Proptech SaaS Case Study
About 8× estimated effective
delivery capacity at peak
Same team size · Already using AI · Peak in May vs January
Proptech SaaS Case Study
A strong product team already using AI individually brought it into a shared delivery process.
91% accepted
Without manual code changes
A strong, fast-moving Proptech SaaS team already used AI individually. It accepted 91% of the tickets GenieWorks produced without developers editing or reworking the implementation.
Human review and comments remained part of the process. Estimated effective delivery capacity reached about 8× at its May peak, with the same team size.
What the 91% acceptance result means
The case-study owner reports that 91% of GenieWorks-produced tickets were accepted without developers manually editing or reworking their PR implementation.
Human review and comments could still occur, and GenieWorks could revise its work in response. This measures acceptance without manual code changes; it does not mean a perfect first attempt or work accepted without review.
The figure is separate from the share of delivered tickets that originated with GenieWorks. It does not isolate the contribution of code assurance or any other single part of the system.
Source: case-study owner’s calculation and definition. The underlying query, exact cohort and reporting period have not been independently verified.
What the AI actually cost
The team reports $400 in total monthly AI/model spend, covered by two $200 subscriptions reused for the delivery workflow. It previously used ten personal subscriptions at $20–$100 each per month.
The recorded token usage was valued at approximately $10,000 per month at equivalent API rates. This is an estimate of what that usage represents at API prices; the actual AI bill was $400.
These figures describe AI/model spending for this adoption. They are not a GenieWorks product price or the total cost of operating a delivery team. The $10,000 equivalent was not a previous bill, and the comparison does not establish a measured reduction in token usage.
Source: case-study owner’s spending figures and confirmation that the API-equivalent estimate uses recorded token usage.
What the 8× peak means
May reached the highest estimated effective delivery capacity in the January–June 2026 report: about 8× January’s baseline. Team size was unchanged, and developers already used AI individually.
The estimate combines recorded human work with estimated GenieWorks effort from delivered changes and specification work.
This comparison covers the team’s customized adoption of GenieWorks. Missing worklogs and estimated effort limit it; it does not establish delivery speed, cost savings, or GenieWorks’ isolated contribution.
Source: corrected CPO Delivery Impact Report, January–June 2026.
Where delivered tickets originated
This separate measure counts tickets originating with GenieWorks. May and June both round to 91%; these percentages do not measure acceptance or manual rework.