From ticket to shipped code
ticket → coding agent → AI review → human approval → shipped
time to first change · number of fixes · review time
In 2–4 weeks we take one department and test whether AI can turn its work into measurable, repeatable workflows — with an owner, data, human-or-AI approval modes and before/after metrics.
Who it’s for: For teams that already have an AI demo, or suspect a specific process is ripe for automation.
Not training, not a capabilities demo: if the process has no owner, or AI can’t get the data, start with the Opportunity Map.
A demo looks great on stage, but has no owner, metrics, data, integrations or risk control. The sprint turns it into a workflow that has all of that — or ends with an honest decision that it’s not worth it.
The sprint works if you have:
The agreement is simple:
ticket → coding agent → AI review → human approval → shipped
time to first change · number of fixes · review time
classification → priority → drafted reply → approval → send or escalate
first response time · cases handled · escalation rate
plain-language query → interpretation → mapping to data → results & recommendations
usage · conversion · returns
from €9,500net
A fixed price for a fixed scope, set before we start — it depends on the number of integrations and data sources.
Tell me which process you want to automate and which systems it connects to. Within 1–2 business days I’ll reply with a price, or with the questions I need answered to set one.
Or by email: michal@jaskol.ski
As of: November 2026
Conservative assumptions, math in the open: what manual handling of a process costs — and what stays in the company when automation takes over part of it. Change the values to yours.
The math
saving over 12 months
€72,000 — saving over 12 monthsAn estimate built on the numbers you enter. That’s why the Sprint ends with before/after metrics and a decision: scale, iterate or kill.
Compare it with the Sprint price: email me and you get a quote within 1–2 business days.
2–4 weeks. The price is fixed for a fixed scope and depends on the number of integrations and data sources — I set it in a conversation or by email, always before we start.
The map picks the process, the sprint changes it. The map runs 1–2 weeks and ends with a decision and an experiment backlog. If you already know which process hurts most, skip the map and start with the sprint.
I need one process owner available throughout, plus data or examples of real cases. The rest of the team joins at two points: describing the process and testing the prototype. Without an owner on your side, the sprint doesn’t work.
A workflow spec splitting the work between people and AI, a working prototype on your data, autonomy boundaries and control rules, before/after metrics — time, cost, quality, scale — and a decision: scale, improve or kill.
No. The sprint is capped at 2–4 weeks and never drifts into an open-ended engagement — afterwards you owe me nothing. You can scale on your own, book another sprint, or take Advisory if you want a second pair of eyes.
Handoff to your team, a scale plan, another sprint or ongoing advisory — depending on the result and the decision.