Most people blame Claude for strict limits. I blamed Claude too. Recently I realized that Claude doesn't count the number of messages. it counts tokens. All you need to do is use tokens wisely, but not everyone knows how to do that and ends up losing a lot of tokens and money as a result. I got really into this and put together a list of the best habits that will save you a ton of tokens. 1. Edit your prompt. Don't send a follow-up When Claude doesn't get your thoughts right, you might feel tempted to send: 1/ “No, I meant [your message]” 2/ “Ugh, that's not what I wanted [your message]” and so on Don't do that! Every subsequent message is added to the conversation history. Claude re-reads ALL of it every turn - burning tokens on context that didn't even help. Token cost per message = all previous messages + your new one. Total = S × N(N+1) / 2 (S = avg tokens per exchange, N = message count) At ~500 tokens per exchange: 5 messages: 7.5K tokens 10 messages: 27.5K tokens 20 messages: 105K tokens 30 messages: 232K tokens Message 30 costs 31x more than message 1 Instead: click Edit on your original message → fix it → regenerate. The old exchange gets replaced, not stacked. 2. Start a fresh chat every 15–20 messages In the previous section, I showed how token costs grow with every message. Ideally, you should start a new chat every 15–20 messages. Now imagine a chat with 100+ messages. At ~500 tokens per exchange, that's over 2.5 million tokens burned - most of it just re-reading old history. One developer tracked his usage and found that 98.5% of tokens were spent on re-reading the history. Only 1.5% went toward actually outputting the result. When a chat gets long → ask Claude to summarize everything → copy it → new chat → paste as first message. 3. Batch your questions into one message Many people believe that splitting questions into separate messages leads to better results. Almost always, the opposite is true. Three separate prompts = three context loads.

This is why I love Lovable. Number two. And this time I have a completely different insight to share. This section did not take one prompt. It took time. Back and forth, message by message, token by token. And somewhere in that process I figured out something that changes everything about how you talk to Lovable. The language matters. I built myself a jargon — the actual vocabulary that web builders use — and when you speak to Lovable in that language it understands you faster, executes cleaner, and wastes far less credits and time. The difference is significant. Tell me in the comments if you want me to upload that to the classroom. Because here is the good news for you. I distilled every insight from that entire build process — every message, every correction, every token — into one single prompt that is already waiting for you in the classroom. I did the painful part so you do not have to. Honestly this time I am not completely happy with the visual result. But I said I would post and I posted. I will improve it next week and drop the updated version when it is ready. Next week we are adding two more sections to The Outliers Vodka site. Both fully documented as always. Worth following closely. Everything is already in the classroom. Go check it out.

I see you guys building absolute magic with Lovable in record time. Going from an idea to a fully functional app in a weekend is a superpower. But here’s the harsh truth: speed often comes at the cost of security. If your app handles user data, processes payments, or stores anything mildly sensitive, you cannot afford to skip a security check. To save you hours of headaches (and potential data leaks), I've put together a Copy-Paste Prompt Arsenal. Drop these exact prompts into your Lovable chat to bulletproof your app right now: 🏗️ 1. The RLS & Storage Lockdown Row Level Security (RLS) is like a bouncer for your database. Without it, anyone who finds your database URL can access everyone's data. (Copy & paste this into Lovable): Review all RLS policies in my Supabase database. Fix any policies that expose personally identifiable information, allow users to access other users' data, or permit privilege escalation. Also, check my storage bucket configuration to ensure private user files are in private buckets with proper access controls. 🔒 2. API, Auth & Bot Protection Don't let unauthenticated users or bots bypass your UI and spam your endpoints directly. (Copy & paste this into Lovable): Review all API endpoints and Edge Functions for auth vulnerabilities. Flag any endpoints unauthenticated users can access. Check for XSS and SQL injection risks. Verify my password requirements enforce strong passwords, add rate limiting to sensitive endpoints, and ensure my login/signup forms have bot protection. ⚠️ 3. The Deadliest Mistake: Exposed API Keys Never paste your raw API keys (like OpenAI or Stripe) directly into the Lovable chat! They live in your chat history forever and can be scraped if someone remixes your project. (Copy & paste this into Lovable to check for leaks): Review my codebase for exposed API keys or secrets. Check for hardcoded keys in frontend code, API calls that should go through Edge Functions, and any use of the Supabase service role key outside of Edge Functions.