Brand Analytics for AI Search Engines (Beta)
Monitors AI search mentions, but only shows one furniture retailer dashboard as proof.
Understand how your brand shows up in LLM responses.
Fills genuine pain: 'found via ChatGPT' can't be measured with old SEO tools—self-host or SaaS.
Product managers, content strategists, companies concerned about AI-driven discovery vs. SEO.
SimilarWeb · Semrush · Brandwatch
We built Sonde (https://github.com/compiuta-origin/sonde-analytics) after noticing - probably like everybody else - our website traffic was declining while prospects were telling us "I found you through ChatGPT".
We wanted to understand our visibility across LLM responses, as we did in the good old days of SEO and web analytics. Since existing tools were enterprise-tier expensive, we built Sonde as a simple internal project to:
- schedule prompts to run against multiple LLMs, with web search enabled - track whether your brand is mentioned in responses, how it ranks vs. competitors and general sentiment - monitor trends over time
Tech stack: Supabase, Next.js, OpenRouter as LLM wrapper.
Sonde is fully open-source and you can self-host it via Docker Compose. We're also offering a managed version for convenience, running with complete feature parity.
Sonde has fundamentally changed how we approach content strategy for our products: I'd love to get feedback on it, or hear how you're currently tracking LLM visibility!
Monitors AI search mentions, but only shows one furniture retailer dashboard as proof.
Tracks AI citations over time when BrightData and Olostep only offer raw scraping.
HN sentiment tracker for under $1/month using llama-3.1; niche but genuinely useful.
Granular API key controls and token cost tracking beat basic llama.cpp wrappers.
Streams evals from a tiny Python client into a shared dashboard and lets you run parameter sweeps and compare up to six configurations with radar/bar charts and scorecards — exactly the sort of tooling that stops results getting lost in notebooks. Useful, pragmatic product for teams who repeatedly evaluate models, but it's competing with general observability/experiment trackers (W&B, Neptune) and will need strong integrations and metric flexibility to stand out.
Brand Entity Kit fixes LLM hallucinations when Prolific and AirOps just track rankings.