We already tried Airtable / Notion / a no-code builder. Why is this different?

No-code is excellent until your process needs real permissions, real integrations, or more rows than the plan allows. This is the version that does not hit a ceiling and that you own outright.

Do we have to abandon our spreadsheets on day one?

No. We migrate the data, and teams typically run both for a week. Spreadsheets get dropped when people stop opening them, not because we said so.

Can it integrate with the systems we already pay for?

If it has an API, generally yes. Bring the list to the mapping call and we'll tell you which ones are cheap and which are their own project.

What happens when we need changes later?

You own the code and it is a conventional stack any competent developer can pick up. If you'd rather we keep building, follow-on sprints are scoped the same way.

What does an agent actually own here?

The repetitive middle of a workflow, with hard boundaries: it never sends money, never deletes, and never decides anything irreversible without a human. Everything it does is logged, and anything outside its remit goes to the exception queue.

How do we know an agent isn't quietly doing the wrong thing?

Every autonomous action is recorded with its inputs and reasoning, and the exception queue makes silence visible. If an agent stops being useful you can switch that step back to manual without the tool breaking.

Our process isn't documented anywhere. Is that a problem?

It is the normal case. Process mapping exists precisely because the real workflow lives in people's heads and in three unnamed spreadsheets.

← ALL SERVICES

PRODUCT 02

2–4 weeks

Ops-to-Software Sprint

Replace spreadsheets, chased approvals and copy-paste between systems with software — and agents — that run the process for you.

Start this project →€4k – €20k+typically €7k – €11k

agents
node
typescript
next.js
postgres
redis
tailwind

WHO THIS IS FOR

Built for you if…

01
SMBs and growing teams drowning in spreadsheets, approvals and manual coordination.
02
Operators who need a custom dashboard, lightweight CRM, or internal tool that fits their exact process.
03
Companies that tried no-code tools and hit the ceiling — or tried an AI pilot that never left the pilot.

WHAT YOU GET

Everything included.

Full workflow discovery

We sit with the people doing the work and map the real process — including the undocumented parts — so we build what is actually needed instead of what the org chart says.

The tool itself

A custom internal tool, operations dashboard, lightweight CRM, or workflow automation, built around your process rather than a template.

Role-based access control

Users, roles and permissions so the warehouse sees the warehouse and finance sees finance.

Clean modern UI

An interface non-technical people can use on day one without a manual. Keyboard-friendly, fast, and responsive on the phone your team actually carries.

Data migration from what you use now

Your existing spreadsheets, exports or legacy database imported and validated, so the tool launches with real data.

Agents on the repetitive steps

The parts of the workflow that are rules plus judgement — triage, chasing, data entry between systems, first-draft responses — handed to agents with explicit escalation paths. Where a plain script is the right answer, you get a script; we don't bill you for a model you don't need.

A human exception queue

Everything an agent won't decide lands in one reviewed queue with the context attached, so nothing falls into the gap between automated and forgotten.

Integrations where they save time

Email, Slack, calendars, accounting or whatever your process already depends on — connected via API so double entry disappears.

Deployment + basic documentation

Hosted, backed up, and documented well enough for a new hire to be useful in an afternoon.

2 weeks of post-launch support

The window where real usage finds the rough edges. We smooth them.

WHAT IT LOOKS LIKE

Some of what you get back.

AGENT BOUNDARIES — WRITTEN, NOT ASSUMEDhandover doc

MAYDraft replies, classify, enrich records, chase overdue steps
MUST ESCALATERefunds, anything over threshold, unrecognised counterparty
NEVERMove money, delete records, email customers unreviewed

Every autonomous action logged with its inputs. Anything outside the remit lands in a human queue with context attached.

COST & LATENCY — ENFORCED IN CODElast 24h

cost / run€0.11
ceiling €0.50
p50 latency740ms
budget 2s
daily spend€38
cap €80 → queues
escalation rate6.2%
tuned weekly

Budgets are code, not a monthly surprise. Crossing the per-run ceiling switches to a cheaper path; crossing the daily cap queues and alerts.

HOW IT WORKS

The process.

01
01
Process mapping call
Days 1–2
We walk through the current workflow end to end, find where time leaks, and pick the smallest tool that removes the most manual work.
02
02
Rapid design of the core flows
Days 3–5
Data model and the two or three screens the job actually runs on. Reviewed with your operators before a line of production code.
03
03
Build + feedback loops
Weeks 2–3
You get a working URL early and it stays live. Your team clicks around each week and we correct course while corrections are cheap.
04
04
Deploy and hand over
Final days
Data migrated, accounts created, deployment finished, and a walkthrough with the people who will use it daily.

TIMELINE & PRICING

What it costs.

DURATION

2–4 weeks

BUDGET RANGE

€4k – €20k+

Typically €7k – €11k

PAYMENT

40% to start · 40% at midpoint · 20% on delivery.

WHERE IN THE RANGE YOU LAND

·€4k–7k: one workflow, one or two roles, data that migrates cleanly.
·€7k–11k: where most of these land — several roles, agents on the repetitive steps, two or three integrations.
·€11k–20k: multi-department rollouts, messy legacy data, or integrations with systems that fight back.
·€20k+: company-wide operational software is a programme, not a sprint — see below.
·Fixed price once scope is locked, so an overrun is our problem rather than your invoice.
·Hosting and third-party service costs are billed to your accounts.

BEYOND THE SPRINT

Replacing how an entire company operates — several departments, dozens of users, migration off a system of record — is €40k – €150k+ of work and runs as a phased programme. The sprint is deliberately the small version: one process, proven, before anyone commits to that.

STACK

What we build it with.

Node
TypeScript
Next.js
Agents
Postgres
Redis
Tailwind

NOT INCLUDED

Where the line is.

×Replacing your ERP or accounting system of record.
×Native mobile apps — the tool is responsive web unless quoted otherwise.
×Ongoing data entry, operational staffing, or process management.
×Hosting and third-party subscription fees.
×Open-ended feature requests after the scope is locked — those become the next sprint.

Contracts, ownership & handover →Security & data handling →

FAQ

Questions we get.

We already tried Airtable / Notion / a no-code builder. Why is this different?: No-code is excellent until your process needs real permissions, real integrations, or more rows than the plan allows. This is the version that does not hit a ceiling and that you own outright.
Do we have to abandon our spreadsheets on day one?: No. We migrate the data, and teams typically run both for a week. Spreadsheets get dropped when people stop opening them, not because we said so.
Can it integrate with the systems we already pay for?: If it has an API, generally yes. Bring the list to the mapping call and we'll tell you which ones are cheap and which are their own project.
What happens when we need changes later?: You own the code and it is a conventional stack any competent developer can pick up. If you'd rather we keep building, follow-on sprints are scoped the same way.
What does an agent actually own here?: The repetitive middle of a workflow, with hard boundaries: it never sends money, never deletes, and never decides anything irreversible without a human. Everything it does is logged, and anything outside its remit goes to the exception queue.
How do we know an agent isn't quietly doing the wrong thing?: Every autonomous action is recorded with its inputs and reasoning, and the exception queue makes silence visible. If an agent stops being useful you can switch that step back to manual without the tool breaking.
Our process isn't documented anywhere. Is that a problem?: It is the normal case. Process mapping exists precisely because the real workflow lives in people's heads and in three unnamed spreadsheets.

BUDGET · €4k – €20k+

Still running the business on spreadsheets and reminders?

Describe the process that wastes the most time each week. We'll tell you what it takes to replace it.

Start this project →