How One Developer Used Claude Code to Launch a GEO Platform for Brands Across Nine AI Models

One question in a work chat in September 2025 set a mobile developer on a complete career turn. He left his staff job on the Biblio Globus app to build a GEO platform that helps businesses see how their brand appears in the answers of nine AI models. Two things matter here: the demand for a new category, generative engine optimization, and how much AI tools like Claude Code have shortened the path from idea to product.

According to the author, the trigger was a remark from the CEO: "Who knows anything about GEO?" After that, the topic stopped being abstract.

GEO, or Generative Engine Optimization, is an attempt to adapt the logic of SEO to the era of chat assistants, when users increasingly get a ready-made answer instead of a list of links. For brands, this changes the task: it is no longer enough to hold a place in search results; they also need to appear in the wording, recommendations, comparisons and shortlists that models generate in conversation.

The author approached the idea as an engineer rather than a theorist. He ran a local technical audit of the frontend, studied how interaction scenarios with AI models work, and began building his own product in the evenings. By then he had long followed the development of generative models, had used ChatGPT since its first high-profile launches, and, by his own account, had been a daily Claude user since March 2025. Betting on Claude Code therefore felt natural to him: the tool let him test hypotheses faster, build interfaces and move forward without a team of several developers.

By December 2025 the side project had become his main occupation. He left his job by mutual agreement and moved to full-time development of the platform. Its mission is stated fairly bluntly: give businesses a tool that takes over the work of managing brand visibility in AI models.

The term GEO itself grew out of this need, as a distinct applied discipline. Where companies once measured traffic, rankings and CTR, they now have to look at a new layer of metrics: whether a model mentions the brand in response to a user query, in what context, whom it shows alongside it, and which sources it uses to form the answer. In effect, this is a shift from traditional web analytics to answer analytics, where clicks matter, but so do meaning, wording and the brand's place inside an AI dialogue.

The title of the original article indicates that the platform works with nine AI models at once. That is an important nuance, because the market stopped being a one-leader story long ago. Different models answer the same questions differently, rely on different web sources, and can give a business very unequal visibility.

For companies, this means optimizing for AI once is not enough: they need to compare answers across systems, track discrepancies, and understand where the brand has already secured a place in recommendations and where competitors occupy it. If one model confidently recommends a competitor while another does not name your brand at all, that is no longer an abstract metric but a direct signal for marketing and content. In this context, the product solves not an academic problem but a practical one: monitoring reputation, presence and digital discoverability.

The main takeaway is that GEO is gradually taking shape as a separate market, and the barrier to building B2B tools has dropped noticeably. One developer armed with a clear problem and a strong AI assistant can now do more than make a prototype: he can build a specialized platform for a new pattern of user behavior. For business, this is a signal that the fight for attention is shifting from classic search to the interfaces of AI models. For developers, it is a reminder that Claude Code and similar tools are becoming not a garnish on the process but a real lever for launching products solo.