PumasAide

PumasAide is a bridge between AI assistants and Pumas. You describe analyses in natural language; the AI uses Pumas tools on your behalf and returns results.

New to Pumas?

Jump straight to NCA Analysis Walkthrough or Population PK Walkthrough to see PumasAide in action, then return here to learn more.

What Can You Do with PumasAide?

Here are examples of what you can ask:

  • Load and transform data: "Load the PK data from study_data.csv and show me the first few rows"
  • Build models: "Create a two-compartment model with first-order absorption"
  • Fit models: "Fit this model to my data using FOCE"
  • Run NCA: "Calculate AUC, Cmax, and half-life for each subject"
  • Simulate: "Simulate 100 subjects at 50mg, 100mg, and 200mg doses"
  • Visualize: "Create a VPC plot comparing predictions to observations"

Every action generates reviewable Julia code, so you learn Pumas syntax while getting results.

How It Works: Tools and Tool Calls

When you make a request, the AI assistant doesn't just generate text—it makes tool calls to PumasAide. Each tool call is a specific action with explicit parameters.

For example, when you ask "Load my PK data from study.csv", the AI makes a tool call like:

Tool: load_dataset
Parameters:
  file_path: "study.csv"
  dataset_name: "pk_data"

This approach gives you:

  • Traceable actions: Every operation is logged with its exact parameters
  • Reviewable parameters: You see what the AI is actually doing, not just what it says
  • Direct code mapping: Each tool call generates corresponding Julia code in programs/
  • Learning opportunity: Watch how natural language maps to specific Pumas operations
What's a 'tool'?

In AI terminology, a "tool" is a function the AI can call to perform actions. PumasAide provides tools for data loading, model building, fitting, NCA, plotting, and more. The AI chooses which tools to use based on your request.

Capabilities

  • Load and transform pharmacometric data
  • Perform non-compartmental analysis (NCA)
  • Build and fit population PK/PD models
  • Run simulations for dose selection and trial design
  • Generate publication-quality plots and tables
  • Create formal analysis reports

See the NCA Analysis Walkthrough and Population PK Walkthrough for complete worked examples.

Why Use It

  • Natural language interface: Describe goals instead of writing code
  • Guided workflows: Built-in steps for data preparation, model specification, and quality checks
  • Reproducible output: Every tool call generates Julia code saved to programs/
  • Standard Pumas packages: Generated code uses Pumas, NCA, AlgebraOfGraphics, SummaryTables—transferable to manual workflows
  • Learn while doing: Every tool call shows you exactly what parameters are being used. Watch the AI work and learn Pumas patterns naturally. Use pumas_docs_search to look up any function you're curious about.

Data Privacy

Your data flows only to your chosen LLM provider (Anthropic, OpenAI, Google, etc.). No analysis data is sent to PumasAI. You control your data and can select providers that meet your compliance requirements.

How It Works

PumasAide runs in the background in your Julia REPL. When you describe an analysis, your AI assistant uses PumasAide tools to run Pumas operations and return results.

Generated code: Every tool call saves executable Julia code to programs/. You can review, edit, and rerun this code independently.

Persistent workspace: Objects (DataFrames, models, fit results) stay in memory across tool calls, so each step builds on previous results naturally.

Live preview: View plots, tables, and results at http://localhost:8081/preview while working.

The generated code uses standard Pumas packages (e.g.: Pumas, NCA, Bioequivalence, AlgebraOfGraphics, SummaryTables), so everything you learn transfers directly to manual Pumas workflows.

Suggested Learning Path

Beginner:

  1. Start with the interactive tutorial: ask "Start the interactive tutorial for NCA analysis"
  2. Follow the NCA Analysis Walkthrough or Population PK Walkthrough
  3. Try basic visualizations with your own data

Intermediate:

  1. Build a PopPK model from scratch using natural language
  2. Review the generated code in programs/ to understand Pumas syntax
  3. Use Workflows for structured analyses

Advanced:

  1. Create custom workflows for your organization's standards
  2. Edit generated code directly for specialized needs
  3. Combine PumasAide sessions with manual Pumas coding

Next Steps