Transparency as our golden rule
You deserve to know exactly how Pulsari measures your visibility. Here are the 6 exact steps, no black box, with the limitations and choices we own.
Enter your business
30 secName, city, industry, website URL (optional) and a short description. Pulsari builds your profile in 30 seconds.
Pulsari generates 15 realistic prompts
10 secOur system uses a reference LLM (Claude Sonnet) to generate 15 questions phrased like a real user would: recommendations, comparisons, urgent needs, direct searches.
Each prompt is sent to target AIs
45 secChatGPT, Perplexity, Gemini, Claude, Google AI Overviews. Each response is captured raw, timestamped, and stored in your database.
Fuzzy mention detection
automaticA dedicated algorithm detects your brand mention in each response: exact name, domain match, partial keyword match on significant words, with protection against false positives (no substring match on less than 5 characters).
Competitor extraction
automaticFor each response, we extract the names of competing businesses, brands or shops mentioned by the AI, with local/national/international classification. Exclusion filter on 30+ platforms (Google Maps, Yellow Pages, LinkedIn...).
Visibility score + recommendations
instantFinal score out of 100 calculated as (mentions / prompts) x 100. Detailed report with: your mentions, competitor list by frequency, and 8 actionable recommendations sorted by impact.
Our limitations, which we own
- · Generated prompts, not collected. Our 15 prompts are produced by a reference LLM based on your industry and city. They are realistic but don't reproduce the full spectrum of real searches in your market.
- · The score is a sample. 15 prompts give a snapshot, not an absolute truth. A Pulsari report identifies trends, not a market share percentage to the decimal point.
- · AIs evolve. Models are updated constantly. A score of 40 today can become 60 tomorrow without you changing a single line on your site. That's why we recommend a monthly audit.
- · Not all citations are equal. Being cited first by Perplexity doesn't weigh the same as a passing mention in a ChatGPT response. Our score aggregates, our recommendations refine.
Our sources and technical stack
AIs queried
Claude Sonnet 4 (Anthropic), GPT-4o mini (OpenAI), Perplexity Sonar, Gemini 2.0 Flash (Google). Each AI is queried with the same prompt structure for comparability.
Technical stack
Supabase for the database, Deno edge functions for orchestration, React 19 for the interface, Cloudflare Pages for hosting. 100% European.
Detection algorithm
Exact name matching, fuzzy on significant words (>= 4 letters), domain match, with word boundary to avoid common false positives.
Platform filter
Over 30 platforms and directories excluded from detected competitors (Google Maps, Yellow Pages, LinkedIn, Trustpilot, etc.).