An AI visibility tracker for brands
Hallam Internet · Innovate UK-funded build, handed to the agency
OpenKit built a platform that lets Hallam see where a brand gets cited inside AI assistants and count those citations towards one score alongside search and social. The agency runs the platform on prompts it chooses and owns the methodology behind the score.
Overview
Hallam Internet is a Nottingham digital agency whose clients pay to be findable. Hallam could see the shift those clients were starting to feel: people ask an AI assistant, get a usable answer inside it and never land on a page anyone can count. No visit happens, so analytics records nothing and rank tracking has nothing to say about it. There was also no shared unit for weighing a mention inside an AI answer against a third-place search result.
Under Hallam’s Innovate UK-funded project, OpenKit designed and built the first version of the platform to the agency’s funding milestones and put it into production. The grant went on the part the market did not have: the citation monitor and one score that spans AI, search and social.
3 AI platforms
ChatGPT, Perplexity and Gemini, checked for brand citations
In production
Run by Hallam’s team, with its beta clients on read-only dashboards
Hallam-owned
The methodology, the parsing logic and the code repository
Approach
What OpenKit built
Citation monitoring across three AI platforms
A scheduled agent puts the agency’s own prompts to ChatGPT, Perplexity and Gemini, then reads each answer for mentions of the brand and links back to it. Each platform cites differently: one returns footnotes, another puts links inline, a third paraphrases the brand without linking anywhere. OpenKit wrote a parser for each.
A dated record of every citation
Each prompt shows its citation rate, average position and sentiment. The run history underneath shows when each platform cited the brand and which page it linked to. The same prompt asked an hour apart can get two different answers, so the trend has to be read from that history.
Search and social data in the same score
Social views, likes, comments and subscriber growth sit alongside search and AI data, which is what makes one score possible. Each source has its own connector and checks, so a source that breaks stops loading and no bad numbers reach the score.
Scoring weights the agency sets
The weights sit in a table behind an admin screen and the score recalculates from them on every read, so the agency can move the score as the platforms change. If Hallam decides a footnote in an AI answer is worth more than a position-eight result nobody clicks, it changes one row.
Result
Hallam runs the platform itself
The platform is in production, with Hallam’s team running the admin side, its beta clients on read-only dashboards and the citation monitor working through prompts the agency controls.
OpenKit wrote the methodology up as the agency’s own intellectual property. The funded work also covers a session with Hallam’s engineers. Hallam owns what the grant paid for:
- The platform, with role-based access and admin screens for what the team changes day to day: the prompts, the weights and who can see what.
- The citation monitor, including the agent, the prompt management around it and the parsing logic that reads the answers.
- The scoring engine, its documented methodology and the repository itself.
Controls on this project
The platform is hosted in the UK and run to UK GDPR. Each brand’s data is kept apart in the database, so adding a brand is a configuration change.
Other engagements
What could your business do with AI?
Find out with experts who become part of your team. We uncover opportunities, get ideas working, and help your people build on the results. We reply within one working day.
Get in touch AI Engineering