AI analytics agent · for marketing teams # An AI analytics agent that tells you why conversions dropped. Agentic analytics that starts where the numbers do. Trackingplan reads the hits your sites and apps send to GA4 and 170+ other providers, plus spend, clicks, and conversions from your ad accounts — and answers in Slack, in the app, or in Claude and ChatGPT through MCP. [Start asking your data →](https://app.trackingplan.com/signup) [Book a demo](/demo) Ask it ## Campaign or tracking? Ask it. The agent works from your real traffic, investigates before it answers, and shows the evidence. Two threads a marketing lead would open here. **Trackingplan** demo workspace **You** · Marketing Lead Pinterest conversions fell off a cliff — is the campaign dying? traffic\_vs\_conversions · pinterest · 14dinspect\_hits · pinterest checkout · last 24h **Trackingplan** **The campaign isn’t. The tag is.** Since Tuesday at 16:40 the Pinterest tag fires without `order_id` on 100% of checkouts, and Pinterest discards those. Clicks and landing sessions are flat versus last week. **Cause:** the variable `DL – order_id` was renamed in GTM release v92. One change, no budget decision needed. clicks *flat* · landing sessions *flat* · conversions −97% · since Tue 16:40 Suggested next actions [Give me the exact change](/#ask=Pinterest%20conversions%20fell%20off%20a%20cliff%20%E2%80%94%20is%20the%20campaign%20dying%3F) [Send this to #paid-social](/#ask=Pinterest%20conversions%20fell%20off%20a%20cliff%20%E2%80%94%20is%20the%20campaign%20dying%3F) [Tell me when it’s back](/#ask=Pinterest%20conversions%20fell%20off%20a%20cliff%20%E2%80%94%20is%20the%20campaign%20dying%3F) [Continue this thread with the agentSend](/#ask=Pinterest%20conversions%20fell%20off%20a%20cliff%20%E2%80%94%20is%20the%20campaign%20dying%3F) **Trackingplan** demo workspace **You** · Marketing Lead Why is Meta showing 240 more purchases than GA4 this week? count\_conversions · purchase · meta vs ga4 · 7dattribute\_gap · view-through, consent, dedup **Trackingplan** **The gap is real, and this time it’s not a tracking error:** Meta counts 1-day view-through conversions, GA4 doesn’t — that’s 212 of the 240. The remaining 28 are iOS purchases GA4 lost to consent. Nothing to fix — but if you need one number for the deck, use the server-side count: **13,172**. meta 13,412 · ga4 13,172 · *view-through 212* · consent 28 Suggested next actions [Send the full breakdown to Rachel](/#ask=Why%20is%20Meta%20showing%20240%20more%20purchases%20than%20GA4%20this%20week%3F) [Alert me only if the gap changes in nature](/#ask=Why%20is%20Meta%20showing%20240%20more%20purchases%20than%20GA4%20this%20week%3F) [Use the server-side count in the Monday report](/#ask=Why%20is%20Meta%20showing%20240%20more%20purchases%20than%20GA4%20this%20week%3F) [Continue this thread with the agentSend](/#ask=Why%20is%20Meta%20showing%20240%20more%20purchases%20than%20GA4%20this%20week%3F) In the product ## What the agent does for your marketing - Install · 30 seconds ### One tag. No schema to define. One tag, SDK, or server-side hook. Events appear as traffic flows — web, mobile, and server — and your tracking plan builds itself from real traffic, with no rules to write. - Coverage · ads, marketing, analytics ### Every platform in the same answer. GA4, Adobe, Amplitude, Meta, Google Ads, TikTok, LinkedIn, your CDP, and your consent vendor — 170+ providers, captured where each request is produced. Connect your ad accounts and spend, impressions, clicks, and conversions per campaign sit next to the traffic they bring. - Context · built from your traffic ### It speaks marketing, not database. Raw events are mapped to the concepts your team talks about, so anyone can ask about revenue, not about purchase.value. What your team teaches it, it keeps for the next question. - Evidence · behind every answer ### A cause only when two pieces of evidence agree. It checks its work with SQL, Python, and a real browser before it answers. Every answer shows the queries behind it, and carries a data quality note when an issue changes the number. - Reports · where your team works ### Reports in Slack, email, or your AI tool. A weekly leads report, a Monday conversion-gap email — the numbers, the chart, and what changed, written for the people who read it. Ask in Slack or Teams, or in Claude, ChatGPT, or Cursor through MCP. Book a demo ## Let’s see if we’re a match, data-style. This isn’t a sales call. It’s a chance to understand what matters most to you, discuss any data quality concerns you may have, and share practical ways Trackingplan could support your goals, if it makes sense. [Book a demo →](/demo) [Start free trial](https://app.trackingplan.com/signup) FAQ ## About the agent. ?What is an AI analytics agent? tp An AI that investigates before it answers. It reads the data, checks its work with tools, and shows the evidence behind its conclusion — the way a digital analyst would. That is what “agentic analytics” means in practice. Trackingplan is your digital analytics agent. It sees the data as it is produced, monitors it continuously across 170+ analytics and ad platforms, and answers where your team already works: Slack, Teams, email, the app, or your AI tool through MCP. ?Why not just connect ChatGPT or Claude to our analytics or our warehouse? tp **Because an AI agent can only reason about what it can see.** A warehouse tells you what data eventually arrived. It doesn’t tell you whether the pixel fired correctly this morning, whether a consent state changed, or whether a GTM release dropped a parameter. Trackingplan starts at that layer — the hits, the dataLayer, the pixels, the server-side payloads, and the consent signals — so the agent can tell a weaker campaign from a broken tag. ?Does it replace our BI tool or our attribution model? tp No. Trackingplan doesn’t replace a warehouse semantic model, a BI platform, or a multi-touch attribution model. It makes the data feeding them inspectable, and it answers the questions they can’t: whether the number was produced correctly, and what changed when it wasn’t. ?Another tool to configure? tp **No.** Add one tag, pixel, server-side connection, or our iOS or Android SDK. No tables to expose, no relationships to define, no semantic layer to build, and no tracking plan to configure before the agent can start working. As data flows in, Trackingplan infers your schema and semantic model from what is actually happening. ?How do I know it isn’t making things up? tp It names a cause only when two independent pieces of evidence agree. Anything less is presented as a hypothesis and labeled as one. If it can’t find the cause, it says so; it never claims there isn’t one. Every answer shows the queries behind it. ?What about privacy and PII? tp Trackingplan only observes the data your site or app is already sending to analytics or marketing tools. It does not use cookies, and all data is anonymized or masked on the user’s device before being forwarded for analysis. It never introduces new tracking mechanisms, never stores personal data, and never builds user profiles. ?Can I try it first? tp Yes. Starter and Growth start with a 9-day free trial: Trackingplan learns your tracking from real traffic, then you ask it about your own data. Plans start at 89€ a month; see [pricing](/pricing). More of Trackingplan - [Monitoring · always on**Every hit, every hour, every event — watched.**](/landings/monitoring) - [Install · 30 seconds**One tag. Your entire data layer monitored.**](/landings/install) - [Coverage · every platform**If it leaves the browser, the app or the server, we see it.**](/landings/coverage) - [Schema · semantics & context**The context your AI needs, built automatically.**](/landings/schema) - [For performance teams**Stop bidding blind on Meta, Google, Bing and TikTok.**](/landings/paid-media) - [For digital analytics teams**Automate the work that consumes your analytics capacity.**](/landings/data-analyst) - [For privacy & legal**Catch PII leaks and consent breaches before legal does.**](/landings/privacy) - [Agencies & consultancies**Every client’s tracking, audited every day, without a bigger team.**](/landings/agencies) - [Automation**Describe it once. Runs forever.**](/landings/automations) - [Journey explorer · real sessions**Complete visibility into your users data, every step of the way**](/landings/journey-explorer) - [Monitoring · iOS, Android, backend**Always accurate mobile analytics, even as your apps evolve**](/landings/app-tracking-monitoring) - [For developers**Your QA engineer for the dataLayer, the SDKs and every release.**](/landings/qa) **Chats** × Send Sample workspace. Answers are scripted — the real one reads your traffic.