Home
Documentation
Click-Coder works with most programming languages.
See the Run menu above for more details.
The Next Step Tip control below the toolbar will guide you thru these steps:
Please click on “Run” on the menu above.
This is where you enter your request. You can add a URL (with www) – the webpage will be included in the context sent to the LLM.
Click the model selection drop list on the status bar to change models. New users will start with the model prefixed with CC which sends requests through the Click-Coder server to Anthropic. The other options are if you want to use your own API account (see “Private API” below).
You can use your own API account (not go through the Click-Coder server) with Anthropic or OpenAI and only pay the small monthly fee for the Click-Coder software:
Click here
Have a suggestion to improve these docs or the app? Please drop us a note – we listen.
– creates a new folder to hold a new project.
– selects a folder containing existing code.
– saves any edits made in the Workspace.
– switches between recently used projects.
– saves a copy of the files in the file tree so you can revert to the current state later. This is useful when your project reaches an improved state and you want to be able to restore to that state if subsequent changes don’t work. This feature is mainly useful when you are not using a more advanced version control system like GIT.
– restores all your code to the last snapshot. If you want to revert to an older snapshot first use File | Version | Show and delete the newest snapshot(s).
– updates the file tree with any changes – normally automatic.
– shows files that do not contain “Summary:” – see Settings.
– creates an AI summary at the top of files selected in the file tree. This improves the accuracy of the Suggest feature.
– shows a list of files not filtered by your settings – see Settings below.
– unchecks any files you checked.
– login to use the AI features.
– see Settings
– show dialog of recent Requests – select one and click OK to load the Request box and select the indicated files.
– opens a control for searching inside the Workspace.
– creates a report showing the number of files of each type, the lines of code, and character count.
– shows a list of prompt modifiers you might want to add to your Request. You can set up your own reference via Tools | Setting | File Paths | Reference File.
– enables checkboxes next to files listed in Request box.
– shows logs of your activity, which is often useful to go back to something you were working on previously.
– creates a file of the current data which you can send to tech support if you want to report an issue.
– opens the folder containing your settings, logs, snapshots, etc. You will likely want to back up some or all of this data. You can also use these files to set up Click-Coder on a new computer.
– opens the folder containing debug logs you can email to support if needed.
Access the Settings dialog via which covers the following settings:
This setting toggles a feature that recommends the next step while learning Click-Coder.
This setting affects how the Suggest command works for suggesting which files are needed given your Request.
Keeping files relatively small and modular also helps (files in the Click-Coder project itself average 4kb).
The Rules file allows you to specify what you want the LLM to know about your project. It is recommended to create a file at the specified path. The file will be included in all submissions to the LLM, so be concise. Items that can help the LLM include: an overview of the purpose of the app; framework used; common utility function signatures that might not be included in each context, style rules, etc.
It is recommended to create a file at the specified path so you can use the Run button to run your program from Click-Coder. In the file include commands needed to run your program – this varies based on the programming language / compiler, etc. If this file is not included, Click-Coder will try to run you program directly if in Python, Node.js, batch file, or Java.
You can create a file at the specified path with quick reference data such as frequently use prompts or anything else that you want to refer to often.
As soon as you get your app working, use File | Version | Snapshot to create a copy of the working program. If you skip this step and make additional changes that lead to errors you will not easily be able to go back to the working version. If you are using Click-Coder with an IDE you can use GIT instead.
Detailed requests work better than very short ones and reduce the number of iterations needed to get the result you want. For example “Create TicTacToe” will work but this is better: “Create a TicTacToe game in Python. Split the code to Main and Config. In Config allow to set the size of the game like 3×3 or 4×4. Draw a red line thru the winning cells. Make the grid lines black and 5 pixels wide. Make cells 100 x 100 pixels. Use a white background. Include a Restart button centered below the cells.”
Don’t be surprised if you have to make multiple attempts to solve a problem or get a feature right or develop a new app. Often individual changes are completed in 1 or 2 tries but sometimes can take up to 10 or even more. Full apps can take dozens or even hundreds of iterations to fine tune how the app works and fix issues. This is so because it’s often hard to know what you want until you build it and use it, and because current LLMs don’t always get it right. If you don’t agree with a change or a change did not do what you want you can:
Try not to use up the allocation of 1,000,000 free tokens too fast. Initially, we recommend to aim to keep token estimates per SEND under 25K (allowing ~40 Requests) and ideally around 10K (allowing ~100 Requests).
The token count shown on the status bar or in a pop-up is an estimate of the tokens (basic unit of text) to be used for a SEND to the LLM.
There are several ways to reduce token usage:
Actual tokens can differ substantially from estimates as shown via menu Log | Stats.
Tokens for the Suggest command are usually lower and not reflected by the status bar value.
While most chatbots feed your conversation history back in to the LLM for each submission, we found that this creates several problems when used for coding. It reduces transparency as to what the LLM sees; uses more tokens and can confuse the LLM. So we don’t do that. We found it better to modify the prompt or the code to record anything you want the LLM to consider with each submission.
To ask a general question, deselect all files and enter your question in the Request box.
In addition to coding, Click-Coder works well for project planning (of coding and non-coding projects). For example, suppose you are designing an electronic circuit but not sure which microprocessor to use, which type of circuit to use, which other components, which software tools, etc. So you start a conversation with a chatbot. As the chat develops it starts to get long and disorganized. You’ll waste time scrolling back to prior sections and end up with a document that is difficult to use. Instead create some files to give structure such as Circuits, Components and Software. Then use Click-Coder. When you ask a question about Components for example, select only the Component file as the context and ask the question in a way that modifies the document. Along the way, delete text you don’t need or edit as needed. This way you will build an organized plan that is easy to reference and put into action without scrolling thru a long cumbersome chat. Use Click-Coder for:
Delegate to AI but don’t completely relinquish oversight or control. Check the final results.
To run your app go to the appropriate section below depending on which language Click-Coder used.
Click the main file with .java extension and then the RUN button. If you encounter an error, use the Build button to create and install dependencies.
Click index.html and then the RUN button. If you encounter an error, use the Build button to create and install dependencies.
Usually you will have a file named index.html in the file list. Click on that file to select it. Then click the RUN button. If you encounter an error, use the Build button to create and install dependencies.
For additional capabilities install node.js which extends JavaScript beyond the browser by providing a server-side runtime, filesystem and networking capabilities, and a vast ecosystem of third-party packages.
For a Python app, install Python and specify to include Python in the “environment variables” as described next.
If you already have Python installed make sure the path to Python is setup in the environment variables as follows: Windows Start menu | Environment Variables | button Environment Variables | System Variables | Path | Edit | New | enter path such as “C:\Program Files\Python311\” depending on Python’s location and version | OK | OK | OK.
After Python is installed, go to Click-Coder and click on a file named main.py or similar in the file list. Then click the RUN button. If you encounter an error, use the Build button to create and install dependencies.
If the RUN button opens Notepad or another editor, it is likely because you previously selected that app to open files with the respective file extension. You can fix this in Windows | Settings | File Extensions by removing the entry.
For .bat files simply click on the file in the file list and then click the RUN button. If you encounter an error, just paste the error into the Request box and click SEND.
If you have specific requirements to run your app, enter the needed commands in the run.bat file found in the .click-coder folder in the root of your project. For example, see the commands in the section above. The RUN button will then launch the run.bat file.
These languages require additional tools such as compilers or an IDE (Integrated Development Environment) such as Visual Studio. After approving code changes in Click-Coder you can use your IDE to build and run, or setup Click-Coder by placing compile commands in .click-coder\run.bat. This method allows you to feed compiler errors directly into Click-Coder so you can SEND them for repair without cutting and pasting errors into Click-Coder. Click-Coder will copy the output from the path after “Compiler-Output:” (see code below) to the Click-Coder Request edit. Here is an example of .click-coder\run.bat (your setup will likely differ):
SET MSBUILD=”C:\Program Files\…MSBuild.exe”
SET SOLUTION_PATH=”C:\…”
SET BUILD_PATH=c:\temp\build
SET OUTPUT_FILE=c:\temp\build\build_output.txt
IF NOT EXIST %BUILD_PATH% mkdir %BUILD_PATH%
IF EXIST %OUTPUT_FILE% del %OUTPUT_FILE%
%MSBUILD% %SOLUTION_PATH% /nologo /t:Rebuild /p:Configuration=Debug /p:Platform=x64 /p:TargetFramework=net8.0 /p:OutputPath=%BUILD_PATH% /m /clp:ErrorsOnly >> %OUTPUT_FILE% 2>&1
echo Compiler-Output: “c:\temp\build\build_output.txt”
exit /b %ERRORLEVEL%
If you want to launch Click-Coder directly from your IDE, simply type “clickcoder” in the terminal.
When creating a new project in Click-Coder it will usually create the needed boilerplate files. Alternatively, you can:
By combining user-centric design with next-generation artificial intelligence, Click-Coder empowers you to develop quality software faster than ever.