Build Your Own Features.
You have the full source code. AI coding tools mean you no longer need to be a developer to extend it.
On February 25, 2026, Andrej Karpathy posted something worth reading carefully.
Karpathy co-founded OpenAI. He built Tesla's Autopilot AI team. He is not someone who overstates things. He wrote that programming has become unrecognizable since December 2025, when AI coding agents crossed a threshold of coherence and started working. He described spinning up an agent, giving it a task in plain English that would have taken a full weekend three months earlier, and coming back thirty minutes later to find it done. He hadn't touched anything.
His conclusion: the era of typing code into an editor, the way things have worked since computers were invented, is over. You give tasks in English and review the results.
That shift means something concrete for you as a Reward Loyalty owner.
Take Your Future Into Your Own Hands
You have the full source code. PHP, Laravel, clean architecture, no obfuscation, no encrypted files. Every feature you've wanted and waited for, you can now build yourself. By learning to direct, not to program.
Why We're Not Building It Faster
Development moves at the pace sales allow. Every feature has a real cost: understanding how it fits the existing multi-tenant architecture, writing it, testing it across hosting environments, documenting it, translating it into 10 languages, and maintaining it through every future update. Support tickets slow things further. Bugs come first.
We're not holding features back. We're working through a list that grows faster than one person can clear it. For the full picture on how development priorities work, see Feature Requests & Pricing.
If you don't want to wait, you don't have to.
What Changed
Until mid-2025, working with a codebase meant knowing the language. You had to understand PHP to extend PHP. You had to know Laravel's conventions to add a database column. The source code was yours in theory but unreachable in practice unless you were a developer, or willing to pay one.
That is over.
Karpathy described his own experience: in November 2025 he was still 80% manual coding, 20% AI. By December it had flipped, 80% AI, 20% manual. Four weeks. He called it the biggest change to his coding workflow in two decades of programming.
What caused the flip: AI coding tools now read your entire codebase, understand how it fits together, and implement changes from plain English instructions. They run into errors and fix them. They test their own work. They explain what they're doing at each step. When something breaks, you describe what you see and they diagnose it.
You are directing, not programming. That distinction is what makes this possible for everyone now.
The Tools
Cursor
The most used AI coding IDE right now. Built on top of VS Code, so the interface looks like a code editor: file tree on the left, editor in the middle, AI chat on the right. You open your project folder, describe what you want, and Cursor writes the code. It reads your entire codebase before answering, so it understands context.
Windsurf
Cursor's closest competitor, built by Codeium. Same core concept: AI-native editor, full codebase awareness, chat interface for instructions. Some users find Windsurf's agent behavior more autonomous for longer multi-step tasks. It keeps going through problems with less prompting. Worth trying if Cursor doesn't feel right.
Google Antigravity
Google's agent-first IDE, announced in November 2025 alongside Gemini 3. Built on a fork of Windsurf, it takes the concept further.
What sets Antigravity apart is its Manager View: a control center where you run multiple agents in parallel across different tasks simultaneously. While Cursor handles one thing at a time in a chat panel, Antigravity lets you dispatch several agents to separate problems at once and monitor them from a single dashboard. For larger extension projects, that's a meaningful difference.
Claude Code
For the more confident user. Claude Code runs in your terminal and operates as a full autonomous agent. It reads files, writes files, runs commands, searches for solutions, and works through complex multi-step tasks without stopping to ask permission at every turn. It uses Claude, Anthropic's model, the strongest programming model available at the time of writing.
Less visual than Cursor or Windsurf, more capable for complex tasks. If you're comfortable opening a terminal, this tool is worth learning.
What they cost
All of these are paid tools. Cursor and Windsurf start around $20/month. Claude Code requires a Claude Pro or Team subscription ($20+/month). Google Antigravity has its own subscription. Pricing changes, so check each tool's site for current plans. The cost is small compared to hiring a developer for the same work.
Which AI Model to Use
The IDE is the interface. The model is the intelligence behind it. Most tools let you choose.
Claude (Anthropic) is the recommended model for Reward Loyalty extension work. It handles Laravel codebases well: Eloquent relationships, Blade templates, middleware, and module boundaries. When Karpathy talks about his workflow flip, he's talking about Claude.
GPT (OpenAI) is the second choice for programming. Capable, widely supported, good at explaining its reasoning step by step.
Gemini (Google) via Antigravity performs better on frontend and design tasks than pure backend programming. When you're working on visual changes — layout, spacing, color, Blade templates — Gemini often produces stronger results than the others.
When in doubt: Claude for programming, Gemini for design.
Getting Started
Step 1. Get the source code on your computer
If you purchased from CodeCanyon, you have a ZIP. Extract it. You now have a folder with the complete Reward Loyalty codebase — every file, readable, yours.
If you're running Reward Loyalty on a server with automatic deployments, you can also clone the repository to your local machine. The files are the same.
Step 2. Install an AI IDE
We'll use Cursor for this walkthrough, but the same process works in Windsurf, Antigravity, or any AI IDE described above.
Download from cursor.com and install it. Open Cursor. Then: File → Open Folder → select your Reward Loyalty directory.
You'll see the file tree on the left. Every folder and file in the project. You don't need to understand what any of it does yet. The AI does.
Step 3. Open the chat panel
In Cursor the AI chat lives on the right side. Think of it as messaging a developer who has read every file in your project and is waiting for your next instruction.
You type what you want. It reads, thinks, and writes code. You review. You say what to change. It changes it.
That's the loop.
The Prompts That Work
The quality of your instructions determines the quality of the output. These are tested patterns.
Always start here
Before asking for anything, orient the AI to your specific codebase. Paste this first, every single time you open a new session:
Read the full codebase. Understand the tech stack, the file structure,
and how the components connect to each other. This is a Laravel 13
application with modules in Modules/. Give me a summary of what you
found: the main folders, what each does, and how a request flows from
a route to a controller to a view. Confirm when you're ready to work.
Wait for the response. Read it. If anything sounds wrong, correct it before going further. An AI that misunderstands the architecture makes confident mistakes. This step costs two minutes and prevents most problems.
Planning a new feature
Never ask for code first. Ask for a plan.
I want to add [describe the feature in plain language].
Before writing any code, explain how you would implement this given
the existing architecture. Which files would you touch? What are the
risks? What edge cases should I know about? What approach would you
recommend?
Read the plan. If it sounds reasonable and doesn't involve touching files you weren't expecting, say:
That approach looks right. Implement it step by step. After each
significant step, tell me what you did, what you changed,
and what comes next.
The step-by-step instruction matters. It prevents the AI from making ten changes at once, leaving you unable to track what happened.
A real example
You want to add a "Happy Birthday" email that automatically sends members a bonus voucher on their birthday.
Start with the plan prompt above. The AI will tell you it needs to: add a date_of_birth column to the members table via a migration, update the member registration form to collect it, create a scheduled Laravel command that runs daily and checks for birthdays, generate a voucher for matching members, and send them an email using the existing email template system. It will identify the model, migration, controller, and Blade files involved.
Review that plan. If it sounds right, approve it. The AI implements one piece, reports back, moves to the next. When it's done you have a working feature — and you understand roughly how it was built because you followed each step.
Fixing something broken
[Describe what's broken]. Here's what I see: [paste the error message
or describe the visual problem exactly].
Read the relevant files and diagnose the issue before making any
changes. Tell me what you think is wrong and why.
Review the diagnosis. If it sounds right:
That makes sense. Fix it. Don't touch anything outside the files
directly involved in this issue.
That last sentence matters. Without it, AI tools sometimes "improve" things you didn't ask about and introduce new problems while solving the original one.
Making visual changes
I want to change [describe the visual element — be specific: which page,
which section, what it looks like now, what you want instead].
Keep changes isolated to the relevant Blade templates and CSS.
Do not modify any PHP logic or database structure. Show me exactly
what you plan to change before applying it.
Specific instructions produce better results. "Make the dashboard look better" produces worse output than "on the partner dashboard, make the analytics cards have rounded corners, reduce the padding, and use the accent color for the chart lines."
Replacing branding across the whole codebase
Find every instance of [old brand name / color value / logo filename]
across all files. List every occurrence with the file name and line
number. Do not change anything yet.
Review the list. Confirm it looks complete. Then:
Replace all of those with [new value]. List every file you
modified when done.
Find first. Change second. Always two steps for wide-reaching changes.
Understanding something before touching it
Explain how [specific feature or behavior] works in this codebase.
Trace it from the route definition through the controller to the
Blade view. Do not change anything.
Use this whenever you're unsure. Understanding before acting is the difference between a clean change and an afternoon of debugging.
After every change, verify
What did you change, exactly? List every file modified and describe
what changed in each one. Did you introduce any new dependencies?
What should I test before considering this done?
Make this a habit. It takes thirty seconds and gives you confidence the change is complete and contained.
Understanding the Reward Loyalty Codebase
When giving instructions to an AI tool, it helps to know the basic shape of the project. You don't need to memorize this — the AI reads it — but it helps you give better directions.
Modules. The application is split into modules inside Modules/. The main product code (loyalty cards, stamp cards, vouchers, etc.) lives here. Each module has its own routes, controllers, views, and models. When you tell the AI "I want to change the voucher system," it knows to look inside the relevant module.
Blade templates. The HTML lives in .blade.php files inside resources/views/ and each module's resources/views/ folder. These are the files you modify when you want to change what something looks like. Blade is Laravel's templating language — it looks like HTML with some {{ }} and @if / @foreach mixed in. The AI understands it natively.
Migrations. Database changes are done through migration files. When you add a new column or table, you create a migration. The AI will do this for you. You run php artisan migrate on your server to apply it.
Routes. Every URL in the application maps to a route file, which points to a controller method. If you want to add a new page, the AI creates a route, a controller method, and a Blade view. Standard Laravel.
Multi-tenant architecture. This is the most important thing to tell the AI when making changes that touch data: Reward Loyalty is multi-tenant. Every query must scope to the correct partner. The AI needs to know this so it doesn't create a feature that leaks data between businesses.
Working With AI Agents Well
The tools work. They work best when you direct them clearly.
One thing at a time. Five changes in one message produces worse results than five separate sessions. Finish one change, verify it, then move to the next.
Scope every instruction. Phrases like "don't touch files outside of X" and "don't modify any database models" are your guardrails. Use them. An AI with unlimited scope will wander into territory you didn't intend.
Read the plan before approving. Every capable AI tool explains its approach before writing code. Read it. If the plan touches files you weren't expecting, ask why before approving. Correcting a misunderstanding takes ten seconds. Undoing a wrong implementation takes longer.
Keep a backup. Before any significant change, copy your working folder somewhere safe. Better yet, use Git. Even if you don't understand it, the AI can help you set up version control so you can revert.
Mind the multi-tenancy. When asking for features that involve data, always remind the AI: "This is a multi-tenant application. All queries must be scoped to the current partner. Never expose data across tenants." This one sentence prevents the most serious category of bugs.
Test locally first. If possible, run Reward Loyalty on your own machine using Laravel Herd (free, macOS) or a local PHP environment. Make changes, verify they work, then upload to your live server. Never experiment on production.
When it goes wrong, be specific. "That broke the staff dashboard. When I click 'Award Points' on a member profile, I get a white screen. Here's the error from storage/logs/laravel.log: [paste error]. Revert that change and try a different approach." The more detail you give, the faster it gets resolved.
Push back when the plan seems off. If the AI proposes modifying ten files for something that should touch two, ask it to explain why. Sometimes the scope is necessary. Sometimes it's overcomplicating. You don't need to understand code to have good instincts about whether a change feels too large.
What You Can Realistically Build
Non-developers using AI coding tools are shipping things that required freelancers six months ago. Here's what's realistic for Reward Loyalty.
Do it today. Color and font changes across the platform, branding updates (logos, names), email template modifications, translation string edits, adding new fields to forms, dashboard layout tweaks, custom CSS for the customer-facing PWA, adding analytics or tracking scripts, modifying the member registration flow.
Achievable with a few sessions. New reward types, custom voucher templates, adding a new dashboard widget, SMS notifications (via a service like Twilio), modified point calculation rules, custom report exports, new admin pages, webhook integrations for external services, birthday or anniversary automations.
More involved but possible. Custom e-commerce integrations beyond the built-in widget, connecting to a specific POS system's API, building a custom mobile app wrapper, adding a new loyalty program type, integrating with CRM platforms, building custom analytics views with charts.
Worth hiring a developer for. Changes to the core multi-tenant isolation logic, payment processing integrations, complex real-time features, structural changes to the authentication system. Knowing where this line sits saves frustration.
Updates and Your Changes
When Reward Loyalty releases a new version, the one-click update replaces core application files. Custom changes you've made may be overwritten if they touch the same files the update modifies.
Before updating, back up your modified files. After updating, you can re-apply your changes. Open both the backup and the updated version, describe what you had changed, and let the AI re-apply the modifications to the new code.
For changes you want to survive updates, keep a list of what you modified and why. A text file tracking "changed X in file Y for reason Z" makes post-update recovery a ten-minute task instead of a guessing game.
The Timing
A year ago, extending a codebase without programming knowledge meant hiring someone or going without. The tools didn't exist at the quality needed. Now they do.
Your source code is on your computer. The feature you've been waiting on might be an afternoon away. Start with something small: ask the AI to explain one part of the codebase you're curious about. Make one change. See what happens.