# Do coding agents recommend Amazon Cognito? > Amazon Cognito was chosen in 3% of 656 judged authentication sessions, ranking sixth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code. Source: https://armature.tech/library/do-coding-agents-recommend-amazon-cognito Published: 2026-09-24 Publisher: Armature, Inc. (https://armature.tech) --- > Amazon Cognito was chosen in 3% of 656 judged authentication sessions, ranking sixth. It was also raised as a candidate in 37 further sessions without being chosen. This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in authentication inside a realistic codebase. Not what a chat assistant says about Amazon Cognito. What an agent actually installed. ## The numbers | | | | --- | --- | | Category | Authentication | | Sessions in the category | 656 | | Sessions where Amazon Cognito was chosen | 20 | | Install share | 3% | | Rank in category | 6 of 28 | | Codebases it won in | 3 | | Raised as a candidate, not chosen | 37 | | Chosen when considered | 35% | | Site | aws.amazon.com | ## By agent Claude Code, Codex, Cursor, Grok Build CLI and Muse Code land within 7 points of each other on Amazon Cognito, which is closer than most products in this experiment manage. | Agent | Sessions | Chose Amazon Cognito | Share | | --- | --- | --- | --- | | Claude Code | 133 | 0 | 0% | | Codex | 136 | 1 | 1% | | Cursor | 133 | 4 | 3% | | Grok Build CLI | 50 | 0 | 0% | | Muse Code | 204 | 15 | 7% | ## By who was asking Amazon Cognito performs similarly across the four kinds of buyer, from 0% to 8%. That is unusual: the category leader changed with the persona in 22 of the 29 categories we measured. | Who is asking | Sessions | Chose Amazon Cognito | Share | | --- | --- | --- | --- | | Vibe coder | 89 | 0 | 0% | | Junior developer | 202 | 0 | 0% | | Senior engineer | 220 | 9 | 4% | | Enterprise team | 145 | 11 | 8% | ## What Amazon Cognito was up against The full ranking in authentication, from the same sessions: | # | Product | Runs won | Share | | --- | --- | --- | --- | | 1 | Auth0 | 157 | 24% | | 2 | WorkOS AuthKit | 125 | 19% | | 3 | Clerk | 78 | 12% | | 4 | Microsoft Entra ID | 73 | 11% | | 5 | Built in-house (no product adopted) | 60 | 9% | | 6 | Better Auth | 26 | 4% | | 7 | Amazon Cognito **(this page)** | 20 | 3% | | 8 | Keycloak | 19 | 3% | ## What this means Amazon Cognito was raised in 37 sessions and chosen in 20. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough. ## Where these numbers come from The 656 sessions in authentication are part of a published set of 13,497, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: [how we measured this](/library/how-we-measured-this). Every authentication run can be replayed on [the board](/leaderboards/auth). If you work on Amazon Cognito: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts. ## Common questions ### Do coding agents recommend Amazon Cognito? Yes. Amazon Cognito was chosen in 20 of the 656 judged sessions in authentication, a 3% install share, ranking sixth in its category. ### Does Claude Code recommend Amazon Cognito? In 0 of the 133 sessions in authentication run with Claude Code, which is 0%. ### Do different coding agents treat Amazon Cognito differently? Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 7% of their runs. ### How was this measured? Real coding agents at pinned versions were run in sandboxes inside 91 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind. ### How often is Amazon Cognito considered but not chosen? It was raised as a candidate in 37 sessions without being chosen, and chosen in 20. That is a 35% conversion from considered to chosen. ## Read next - [How to get picked for authentication by coding agents](https://armature.tech/library/auth-coding-agents-playbook) (Markdown: https://armature.tech/library/auth-coding-agents-playbook.md) - [Do coding agents recommend Auth0?](https://armature.tech/library/do-coding-agents-recommend-auth0) (Markdown: https://armature.tech/library/do-coding-agents-recommend-auth0.md) - [Do coding agents recommend WorkOS AuthKit?](https://armature.tech/library/do-coding-agents-recommend-workos-authkit) (Markdown: https://armature.tech/library/do-coding-agents-recommend-workos-authkit.md) - [Do Claude Code, Codex and Cursor pick the same tools?](https://armature.tech/library/do-claude-code-and-codex-agree) (Markdown: https://armature.tech/library/do-claude-code-and-codex-agree.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