Most teams can name the review they have to pass. Fewer can say what that reviewer will ask them to produce, who inside the company owns each item, and which decisions have to be settled before anyone opens an editor. That gap is where the questions below come from, and it is worth sitting with them before a build plan hardens.
When should compliance enter the build?
The instinct is to treat review as a stage near the end, something you prepare for once the product exists. That framing feels efficient because it keeps the early weeks focused on features. It also quietly fixes the answers to questions like age assurance, consent handling, audit trails and data residency months before anyone asks them. By the time a reviewer raises one, the architecture has already decided the answer. A good outcome depends on when you accept that these are design inputs, not paperwork, and on whether the person who can commit to that sits in the room early enough to matter.
What does a useful first week actually produce?
Plenty of discovery weeks end with a deck, a proposal written to win the work, or a document nobody reopens. The question worth asking is what physically exists on Friday that did not exist on Monday, and whether it would still be useful if you handed it to a different supplier. A good answer depends on artefacts, not conversation: a map of the gate and its approver, an evidence list with a named owner per item, and a clear record of what would have failed if tested against that list. If the week cannot survive being handed to someone else, it was a pitch.
Which problems tend to surface too late?
Four keep coming up. Evidence nobody is producing, where the current setup cannot reconstruct audit trails or consent logs after the fact. A second gate nobody named, usually a market, partner or app store with its own date that never entered the plan. An approver who has not seen the product, whether that is a compliance lead, clinical safety officer or security owner. And scope too wide for the fixed date, where cutting deliberately later costs far more than cutting early. Each is cheap to raise while it is still a line on a plan and expensive to discover in month five.
Who needs to be in the room?
The temptation is to delegate the week to whoever is least busy. That usually produces a plan nobody with authority has agreed to. The decisions that cost most to undo are sequencing decisions, and they belong to the person who can sign them off. A good answer depends on a founder or equivalent giving a few focused hours across the week, plus someone who can answer questions about existing systems. Nobody needs to be pulled off their work full time, but the wrong person in the room makes the whole exercise decorative.
What does a good result look like?
Not a document. A sequence that runs backwards from a date nobody will move, a written list of what is deliberately not in version one, and a price attached to a fixed scope instead of a day rate guessing at an unknown. The test is whether the review and the build share the same evidence list, so nothing gets estimated twice from a blank page.
The full guide at how the Week-One Review works, day by day and what it costs to start sets out what happens on each of the five days, the four artefacts you keep, how the fee is credited against the build, and the terms if you walk away.
Top comments (0)