Rails and AI — Ruby on Rails
Rails is built for AI.
Rails gives coding agents the same thing it has always given developers: clear conventions, expressive code, and a complete framework for turning ideas into production software.
01
Convention Over Configuration
Rails gives agents a map. Standard names, folders, commands, and patterns help generated changes land closer to idiomatic Rails with less prompting.
02
Token Efficiency
Less code means more context. Ruby and Rails express product ideas with fewer tokens, helping agents make smaller edits and move faster from request to working feature.
03
Quality Training Data
The patterns are everywhere. Decades of public Rails code give models strong signals for controllers, models, views, tests, jobs, migrations, and the glue between them.
04
The One Person Framework
One person can ship more. Rails provides the full product stack. Add an AI coding agent, and a solo builder can take on broader work without stitching everything together from scratch.
Agents on Rails
Which model is best?
Compare accuracy, speed, token efficiency, cost, and API recall across the same set of Rails evaluations.
Swipe to compare all model metrics →
Model<br>AccuracySuccessful runs<br>SpeedMedian<br>TokensMean per run<br>CostMean per run<br>API RecallRuns
OPUS-5
92.1%
9m 42s
47000
$1.9
31.7%
KIMI-K3
90.5%
12m 45s
51000
$1.09
23.8%
FABLE-5
90.5%
6m 47s
24667
$2.317
33.3%
GPT-5.6 Sol
84.1%
5m 4s
28000
$0.52
31.7%
MUSE-1.2
76.2%
15m 44s
68333
$1.687
22.2%
LUNA
73.0%
3m 19s
21000
$0.014
25.4%
GLM-5.2
66.7%
6m 0s
33000
$0.239
11.1%
DEEPSEEK
65.1%
6m 48s
44333
$0.031
7.9%
Accuracy vs. token efficiency
The strongest models rise toward the top-left.
Tokens<br>Speed<br>Cost
Swipe to explore every model →
Accuracy Higher is better
Mean tokens per run Lower is better
Higher is more accurate
Further left uses fewer tokens
Read the most recent benchmark report
Methodology
Each model ran every evaluation three times in August 2026, using the provider's default settings — 63 runs per model. Accuracy is the share of runs that passed the evaluation's hidden tests; refusals count as failures, and differences of a few points between models are within run-to-run noise. Speed is the median run duration, and tokens and cost are means per run. API recall is the percentage of runs in which the model reached directly for the target Rails API. Model-level medians come from run-level data, so they can differ slightly from the per-evaluation timings. Select any model or result for the underlying evaluation details.
Explore the open-source Rails AI evaluation suite.
Convention over configuration set the path for 20+ years of great training data for AI to use today. Not only does this mean agents do great with Rails, but also that squishy humans can quickly and confidently review the output without a jungle of distracting boilerplate.
David Heinemeier Hansson
@dhh
Rails' convention over configuration explains why I got very good LLM output quality in the early days of LLM-assisted coding while many developers still thought it was unusable. Most Rails codebases look the same and on average is high quality.
Marc Köhlbrugge
@marckohlbrugge
One of the killer features of using Rails in this AI era is "Convention over configuration". If you keep your project close to the Rails defaults, the AI knows so much already about your project… It makes things 100x faster.
Ivan Morgillo
@hamen
Evaluation<br>Framework<br>Target<br>Score<br>Time<br>Tokens/run<br>Cost/run<br>API Recall