How to get picked for observability by coding agents
Sentry took 36% of 593 judged observability sessions. What the numbers say a vendor in this category should do.
If you sell observability tools, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for observability and never compares vendors.
The numbers come from 593 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code, spread across 11 realistic codebases, with every session read by a judge.
What coding agents choose for observability
Across 593 judged sessions, Sentry was chosen most often, in 36% of runs. Grafana was second with 15%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Sentry | 211 | 36% |
| 2 | Grafana | 86 | 15% |
| 3 | Amazon CloudWatch | 59 | 10% |
| 4 | Built in-house (no product adopted) | 41 | 7% |
| 5 | Better Stack | 26 | 4% |
| 6 | Checkly | 25 | 4% |
| 7 | New Relic | 24 | 4% |
| 8 | Datadog | 24 | 4% |
| 9 | Honeycomb | 20 | 3% |
| 10 | AWS X-Ray | 18 | 3% |
Full board, every run replayable: the observability leaderboard.
What the shape of this category means
The leader takes 36% of runs and there is a real second place. The category has a default but it is not settled.
Sentry at 36% with Grafana at 15% 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 Sentry 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 (24 sessions) and Muse Code (89 sessions) join this table with fewer runs, so read their rows as indicative.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 150 | Sentry (52) |
| Codex | 180 | Sentry (42) |
| Cursor | 150 | Sentry (68) |
| Grok Build CLI | 24 | Sentry (9) |
| Muse Code | 89 | Sentry (40) |
Even where they agree, they get there differently. In this category Codex ran a web search in 100% of its sessions and Claude Code in 51%, so what you publish reaches nearly all of Codex's observability sessions and about half 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 | 20 | Better Stack |
| Junior developer | 20 | Sentry |
| Senior engineer | 493 | Sentry |
| Enterprise team | 60 | Grafana |
That is 3 different products winning observability for 4 kinds of buyer, out of the same 593 sessions. Nobody here is winning observability. 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 7% 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 observability the clearest case is Highlight: on the table in 56 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Highlight | 56 sessions | 0 |
| Jaeger | 52 sessions | 0 |
| ELK Stack | 49 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 157 sessions is recorded in each transcript, one reason at a time.
What to do about it in observability
- Aim at second place first. Sentry holds 36% and Grafana holds 15%. The gap between the default and the field is where the reachable sessions are.
- Pick which buyer you are for. The same observability need written as a vibe coder landed on Better Stack, and written as an enterprise team landed on Grafana. 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 observability 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 Sentry? — chosen in 36% of sessions
- Do coding agents recommend Grafana? — chosen in 15% of sessions
- Do coding agents recommend Amazon CloudWatch? — chosen in 10% of sessions
- Do coding agents recommend Better Stack? — chosen in 4% of sessions
- Do coding agents recommend Checkly? — chosen in 4% of sessions
- Do coding agents recommend New Relic? — chosen in 4% of sessions
- Do coding agents recommend Datadog? — chosen in 4% of sessions
- Do coding agents recommend Honeycomb? — chosen in 3% of sessions
- Do coding agents recommend AWS X-Ray? — chosen in 3% of sessions
- Do coding agents recommend GlitchTip? — chosen in 2% of sessions
- Do coding agents recommend Azure Monitor? — chosen in 2% of sessions
- Do coding agents recommend Azure Application Insights? — chosen in 1% of sessions
- Do coding agents recommend OpenTelemetry? — raised in 349 sessions, chosen in none
- Do coding agents recommend Pino? — raised in 62 sessions, chosen only within 1 joint choice
Where these numbers come from
593 judged sessions in observability across 11 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 observability run can be replayed on the board.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
How many codebases is this based on?
593 judged sessions across 11 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 observability tool do coding agents choose?
Across 593 judged sessions, Sentry was chosen most often, in 36% of runs. Grafana was second with 15%. The result changes by who is asking.
Do Claude Code and Codex pick the same observability tool?
Yes. Claude Code and Codex both put Sentry 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 observability themselves instead of installing something?
In 7% 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 observability tools do agents consider but never choose?
Highlight (raised in 56 sessions, chosen in none), Jaeger (raised in 52 sessions, chosen in none), ELK Stack (raised in 49 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.