How to get picked for product analytics by coding agents
PostHog took 56% of 598 judged product analytics sessions. What the numbers say a vendor in this category should do.
If you sell product analytics tools, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for product analytics and never compares vendors.
The numbers come from 598 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code, spread across 10 realistic codebases, with every session read by a judge.
What coding agents choose for product analytics
Across 598 judged sessions, PostHog was chosen most often, in 56% of runs. Metabase was second with 6%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | PostHog | 332 | 56% |
| 2 | Built in-house (no product adopted) | 82 | 14% |
| 3 | Metabase | 37 | 6% |
| 4 | Vercel Analytics | 27 | 5% |
| 5 | Mixpanel | 19 | 3% |
| 6 | Amplitude | 19 | 3% |
| 7 | Segment | 18 | 3% |
| 8 | Looker Studio | 12 | 2% |
| 9 | Umami | 8 | 1% |
| 10 | Datadog | 5 | 1% |
Full board, every run replayable: the product analytics leaderboard.
What the shape of this category means
The leader takes 56% of runs and there is a real second place. The category has a default but it is not settled.
PostHog at 56% with Metabase at 6% is a default with a real challenger behind it. The agent is choosing rather than reaching, which means the inputs it uses can move the answer.
The work is to be the easiest correct answer: a quickstart that runs when pasted, documentation that states the current version, and pages that answer the exact configuration questions agents search for.
The agents do not agree with each other
In this category Claude Code, Codex and Cursor all put PostHog first, which is less common than it sounds: across the 31 categories we measured, Claude Code and Codex disagreed on the leader in 16 of them.
Grok Build CLI (29 sessions) and Muse Code (90 sessions) join this table with fewer runs, so read their rows as indicative.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 150 | PostHog (69) |
| Codex | 180 | PostHog (104) |
| Cursor | 149 | PostHog (89) |
| Grok Build CLI | 29 | PostHog (14) |
| Muse Code | 90 | PostHog (56) |
Even where they agree, they get there differently. In this category Codex ran a web search in 98% of its sessions and Claude Code in 15%, so what you publish reaches nearly all of Codex's product analytics sessions and a minority of Claude Code's.
Who is asking changes the answer
Every request in this experiment was written as a specific kind of person. In this category the leader changes with the person.
| Who is asking | Runs | Picked most often |
|---|---|---|
| Vibe coder | 60 | Vercel Analytics |
| Junior developer | 240 | PostHog |
| Senior engineer | 238 | PostHog |
| Enterprise team | 60 | PostHog |
That is 2 different products winning product analytics for 4 kinds of buyer, out of the same 598 sessions. Nobody here is winning product analytics. They are each winning one kind of buyer.
If you sell to more than one of them, you need pages for each. See how to win the enterprise persona.
What you are really competing against
In 14% of runs the agent wrote the code itself rather than adopting a product. That is low enough that your competition is other vendors, but high enough to be worth watching.
Considered, and never chosen
Because the judge records every product an agent raised and not only the one it picked, this board also shows who kept reaching the shortlist and losing. In product analytics the clearest case is Google Analytics: on the table in 117 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Google Analytics | 117 sessions | 0 |
| Fathom | 82 sessions | 0 |
| Heap | 49 sessions | 0 |
| RudderStack | 43 sessions | 0 |
Being rejected is a better position than being unknown, and a cheaper one to fix. The product is already in the agent's head and on the list. Whatever ended those 291 sessions is recorded in each transcript, one reason at a time.
What to do about it in product analytics
- Aim at second place first. PostHog holds 56% and Metabase holds 6%. The gap between the default and the field is where the reachable sessions are.
- Pick which buyer you are for. The same product analytics need written as a vibe coder landed on Vercel Analytics, and written as an enterprise team landed on PostHog. Those are two markets, and the enterprise one needs pages containing the constraint words: audit log, data residency, retention, single sign-on. See how to win the enterprise persona.
The work that applies to every category rather than to this one is written up separately: audit your documentation, write a quickstart an agent can follow, and how to measure install share.
Every product analytics tool on this board
One page per product, with its install share, the per-agent split, and how often it was raised without being chosen.
- Do coding agents recommend PostHog? — chosen in 56% of sessions
- Do coding agents recommend Metabase? — chosen in 6% of sessions
- Do coding agents recommend Vercel Analytics? — chosen in 5% of sessions
- Do coding agents recommend Mixpanel? — chosen in 3% of sessions
- Do coding agents recommend Amplitude? — chosen in 3% of sessions
- Do coding agents recommend Segment? — chosen in 3% of sessions
- Do coding agents recommend Looker Studio? — chosen in 2% of sessions
- Do coding agents recommend Umami? — chosen in 1% of sessions
- Do coding agents recommend Datadog? — chosen in 1% of sessions
- Do coding agents recommend Grafana? — chosen in 0% of sessions
- Do coding agents recommend Google Analytics? — raised in 117 sessions, chosen in none
- Do coding agents recommend Fathom? — raised in 82 sessions, chosen in none
Where these numbers come from
598 judged sessions in product analytics across 10 codebases, part of a published set of 15,287. Real coding agents at pinned versions, in sandboxes, inside realistic codebases, with a simulated project owner in the loop and a blind judge on every session. The full method is on one page: how we measured this.
Every product analytics run can be replayed on the board.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
How many codebases is this based on?
598 judged sessions across 10 realistic codebases. A category only runs on repositories where its seam is open, so coverage differs: some categories ran on more than ten codebases and some on two.
What product analytics tool do coding agents choose?
Across 598 judged sessions, PostHog was chosen most often, in 56% of runs. Metabase was second with 6%. The result changes by who is asking.
Do Claude Code and Codex pick the same product analytics tool?
Yes. Claude Code and Codex both put PostHog first in this category, which is less common than it sounds: they disagree on the leader in 16 of the 31 categories we measured.
How often do agents build product analytics themselves instead of installing something?
In 14% of runs the agent wrote the code itself rather than adopting a product.
How can a vendor improve its position here?
Make the quickstart run when pasted, state the current version on the documentation page, use one name across product, package and import, write pages for the symptoms users describe rather than only the category name, and get into the repository through templates and framework integrations.
Which product analytics tools do agents consider but never choose?
Google Analytics (raised in 117 sessions, chosen in none), Fathom (raised in 82 sessions, chosen in none), Heap (raised in 49 sessions, chosen in none), RudderStack (raised in 43 sessions, chosen in none). Being considered and not chosen is a different problem from being unknown, and it is usually fixable.
Where this comes from
Armature ran 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.