How to get picked for ai sre by coding agents
Sentry Seer took 26% of 179 judged ai sre sessions. What the numbers say a vendor in this category should do.
If you sell ai sre, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for ai sre and never compares vendors.
The numbers come from 179 judged sessions with Claude Code, Codex and Cursor, spread across 6 realistic codebases, with every session read by a judge.
What coding agents choose for ai sre
Across 179 judged sessions, Sentry Seer was chosen most often, in 26% of runs. Resolve AI was second with 20%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Sentry Seer | 47 | 26% |
| 2 | Resolve AI | 35 | 20% |
| 3 | Datadog Bits AI Dev Agent + Datadog Bits Investigation | 26 | 15% |
| 4 | Cursor Automations | 15 | 8% |
| 5 | Claude Code GitHub Action | 11 | 6% |
| 6 | Cursor Cloud Agents | 9 | 5% |
| 7 | incident.io AI SRE | 4 | 2% |
| 8 | Cursor Automations + Cursor Cloud Agents | 3 | 2% |
| 9 | Grafana Assistant Investigations | 3 | 2% |
| 10 | Cleric | 3 | 2% |
Full board, every run replayable: the ai sre leaderboard.
What the shape of this category means
The leader takes only 26% of runs. This category is genuinely open and the ordering can be moved.
With the top product at 26%, ai sre is decided in the moment, from what the agent reads and what it finds in the repository. Nothing is locked in, which is the best situation a vendor can be in and the one where the work pays fastest.
The order here is set by the quality of what an agent can read and by whether your product is already present in the codebase. Both are things you can change.
The agents do not agree with each other
In this category the three agents we ran put different products first.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 71 | Sentry Seer (21) |
| Codex | 72 | Resolve AI (25) |
| Cursor | 36 | Cursor Automations (14) |
That split decides where a vendor spends. Codex ran a web search in 53% of decision runs and Claude Code in 1.6%, so the pages you publish are live in half of Codex's ai sre sessions and almost none of Claude Code's. Taking Resolve AI's position with Codex is a content problem. Taking Sentry Seer's with Claude Code is a repository problem.
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 | 30 | Sentry Seer |
| Junior developer | 60 | Sentry Seer |
| Senior engineer | 30 | Resolve AI |
| Enterprise team | 59 | Resolve AI |
That is 2 different products winning ai sre for 4 kinds of buyer, out of the same 179 sessions. Nobody here is winning ai sre. 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 this category agents never chose to build it themselves. Every session ended with a product. That is good news: you are in a straight vendor comparison, and the levers that work are the ones you control.
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 ai sre the clearest case is Traversal: on the table in 74 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Traversal | 74 sessions | 0 |
| Rootly AI SRE | 51 sessions | 0 |
| Datadog Bits AI Dev Agent | 21 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 146 sessions is recorded in each transcript, one reason at a time.
What to do about it in ai sre
- Skip the build-versus-buy argument. No ai sre session in this experiment ended with the agent writing its own implementation. Every one adopted a product, so the whole contest is against the other names in the table above.
- Aim at second place first. Sentry Seer holds 26% and Resolve AI holds 20%. The gap between the default and the field is where the reachable sessions are.
- Pick which buyer you are for. The same ai sre need written as a vibe coder landed on Sentry Seer, and written as an enterprise team landed on Resolve AI. 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.
- Measure per agent. Claude Code put Sentry Seer first, Codex put Resolve AI first, Cursor put Cursor Automations first. A blended number for ai sre describes a market that does not exist.
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 ai sre 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 Seer? — chosen in 26% of sessions
- Do coding agents recommend Resolve AI? — chosen in 20% of sessions
- Do coding agents recommend Cursor Automations? — chosen in 8% of sessions
- Do coding agents recommend Claude Code GitHub Action? — chosen in 6% of sessions
- Do coding agents recommend Traversal? — raised in 74 sessions, chosen in none
Where these numbers come from
179 judged sessions in ai sre across 6 codebases, part of a published set of 7,852. 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 ai sre run can be replayed on the board.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
How many codebases is this based on?
179 judged sessions across 6 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 ai sre do coding agents choose?
Across 179 judged sessions, Sentry Seer was chosen most often, in 26% of runs. Resolve AI was second with 20%. The result changes by agent and by who is asking.
Do Claude Code and Codex pick the same ai sre?
No. Claude Code picked Sentry Seer, Codex picked Resolve AI, Cursor picked Cursor Automations. Measuring one agent tells you about part of the market only.
How often do agents build ai sre themselves instead of installing something?
Never, in this category. Every one of the sessions ended with the agent adopting a product rather than writing the code itself.
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 ai sre do agents consider but never choose?
Traversal (raised in 74 sessions, chosen in none), Rootly AI SRE (raised in 51 sessions, chosen in none), Datadog Bits AI Dev Agent (raised in 21 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 7,852 judged sessions with Claude Code, Codex and Cursor inside 90 realistic codebases, and published every run. The numbers on this page come from that work.