Total Search Visibility Platform. Hallam Internet · Innovate UK-funded build, handed to the agency
A platform that measures where a brand gets cited inside AI assistants, puts that next to search and social in one score, and leaves the agency owning the methodology, the code and the repository.
Innovate UK-funded 3 AI platforms monitored Client owns the codebase
Buyers are getting their answers somewhere analytics cannot see.
Hallam Internet is a Nottingham digital agency whose clients pay to be findable. Their team could see the shift those clients were starting to feel: people asking an assistant, getting a usable answer inside it, and never landing on a page anyone could count. Rank tracking has nothing to say about that, and there was no shared unit for comparing a mention inside an AI answer against a third-place search result.
OpenKit designed, built and deployed the MVP under the agency’s Innovate UK-funded project, working to their funding milestones. The work ran across the data foundations and connectors, the citation monitor, the configurable scoring engine, and the dashboards on top, then finished with documentation, a handover session with their technical team, and the repository transferred to them.
- 01
A citation monitor querying three AI platforms on the agency’s own prompts, with the answers parsed for brand mentions and links.
- 02
A scoring engine whose weights live in a table the agency edits, so recalibrating the score takes a row update.
- 03
UK-hosted throughout, with per-tenant isolation enforced in the database itself.
The brief and the funding constraints.
What the platform had to do
One index across AI citations, traditional search and social, so the three read on the same scale.
The tenant boundary enforced in the database, so adding a brand is a configuration change.
Calibration belonging to the agency: the weights live in a table their own team edits.
What Hallam’s Innovate UK grant covered
Grant money goes to the part that did not exist yet, which is the citation monitor and the cross-surface score.
The agency owns the methodology, the parsing logic and the codebase at the end of it.
Handover covers documentation, a session with their engineers, and the repository transferred to them.
Inside the Total Search Visibility Platform.
Citation monitoring across the AI platforms
A scheduled agent takes the target prompts from a table the agency controls, puts them to ChatGPT, Perplexity and Gemini, then parses each unstructured answer for mentions and links back to the brand. Rate limiting, retries and cost ceilings are built into the agent itself.
Every citation pinned to a date, a platform and a source
Per-prompt citation rate, average position and sentiment, with the run history underneath showing exactly when each platform cited the brand and which page it linked to. Two identical queries an hour apart can return two different answers, so the history is the only honest way to read the trend.
Search, social and AI through one ingestion path
Views, likes, comments and subscriber growth land in the same normalised insert path as search and AI, which is what makes a single index possible at all. Each source runs as its own function owning one connector and one validation pass, so a broken source stops ingesting rather than feeding bad numbers into the score.
Scoring weights the agency edits in a screen
The scoring model is database-driven: weights sit in a table with an admin interface over it, and a view recomputes the score from the latest weights on every read. When the agency decides a footnote in an AI answer is worth more than a position-eight result nobody clicks, they change a row and the next read reflects it.
The design decisions behind the score.
- 01
A zero-click answer leaves no session to count
When the answer arrives inside the assistant, no visit happens, so analytics goes quiet on exactly the surface the brand most needs to defend. Measuring it means asking the platforms directly, on a schedule, and keeping what they say.
- 02
Every platform cites differently
One returns footnotes, another puts links inline, a third paraphrases the brand without linking anywhere. Each platform needed its own parser, and that parsing logic is a meaningful part of what was built.
- 03
The weighting is the agency’s judgement
Deciding what a mention inside an AI answer is worth relative to a search position is a professional judgement, and it moves as the platforms do. That judgement belongs to the agency, so it lives in a table their own team edits.
What we handed over to Hallam.
The platform runs in production, with Hallam’s own admin tier active, their beta clients on read-only dashboards, and the citation monitor working through prompts the agency controls. An agency that has to raise a ticket every time it wants to change a weighting does not own its product, so the scoring model was built database-driven, the methodology was written up as the agency’s own intellectual property, and the admin interfaces cover what a working team needs to change: the prompts, the weights, and who can see what.
- 01
The platform in production, hosted in the UK, with role-based access and per-tenant isolation enforced at the data layer.
- 02
The citation monitor: the agent, the prompt management around it, and the parsing logic that reads the answers.
- 03
The scoring engine, its documented methodology, the admin interfaces, and the repository itself.
The build
- Supabase PostgreSQL (AWS London)
- Vite + React + TypeScript
- Tailwind + Recharts
- Supabase Edge Functions
- LLM Citation Monitor (scheduled agent)
OpenKit certifications
- ISO 27001
- ISO 9001, UKAS-accredited
- Cyber Essentials
Controls on this project
- UK GDPR
- UK data residency (AWS London)
- Row-Level Security per tenant
More of the work.
Find your first workflow.
We start with a conversation, audit where AI actually pays back, and build the first automation into how your team already works. We reply within one working day.
Start the conversation AI Engineering