# How to get picked for file storage by coding agents > Amazon S3 took 46% of 90 judged file storage sessions. What the numbers say a vendor in this category should do. Source: https://armature.tech/library/storage-coding-agents-playbook Published: 2026-09-03 Publisher: Armature, Inc. (https://armature.tech) --- If you sell file storage services, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for file storage and never compares vendors. The numbers come from 90 judged sessions with Claude Code, Codex and Cursor, spread across 8 realistic codebases, with every session read by a judge. ## What coding agents choose for file storage > Across 90 judged sessions, **Amazon S3** was chosen most often, in **46%** of runs. Azure Blob Storage was second with 20%. | # | Product | Runs won | Share | | --- | --- | --- | --- | | 1 | Amazon S3 | 41 | 46% | | 2 | Azure Blob Storage | 18 | 20% | | 3 | Google Cloud Storage | 18 | 20% | | 4 | Cloudflare R2 | 12 | 13% | | 5 | Tigris | 1 | 1% | Full board, every run replayable: [the file storage leaderboard](/leaderboards/storage). ## What the shape of this category means The leader takes 46% of runs and there is a real second place. The category has a default but it is not settled. Amazon S3 at 46% with Azure Blob Storage at 20% 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 all three agents put Amazon S3 first, which is less common than it sounds: across the eighteen categories we measured, Claude Code and Codex disagreed on the leader in nine of them. | Agent | Runs | Picked most often | | --- | --- | --- | | Claude Code | 30 | Amazon S3 (10) | | Codex | 30 | Amazon S3 (16) | | Cursor | 30 | Amazon S3 (15) | Even where they agree, they get there differently. Codex ran a web search in 53% of decision runs and Claude Code in 1.6%, so what you publish reaches one of them in half its file storage sessions and the other in almost none. ## 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 | | --- | --- | --- | | Junior developer | 18 | Amazon S3 | | Senior engineer | 27 | Amazon S3 | | Enterprise team | 36 | Azure Blob Storage | That is 2 different products winning file storage for 3 kinds of buyer, out of the same 90 sessions. Nobody here is winning file storage. 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](/library/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. ## What to do about it in file storage 1. **Skip the build-versus-buy argument.** No file storage 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. 2. **Aim at second place first.** Amazon S3 holds 46% and Azure Blob Storage holds 20%. The gap between the default and the field is where the reachable sessions are. 3. **Report install share per persona, not as one number.** In file storage the leader changes with who is asking, so a blended figure averages markets that behave differently. The work that applies to every category rather than to this one is written up separately: [audit your documentation](/library/audit-your-docs-for-coding-agents), [write a quickstart an agent can follow](/library/write-a-quickstart-an-agent-can-follow), and [how to measure install share](/library/how-to-measure-install-share). ## Every file storage service 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 Amazon S3?](/library/do-coding-agents-recommend-amazon-s3) — chosen in 46% of sessions - [Do coding agents recommend Azure Blob Storage?](/library/do-coding-agents-recommend-azure-blob-storage) — chosen in 20% of sessions - [Do coding agents recommend Google Cloud Storage?](/library/do-coding-agents-recommend-google-cloud-storage) — chosen in 20% of sessions - [Do coding agents recommend Cloudflare R2?](/library/do-coding-agents-recommend-cloudflare-r2) — chosen in 13% of sessions ## Where these numbers come from 90 judged sessions in file storage across 8 codebases, part of a published set of 5,292. 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](/library/how-we-measured-this). Every file storage run can be replayed on [the board](/leaderboards/storage). ## Common questions ### How many codebases is this based on? 90 judged sessions across 8 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 file storage service do coding agents choose? Across 90 judged sessions, Amazon S3 was chosen most often, in 46% of runs. Azure Blob Storage was second with 20%. The result changes by agent and by who is asking. ### Do Claude Code and Codex pick the same file storage service? Yes. All three agents we tested put Amazon S3 first in this category, which is unusual: they disagree in half of the categories we measured. ### How often do agents build file storage 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. ## Read next - [Agent discoverability: the complete guide](https://armature.tech/library/agent-discoverability) (Markdown: https://armature.tech/library/agent-discoverability.md) - [How coding agents choose tools](https://armature.tech/library/how-coding-agents-choose-tools) (Markdown: https://armature.tech/library/how-coding-agents-choose-tools.md) - [Do coding agents recommend Amazon S3?](https://armature.tech/library/do-coding-agents-recommend-amazon-s3) (Markdown: https://armature.tech/library/do-coding-agents-recommend-amazon-s3.md) - [Do coding agents recommend Azure Blob Storage?](https://armature.tech/library/do-coding-agents-recommend-azure-blob-storage) (Markdown: https://armature.tech/library/do-coding-agents-recommend-azure-blob-storage.md) - [Do coding agents recommend Google Cloud Storage?](https://armature.tech/library/do-coding-agents-recommend-google-cloud-storage) (Markdown: https://armature.tech/library/do-coding-agents-recommend-google-cloud-storage.md) --- Armature helps software products get discovered and used by coding agents. Service: https://armature.tech/discoverability · Results: https://armature.tech/leaderboards/sectors · Contact: contact@armature.tech