Built for RStudio

Your AI assistant, inside RStudio

AiR lives in your Viewer pane. Fix errors, generate complete EDA reports, edit code, and understand your data — without leaving your IDE.

Get Started FreeSee what it does

Everything you need, right in RStudio

No context switching. No copy-pasting to ChatGPT. AiR understands your code, your data, and your errors — and fixes them in place.

Error Fixing

Errors caught and fixed automatically

When your R Markdown fails to knit or your script throws an error, AiR detects it instantly. It reads the full error output, diagnoses the root cause, and proposes a fix — showing you exactly what changed with a color-coded diff.

  • Detects knit failures, console errors, and warnings
  • Reads full stack traces and render logs
  • Shows exact changes with accept/reject controls
  • Iterates if the first fix doesn't work
AiR — Viewer Pane
Ai
AiR
ChatDataUsage
regression.Rmd
Error in lm(price ~ carat + , data = diamonds): unexpected ","Fix
U
You
Fix it
Ai
AiR

There's a trailing comma in your formula. Here's the fix:

regression.Rmd
+1-1
-model <- lm(price ~ carat + , data = diamonds)
+model <- lm(price ~ carat + cut, data = diamonds)
summary(model)
AcceptReject
AiR — Viewer Pane
Ai
AiR
ChatDataUsage
explore.R
U
You
/eda diamonds deep
Ai
AiR

Planning a deep EDA for diamonds (53,940 rows, 10 columns)...

Analysis Plan
1. Distribution of numeric variables (carat, price, depth, table)
2. Frequency analysis of categorical variables (cut, color, clarity)
3. Price correlations and interaction effects
4. Statistical tests (normality, ANOVA by cut)
5. Multivariate visualizations with faceting
Created file: diamonds_eda.Rmd (247 lines)
EDA Reports

Full analysis reports in seconds

Say /eda and AiR generates a complete R Markdown report — distributions, correlations, statistical tests, and narrative insights. Choose quick, standard, or deep depth.

  • Generates complete .Rmd files with visualizations
  • Three depth levels: quick overview to full statistical analysis
  • AI plans the analysis strategy before generating
  • Validates R code and audits insights for accuracy
Code Editing

Edit code with natural language

Describe what you want changed and AiR edits your active file directly. Refactor functions, add documentation, restructure code — all shown as a diff you can accept or reject.

  • Edits your active file in RStudio directly
  • Color-coded diffs with line-by-line changes
  • Accept or reject with one click
  • Understands your full project context
AiR — Viewer Pane
Ai
AiR
ChatDataUsage
clean_data.R
U
You
Add input validation to the clean_survey function
Ai
AiR

I'll add input validation at the top of the function:

clean_data.R
+4-0
clean_survey <- function(df, threshold = 0.5) {
+ if (!is.data.frame(df)) stop("Input must be a data frame")
+ if (nrow(df) == 0) stop("Data frame is empty")
+ if (threshold < 0 || threshold > 1) stop("Threshold must be 0-1")
+
df %>% select(where(~mean(!is.na(.)) >= threshold))
AcceptReject
AiR — Viewer Pane
Ai
AiR
ChatDataUsage
diamonds53,940 x 10
caratdbl0.23, 0.21, 0.23...
cutfctIdeal, Premium, Good...
colorfctE, I, J, H, F, D...
priceint326, 326, 327...
mtcars32 x 11
mpgdbl21.0, 21.0, 22.8...
cyldbl6, 6, 4, 6, 8...
hpdbl110, 110, 93...
Smart Context

Understands your R environment

AiR automatically syncs with your R session. It knows every dataframe loaded, their columns, types, and distributions. When you ask for help, it already has the context.

  • Live sync with your R environment
  • Sees all loaded dataframes with column metadata
  • Knows your project file structure
  • Reads your active file and selected code
Instant Data Profiling

Profile, summarize, and explore — one click

The Data tab gives you instant insight into every loaded dataframe. Click any column to see its distribution, stats, and missing values. Then go further — hit Run EDA to generate a full exploratory report, or Summary for a quick statistical overview. No code required.

  • Click columns to see histograms, bar charts, and stats instantly
  • Run EDA — generates a complete .Rmd analysis report
  • Summary — quick statistical overview of any dataframe
  • Data cleaning tools coming soon
AiR — Data Explorer
Ai
AiR
ChatDataUsage
diamonds53,940 x 10
Run EDASummary
priceint326 — 18,823
Distribution
mean 3,933med 2,401
32618,823
caratdbl0.20 — 5.01
Distribution
mean 0.80med 0.70
0.205.01
cutfct5 levels
Top values5 levels
Ideal
21,551
Premium
13,791
Very Good
12,082
Good
4,906
Fair
1,610
colorfct7 levels
depthdbl43.0 — 79.0

Up and running in 60 seconds

Three commands. That's all it takes.

1

Install the R package

Install AiR from GitHub with a single command.

# Install AiR
devtools::install_github("useAiRStudio/air-package")
2

Authenticate

Run air_login() to link your account. A browser window opens for sign-in.

# Authenticate (opens browser)
AiR::air_login()

✓ Authentication complete
3

Launch the panel

Start AiR and it opens directly in your RStudio Viewer pane.

# Launch AiR in the Viewer pane
AiR::air_start()

✓ AiR panel opened in Viewer

Simple, transparent pricing

Start free. Upgrade when you need more.

Free

Get started with AiR at no cost.

$0 / forever
  • 50 requests per month
  • Error fixing & diagnosis
  • Code editing with diffs
  • EDA reports (quick depth)
  • Smart context sync
Get Started
Popular

Pro

Unlimited access for power users.

$20 / per month
  • Unlimited requests
  • All Free features
  • Deep EDA reports with statistical tests
  • Priority response times
  • Data cleaning & modeling pipelines
Get Started