Kilvin is an AI-native agency that builds private custom software for non-technical teams. It fits an operator who has a workflow too specific for off-the-shelf SaaS but does not want to hire an internal engineering team for every internal tool.
What it does
The YC profile describes a private, secure workspace of custom applications built around a company’s workflows and delivered in days rather than months. The promise is a configured system that fits the business instead of asking the team to adapt to another generic product.
Kilvin’s older BrowserBook launch is useful product history. It described a Jupyter-like browser-automation IDE with an inline browser, Playwright coding agent, built-ins for screenshots and authentication, and an API for deployed automations. The current YC positioning is broader custom software for non-technical teams, so I would treat BrowserBook as a prior product direction, not assume it is the current offer.
The buyer decision is the boundary between a custom application and a service engagement. Kilvin may be a good fit when the workflow is important, repeatable and owned by a small team. It is a weaker fit when the need is a standard CRM, an open-ended software project or a process that no one can clearly specify.
Founder context and tradeoffs
The YC record identifies Christopher Schlaepfer as CEO and Jorrie Brettin as CTO. The public profile provides little more founder detail than their roles and the company site, so I am not inventing a deeper background.
Pricing is not public. A buyer should ask who owns the source code, how changes are handled after launch, what “private” means operationally, how integrations are maintained and whether the team can continue without Kilvin. Speed is useful, but the durable decision is whether the new tool becomes an owned operating asset.
Editorial take
I would shortlist Kilvin for a narrow internal workflow with a clear owner, a measurable manual cost and enough repetition to justify custom software. Start with one process and an explicit handoff plan. If the problem is primarily browser automation, compare the current offering with the older BrowserBook direction before signing a broader build engagement.
Quick facts
| Field | Sourced detail |
|---|---|
| Product | Private custom software and automation for non-technical teams |
| Buyers | Operations teams with workflow-specific software needs |
| Historical product | BrowserBook browser-automation IDE and API |
| Pricing | Not publicly listed |
| Main gate | Ownership, maintenance, scope and current product continuity |
Sources checked
| Source | Checked |
|---|---|
| YC profile | 2026-09-19 |
| Kilvin launch | 2026-09-19 |
Cohort context
Kilvin is listed in Fall 2024. In our 2026-09-18 directory snapshot, 57 of 94 listed companies in that cohort have YC’s primary industry label B2B (60.6%). This is a current-directory comparison, not an original intake count or a performance ranking. Nine-cohort dataset.
Public website snapshot
Observed 2026-09-19 16:14 UTC in raw homepage HTML. This records visible metadata and advertised links, not agent execution or product quality.
| Signal | Homepage observation |
|---|---|
| Product description metadata | Observed |
| Canonical link | Observed |
| H1 or H2 heading | Observed |
| Typed structured data | Observed |
| Docs/developer link | Not observed in this response |
| Pricing link | Observed |
| llms.txt link | Not observed in this response |
| Markdown alternate | Not observed in this response |
Public observations · Collection method. Missing links here do not establish that a capability or file is absent elsewhere.
