Features

The capabilities, not the marketing version.

Five surfaces, one data lake, one reasoning engine. Below is what Combot does today — not what's on a roadmap slide.

Surface 01

Continuous monitoring.

Pipelines run on 15-min, hourly, and daily cadences. Source data lands in BigQuery, partitioned and clustered, with a per-pipeline observability record.

Web analytics

GA4 · Segment · GTM

Live GA4 for the freshest 24h; Segment's HTTP Tracking API streams first-party events straight into BigQuery; GTM container audits flag broken or duplicated tags.

Search & rankings

Search Console · Ahrefs · SEMrush

GSC live + bulk export, joined to the Ahrefs v3 API (backlinks, organic positions, SERP) and the SEMrush API (keyword universe, Position Tracking). Traditional rank and AI-answer citation in one table.

Technical SEO

Screaming Frog · CrUX · PSI

Scheduled headless Screaming Frog crawls export status codes, canonicals, schema and render output. URL-level Core Web Vitals from CrUX; lab Lighthouse from PageSpeed Insights.

Warehouse & dashboards

BigQuery · Hex

Source data lands in BigQuery, partitioned and clustered. Hex notebooks publish white-labeled, row-level-secured dashboards over it via signed-URL embeds.

Paid

Google Ads · Merchant Center

DTS for historical, API for live. Feed status, price freshness, Shopping Pack appearances tracked nightly.

Commerce

WooCommerce · HubSpot

Orders, inventory, contacts, deals — joined to attribution signals from the web analytics stack.

Edge & logs

Cloudflare · nginx

Edge analytics, DNS state, bot identification from nginx logs. Distinguishes human, search, and AI bot traffic.

Experimentation

Statsig

SEO and content experiments run as Statsig A/B tests via the Console API — template and on-page changes measured for lift against the same organic and AI-visibility baselines as everything else.

Docs & ops

Mintlify · Airtable · Linear

Documentation-site SEO for docs on Mintlify (and Docusaurus, GitBook, ReadMe): information architecture, indexability, search rankings. Editorial queues and findings tracked in Airtable and Linear.

Surface 02

Anomaly + correlation.

Each metric is checked against multiple baselines: rolling week-over-week, year-over-year, learned seasonality. The interesting signals are compound — a spend spike that doesn't match the click curve and lines up with a regressed Core Web Vitals release.

Multi-baseline

Time-series detection

Z-score against a 7-day rolling baseline plus a learned seasonality model. Threshold tuned per-metric, not one-size-fits-all.

Cross-channel

Compound flagging

When ranks drop and CWV regressed and Ads spend held flat — that's one story, not three. Combot stitches it together.

Forecasting

Trend extrapolation

7-day, 30-day, and 90-day forecasts for revenue-adjacent metrics with confidence bands. Surface what's drifting before it crashes.

Surface 03

AI visibility module.

The newest pillar. A dedicated 7-layer model of how brands appear in language-model answers, with a north-star AI Share of Recommendation metric, nightly prompt runs across Claude / GPT / Gemini / Perplexity, citation extraction, fact accuracy scoring, and competitor benchmarking.

APrompt library & versioningBranded, category, comparison, local, action, multilingual. Version-controlled.Portfolio coverage

BMulti-model nightly runsSame prompt, multiple engines, same night. Cross-model agreement & divergence tracked.Mention rate

CCitation extractionWhich URLs the model linked. Domain share, position rank, source-type classification.Citation share

DFact accuracy centerEach answer compared to canonical brand facts. Hallucinations alerted on, not dunked on.Accuracy score

ECompetitor battlecardWin/loss reasons extracted from comparison prompts. Replacement-rate per competitor.Share of recommendation

FAction queueRanked recommendations: fix this content, repair this directory, file this feed correction.Time to resolution

Surface 04

Chat-native command.

Every Combot capability is invokable from chat. The bot lives in the channels your team already uses — Slack, Teams, Mattermost, or any platform connected via API integration. The answers come back where the conversation is. No new dashboard URL to bookmark, no new login to remember.

@combot

Conversational queries

@combot weekly anomaly report, @combot why did organic drop on /pricing, @combot SOV for elisa vs dna on 5g queries. Plain English, real answers.

Scheduled

Digests + alerts

Weekly digest to a channel. Real-time alerts when a metric crosses a threshold or an anomaly fires. Routing per team, per client, per severity.

Permissions

Channel-scoped access

Tenant isolation extends into chat: which channel sees which client's data is configured per workspace. Cross-client leakage prevented at the bot layer.

Surface 05

Audits as code.

Combot's compound audits run on demand or on schedule. Each is a tool the Claude agent can call; results are streamed back as structured findings, ranked by severity and confidence.

audit_seo

SEO audit

Indexing state, ranking trends (Ahrefs + SEMrush), crawl health (Screaming Frog), CWV per template, schema coverage, content gaps, sitemap health. Compound — not 10 silos.

audit_ads

Ads audit

Budget pacing, Quality Score by ad group, waste segments (zero-conv impressions), ROAS trend per campaign.

audit_ai

AI bot audit

Bot identification from nginx logs. Which AI crawlers reach your pages. Which never see your content because they can't render JS.

audit_traffic

Traffic audit

GA4 + Rybbit + nginx joined to surface session-level anomalies that single-source dashboards miss.