Episode 12 · October 8, 2026 · Hosted by Sebastian
Automating a Quote Process Step by Step: From Baseline to Roadmap
We took our own offer process, the one we use to quote every customer, and walked it from as-is to to-be live. Not in one leap but in milestones: an agent drafting offers, offers published on a portal, and contracts triggered on acceptance, each one a change small enough to hand to an implementation team.
One process. Four milestones.
The big takeaway
The to-be is not one diagram you draw at the end. It is a sequence of milestones you build from the as-is, left to right.
Freeze the current state first. Then make one change, checkpoint it, and compare. Each milestone shows exactly what moved, and each one is something a team can actually go and build.
What we walked through
- 01
Freeze the as-is
Our own offer process ran on templates, a manually updated offer table, separate files, a presentation to the customer, and new version numbers every time something changed. We captured it as it was and locked it as a milestone. That is the baseline everyone works from.
- 02
Let an agent draft the offer
First change: an agent with access to the templates, the offer table and the opportunity data drafts the offer from a prompt, then updates the table itself. Two manual steps gone. New milestone.
- 03
Compare, don't describe
Open two milestones side by side. Added and removed tasks are highlighted, and attribute changes show up too. The implementation team gets a precise picture of what to build, without anyone writing a spec.
- 04
A portal instead of a PDF
Second change: offers are published as a page on a portal and sent as a link. Each version is stored, the table updates, and the customer always sees the current one. Another milestone.
- 05
Accept online, and the contracts follow
Third change: the customer accepts in the portal. That triggers the master service agreement and the data processing addendum, pings sales in the team chat, and the agent sets the opportunity to won. The happy path runs end to end with one human step we kept on purpose.
- 06
Work left to right
It depends on the use case, but it often makes sense to improve upstream first and then move downstream. Each milestone builds on a state that already works, so you never have a to-be that depends on five other things being finished at once.
Discuss this episode
Ask a question, share how you would model it, or suggest the next topic.
More episodes
All episodes →
Where Should AI Go First? Prioritizing Processes and Tasks With Attributes
How to prioritise AI initiatives from your process models instead of case by case. We ran two passes: on the process level, two simple attributes and a filter produced a shortlist; on the task level, value potential against feasibility picked the first initiatives. In our example that left five concrete opportunities.
We Drove Our Own Expense Process Close to Full Autonomy
Our own finance operation, taken apart and redesigned from scratch around AI. We modelled the ideal on a green field: snap a receipt and the agent labels, classifies and matches it against payments, with weekly runs instead of a month-end scramble. The diagram became the spec for our developers, and the process has been running live ever since.
Most BPMN Diagrams Get This Wrong
Why mixing departments, systems and roles in the same view quietly breaks a process landscape. We tied each view to a modelling level: on the business level, lanes show responsibilities; on the system level, systems become pools and message flows show their interactions. And we landed on one principle: consistency beats correctness.