# Agents on Rails: Stage 2. Can a model ship a feature?

DevFeed: [Agents on Rails: Stage 2. Can a model ship a feature?](<https://devfeed.tech/articles/agents-on-rails-stage-2-can-a-model-ship-a-feature-3567.md>)

Original publisher: [Read original article](<https://rubyonrails.org/2026/9/9/agents-on-rails-stage-2>)

Author: Svyatoslav Kryukov, Artur Petrov, Alexander Baygeldin

Published: 2026-09-09T00:00:00Z

Content type: article

Language: en

Sources: [Ruby on Rails: Compress the complexity of modern web apps](<https://devfeed.tech/sources/ruby-on-rails-compress-the-complexity-of-modern-web-apps.md>)

Topics: [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [developer](<https://devfeed.tech/tags/developer.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [feature](<https://devfeed.tech/tags/feature.md>), [model](<https://devfeed.tech/tags/model.md>)

## AI overview

Agents on Rails Stage 2 benchmarks models on completing 20 realistic feature tickets for a Rails kanban app. It evaluates accuracy, cost, and speed using deterministic verification, hidden checks, and the app's test suite; GPT-6 Astra led the reported results.

## Source excerpt

Today we're expanding Agents on Rails with Stage 2, a new set of benchmark tasks that exercise a model's ability to deliver real-world features, more in line with how a developer would actually work.