A new layer of business intelligence

Measure what the models measure.

Combot provides the authoritative, non-obvious metrics for how large language models see your brand — from training-data memory to final recommendation.

Request access See what we track →

Beyond mentions.

Your brand's visibility inside an AI answer is not a binary "yes/no." It's a 7-layer funnel from a model's latent knowledge to its final, commercially-weighted recommendation. Combot's AI Share of Recommendation is the north-star metric for the AI era.

01 Trained-onMemory mode — does the model already know the brand exists from its pretraining corpus? Tools-off recall
02 RetrievedSearch mode — when the model invokes a search tool, does your URL survive into the candidate set? Share of citations
03 FetchedFetch mode — can the AI actually read the URL once retrieved, or does the SPA shell defeat it? Fetch-readiness
04 CitedYour URL is kept through synthesis and appears in the final answer's structured citations. Cited-URL share
05 Sentiment & AccuracyHow the answer frames you — positive, neutral or negative — and whether the facts are right. Attribute accuracy
06 RecommendedYou are not just mentioned but chosen: in the top three when the model is asked to recommend. AI Share of Recommendation
07 Acted-onClick-through, follow-up, conversion, agent action — the layer that closes the loop with revenue. Downstream conversion

Read the full framework in The 7 layers of AI visibility.

Your data, modelled.

Combot integrates with the systems you already run and consolidates them into a single BigQuery-backed data lake. The Claude tool-use loop reasons across every source at once — not just one channel, not just one chart.

Google Analytics 4
Live + BQ export
Search Console
Live + Bulk export
Google Ads
DTS + API
Merchant Center
Feed + Shopping Pack
Google Tag Manager
Container audit
Snowplow
First-party event collection
Rybbit
Privacy-first analytics
Adobe Commerce
Orders, catalogue, inventory
Shopify
Orders, products, fulfilment
BigQuery
Per-tenant data lake
Amazon AWS
EC2, S3, Lambda@Edge, CloudFront
Cloudflare
Analytics, DNS, Workers, logs
Fastly
VCL edge + shielding
PrerenderProxy
AI-bot fetchability + cache health
PageSpeed Insights
Lab Lighthouse
WebPageTest
Self-hosted CWV + filmstrips
Looker / Data Studio
BI on top of BigQuery
Grafana
Operational dashboards
Prometheus
Metrics scraping + TSDB
Victoria Metrics
Long-term Prometheus-compatible TSDB
New Relic
APM + business transactions

Combot's own reasoning runs on a multi-model orchestra — Anthropic Claude, OpenAI, and Google Gemini — but those are the engine, not your integrations. Your data stays in your warehouse.

Chat-native. Where your team already works.

Combot lives in your team's chat — Slack, Teams, Mattermost, or any platform you connect via API integration. Trigger a full SEO audit, ask for a weekly anomaly report, query the data lake, or pull live SERP — without leaving the channel. No new dashboard to learn. The answer comes back where the conversation already is.

@combot

Conversational command

Ask Combot in plain English. It chooses tools, runs queries against BigQuery, calls live APIs, assembles the answer. No SQL needed for the common cases — and full SQL passthrough for the rest.

Nightly

Anomalies surfaced, not searched

Multi-channel correlation: when a spend spike on Ads doesn't match a click pattern in GSC and CWV regressed at the same time on the same template, Combot flags the compound — not three siloed warnings.

Per-client

Tenant isolation by design

Each client lives in its own GCP project with its own BigQuery datasets, its own service account, its own audit trail. Multi-tenant where it counts; isolated where it must be.