Start with an assessment if you are not sure what to build, a pilot if you are, or a partnership if the systems keep growing. Prices below are proposals — the real number follows the scope.
For a company that knows something is wrong but not yet what the right solution is.
For a company that wants to see the solution working inside a real process.
For companies that need someone to own the AI systems long term.
Payment by card through Creem, or a contract with an invoice — same price, different paperwork. Company details, purchase orders and NDA on request.
Because a flow I cannot harden in two days is a flow I should not take as a pilot. Bigger work is scoped after.
The outcome is written before I start. If I miss it, the money goes back and the code stays with you.
I do the plumbing AI needs to survive: queues, retries, idempotency, compliance, audit. The model is the easy part.
Yes — that is the point. Contractor first, seat second. Remote, CET, 4h overlap with EST.
I reply with a fixed scope and a start time — same day, in writing.
I work at the intersection of business operations, software architecture and AI automation. My focus is not another chatbot — it is systems that solve an operational problem and can be tested, maintained and used in production.
Before software, I spent years in organisations where process, measurement and standards were the job: laboratories, quality systems, international certifications. That is where I learned to ask what "it works" actually means, and to write it down before building anything.
Businesses that have outgrown spreadsheets, manual processes and disconnected software — and need systems that fit how they actually operate.
Not sure whether your process can be automated? That is where we start.
Tell me what isn't working, how you handle it today and what you want to improve. I review the request and come back with a recommended next step — not a generic sales call.