The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Imagine hiring a librarian with one strict rule: never answer from memory. Only from the books on the shelf.
That is exactly how a RAG chatbot works, and it is my favourite thing to build right now.
Here is the fun part of how it goes:
🔎 You ask a question. “What is the refund policy?”
📖 The librarian runs to the shelf. The system searches your documents by meaning, not just keywords, and grabs the few passages that matter most.
✍️ Then the AI writes the answer, using only those pages. Nothing else.
🤷 And if the shelf has no answer? The librarian says “I could not find that.” I think this is the most underrated feature of all. A bot that admits it does not know is worth more than one that sounds sure and is wrong.
I have built retrieval pipelines like this with OpenAI and Anthropic models, plus a car-dealership chatbot where four AI agents split the conversation between them, a bit like a small team where each person has one job.
A tiny experiment you can try: take any chatbot you use and ask it something it could not possibly know, like a specific detail about a private document. Does it admit it, or does it invent something? You learn a lot about a bot in that one question.
👇 Your turn: what is the funniest or most confident wrong answer a chatbot has ever given you? I want stories.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
42% of failed startups built something nobody needed.
That is from one CB Insights analysis of 101 founder post-mortems.
Not bad code. Not bad luck. Nobody needed it.
If you are building an AI product...this is the cheapest fix you will ever make...
Ask these 5 questions BEFORE you build...
1. Who exactly has this problem?
Everyone is not an answer. Name a job title.
2. How are they solving it today?
If they are not solving it at all, it may not hurt enough.
3. What does it cost them?
Hours, money or missed deals. Get a number.
4. Would they pay for a fix this month?
Ask for a pre-order or a pilot, not a compliment.
5. Who have you talked to this week?
Aim for 5 real conversations before writing a line of code.
Copy-paste prompt to prepare your interviews:
I am building [product] for [job title]. Write 10 customer interview questions that uncover how they solve [problem] today, what it costs them, and what they have already paid for. No leading questions.
Compliments do not validate a product.
Payments and pilots do.
Save this before your next build sprint.
Follow me to meet again
Daily learn with me (Maryam Tehsin)
Such an important reminder! 👏 It's easy to focus on building a product, but understanding the customer's real problem should always come first. Real feedback is worth more than compliments!
Giving AI full access to your business data is risky. Giving it no access makes it useless.
So I built a small server that sits in the middle. Claude can search and read my agency records, but it cannot change anything on its own. Every change needs a human to approve it first, and every answer shows which record it came from.
I use it every day with Claude Code.
If you want AI to work with your own systems safely, I can build the same for you.
I'd bind each approval to the proposed field changes and the record version it was reviewed against. If someone edits an agency record while a change is waiting, does your server require a fresh approval before applying the proposal to the newer data?
Aisle is an AI wedding planner that does the work for you. 💍
It finds real vendors, emails them, turns their replies into side-by-side quotes, negotiates when a quote is over budget, and books with one tap. It also chases RSVPs, reminds you of payments, and makes a mood board every vendor sees. You just decide.
It works for every tradition and for weddings that last more than one day.
Built on Base44: entities, 23 backend functions, 5 workflows, an AI agent, and InvokeLLM + GenerateImage.
Live demo: https://aisle-3264f1eb.base44.app/demo
