Quick update from our side:

AI-driven PxPlus development with Git and automated deployment

We're working on a PxPlus-based ERP/logistics system and have set up a workflow where AI (Claude) doesn't just write the PxPlus source code, but also generates database definitions and NOMADS panels.

Everything runs through GitHub with automated deployment.

What the AI writes:

• PxPlus source code — Programs, API endpoints, calculations. The AI has full knowledge of the PxPlus language and writes code that compiles directly.
  
• Data Dictionary create scripts — Instead of manually creating table definitions, the AI generates create scripts for the data dictionary, describing the full database structure.
  
• NOMADS panels — The AI also generates screens. We export NOMADS panels to ".pxpnl" text files (the native PxPlus TO_CVS format). This format is human-readable and diffable.
  

Git workflow:

• Branches: feature branches → dev → test → main (live)
  
• Source only in Git: Compiled ".pxp" files are in ".gitignore"; only "src/" directories are committed.
  
• NOMADS watcher: A PowerShell FileSystemWatcher monitors ".en" library files. On every change, panels are automatically exported to ".pxpnl" text files, so the diff is visible in Git.
  

Automated deployment:
A deploy script ("deploy.sh") handles the full chain on the server:

• 1. git pull - fetch source code
• 2. Compilation - compile all source files with "pxplus -cpl"
  
• 3. Panel import - import ".pxpnl" text files back into the NOMADS ".en" libraries
  
• 4. Database migration - run new or changed create scripts to update the data dictionary
  
• 5. Environment routing - deploy across three environments with their own paths and branches (dev, test, live)
  

What this gives us:

• Version control on everything: Code, screens, and database structure, all as readable text in Git.
  
• Reproducible environments: Setting up a new environment is just a "git clone" + "deploy.sh".
  
• AI as a development tool: The AI has full knowledge of PxPlus syntax and conventions, the NOMADS format, and the data dictionary structure and generates working code including screens and database definitions.
  

We've released a significant update to our claude-pxplus-template that improves performance, context efficiency, and accuracy.
 
What's New:
 
🚀 Dedicated MCP Server
- Moved from embedded documentation to a specialized MCP server for PxPlus.
- Reduced context usage - documentation is now fetched on-demand via indexed search instead of Claude having to scan through markdown files.
- Faster response times - Claude can now quickly search through all PxPlus docs without context overhead
- Built-in syntax checking for PxPlus files (when PxPlus executable path is configured)
- Built-in compilation tool for PxPlus files (when PxPlus executable path is configured)
 
📦 One-Command Installation & Updates for VSCode
bash -c "$(curl -sSL https://raw.githubusercontent.com/Astecom/claude-pxplus-template/master/install.sh)"
- Automated setup process checks prerequisites and installs everything
- Run the same command to update to the latest version
- Smart CLAUDE.md handling - creates new or appends to existing without removing your custom instructions

Just a quick note for those working with Claude and PxPlus:

We've set up a Model Context Protocol server (MCP) via Context7, used purely as a documentation source for Claude Code in VS Code.
It contains the full PxPlus manual and related notes, cleanly structured and easy to query.

Claude uses the MCP to look up syntax, commands, and language behavior during code generation. We don't compile or run any code from the MCP, it's strictly a read-only knowledge base for the AI.

Creating a Context7 account is free, and adding the MCP to Claude is easy using their CLI:

claude mcp add --transport http context7 https://mcp.context7.com/mcp --header "CONTEXT7_API_KEY: YOUR_API_KEY"

If anyone's exploring similar setups or wants help getting started, feel free to reach out.

Hi HendersonS,

Happy to share! We've made our full Claude + PxPlus setup publicly available here:
👉 https://github.com/Astecom/claude-pxplus-template

This repo contains everything we use internally to get consistent results with Claude when working on PxPlus code. It includes:

The entire PxPlus manual, converted into Markdown for better parsing.

A detailed instruction file that explains PxPlus-specific behavior (like FOR/NEXT quirks), coding style preferences, and how Claude should run syntax checks and compilation using the executable.

Note: We've found that the quality of Claude's output depends heavily on having all this context loaded and available together in the workspace. Partial use tends to lead to the kind of mixed results you mentioned.

There's no separate reference program or isolated syntax script, Claude learns from the structure and instructions in context. Once that's in place, it tends to follow our conventions and workflow very effectively.

Also, expect that in the beginning Claude may still make syntax mistakes or miss certain PxPlus-specific details. But one of the powerful aspects of Claude is that you can explicitly tell it to avoid those mistakes in the future, and it will store those instructions for itself during the session. Over time, it gets noticeably better at anticipating issues and generating cleaner code, especially if you keep refining the instruction context to your standards.

Hope that helps, and if you have questions while getting it running, feel free to reach out.

Totally agree on the importance of having a maintained guidelines document. We've done something similar by creating a structured workspace with our coding standards, naming conventions, and some PxPlus-specific notes (like how FOR/NEXT loops always run at least once). Everything is in Markdown and lives alongside the code, so the AI has consistent access to it.

Interestingly, the setup didn't take us that long, but that might be because we already had some experience using AI for development in other languages, especially Python and web-based tools. That helped us approach the prompt structure and environment setup.

We've also moved away from relying on AI to "look up" documentation. Instead, we embed the entire PxPlus manual (converted to Markdown) directly into the workspace. That avoids the classic "I double-checked this" hallucinations, because the model actually has the correct references. This made a huge difference in consistency and correctness.

One key difference for us has been switching from ChatGPT to Claude. In our experience, Claude has proven to be significantly stronger when it comes to programming tasks, not just in code correctness, but also in following patterns, preserving structure, and avoiding hallucinated syntax. It feels much more grounded in logic and context, especially when the reference material is present.

The idea of prototyping in Python and converting to PxPlus could be a good idea. We haven't tried that yet, but it could work well for logic-heavy routines. That said, we've had good results generating PxPlus directly, especially when the AI can reference to a well-written example program.

All in all, we're seeing real time savings now that the setup "complete". What used to take days is now sometimes reduced to hours, or even less.

Hi Mike,

Thanks for sharing your experience, great to hear others are exploring this as well.

We're using Claude through VS Code with the Claude Code extension. To give it proper context, we converted the entire PxPlus manual into Markdown files and added them to the workspace. That way, Claude has direct access to the full documentation while writing or reviewing code, which noticeably improves accuracy.

We also included a reference program in the workspace. Interestingly, Claude automatically tries to match the structure, naming, and logic style it sees in that code, even without explicitly prompting it to do so. That's been a big help in keeping generated output aligned with our internal conventions.

In addition, we wrote a few short instruction files, kind of like "developer notes", to clarify specific PxPlus behaviors that differ from other languages. For example, we explained that FOR/NEXT loops always execute at least once, which is different from how most languages handle them. Claude takes those notes into account when generating logic, which helps avoid subtle errors.

Before we let Claude generate any code, we often ask it to first read and summarize these internal notes, so it's "aware" of the domain-specific things before starting. That small step has made a big difference in the quality and reliability of its output.

We also added instructions for how to perform a syntax check and compile the program using our PxPlus executable. Claude frequently includes those steps itself now, helping catch issues early.

Hi everyone,

At our company, we've been working extensively with AI across different domains, including the generation of web applications and business logic. Lately, we've applied it to PxPlus development, and the time savings have been nothing short of dramatic.

We're not just using AI to suggest snippets. The AI actually:

• Generates complete PxPlus programs
  
• Performs its own syntax checks
  
• Fixes code automatically
  
• Creates test routines
  
• Compiles and validates everything end-to-end
  

As an example: we had it generate a complex bin packing algorithm with multiple packing strategies, a task that would normally take several weeks of design and coding. With AI, we had a working version within one day, including multiple packing methods.

Even more impressively, the AI also produced an HTML file with a live 3D model of the box and its packed contents, making validation and demonstration far more intuitive.

We're not yet applying it to Nomads or PxPlus-level file I/O, but for logic-heavy tasks and algorithms, the time savings are massive, what used to take days now takes hours, and in some cases, minutes.

---

We'd love to hear from others in the PxPlus community:

• Have you tried using AI in your PxPlus development flow?
• Would you trust AI-generated logic in production?
• Which tasks would you delegate to AI, and which not?

Looking forward to the discussion!

Hi Phil,

we do offer custom development services using PxPlus. At Astecom, we've been working with PxPlus for many years and provide tailored solutions for clients who need either standalone development or enhancements to existing PxPlus-based applications. So yes, there are still companies actively doing custom work with PxPlus. We're one of them.

Would love this feature, could you please look into this?

If I want to get the contents of a column, it would be nice if we could use the column name instead of number.
Like this:

GRID FIND ctl_id, columnName$, row, var$