Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

How do you stop one customer from seeing another customer's data when they're all on the same database? I've been building SmartFarmAI in Rust farms from 550 to 60,000 birds all sharing one PostgreSQL database. This is the full breakdown: → Schema design with composite foreign keys → PostgreSQL... show more

chinedu🦀

9,081 subscribers

13,481 views • 4 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

This is, by far, one of the best uses of modern AI. If you don't use embeddings when querying your database, you are definitely leaving a lot on the table. In this video, I'll show you how to run semantic searches using OpenAI and PostgreSQL. It's all thanks to Pgai, an open-source PostgreSQL extension: Here's what will happen: 1. We'll create a simple table with news articles 2. We'll generate embeddings for those articles 3. We'll run queries on top of those embeddings For this video, I generated the embeddings using a simple query, but pgai Vectorizer would do the same automatically as new information makes it into the database. This is awesome! If you have a PostgreSQL database with data you are searching over, you should start experimenting with semantic searches immediately. For most use cases, a combination of full-text search + semantic search is the best approach. If you don't have a PostgreSQL database around, you can try free for 30 days using Timescale: Thanks to the TimescaleDB (by Tiger Data) team for partnering with me on this post!

This is, by far, one of the best uses of modern AI. If you don't use embeddings when querying your database, you are definitely leaving a lot on the table. In this video, I'll show you how to run semantic searches using OpenAI and PostgreSQL. It's all thanks to Pgai, an open-source PostgreSQL extension: Here's what will happen: 1. We'll create a simple table with news articles 2. We'll generate embeddings for those articles 3. We'll run queries on top of those embeddings For this video, I generated the embeddings using a simple query, but pgai Vectorizer would do the same automatically as new information makes it into the database. This is awesome! If you have a PostgreSQL database with data you are searching over, you should start experimenting with semantic searches immediately. For most use cases, a combination of full-text search + semantic search is the best approach. If you don't have a PostgreSQL database around, you can try free for 30 days using Timescale: Thanks to the TimescaleDB (by Tiger Data) team for partnering with me on this post!

Santiago

110,133 views • 1 year ago

No more April Fools jokes, I'm still at Replit ⠕. Now this is real big thing: Replit Agent can now build mobile + web apps in the same project, from one prompt. Mobile and web share the same backend + database. this used to take two frontend teams, with separate stacks, and a backend team. now Replit Agent has been upgraded to handle all. including shipping to web and App Store If you are building your own product, this is my gift for you here are 3 examples with prompt instructions ↓

No more April Fools jokes, I'm still at Replit ⠕. Now this is real big thing: Replit Agent can now build mobile + web apps in the same project, from one prompt. Mobile and web share the same backend + database. this used to take two frontend teams, with separate stacks, and a backend team. now Replit Agent has been upgraded to handle all. including shipping to web and App Store If you are building your own product, this is my gift for you here are 3 examples with prompt instructions ↓

Zhen Li

20,802 views • 4 months ago

Hello everyone, i've been very very busy with the Contra Force port. Specifically, this IRQ sequence in stage 4 which i've converted to HDMA. Hands down, the most difficult split screen i've worked on in all my years. The part that stinks about this, is the developers have the construction of the additonal sequences like this, different from this one i've worked on. So all of the wing-to-wing sequences in this have to be different from the on i've just done here. Once this level is complete, it's full speed ahead. I'm hoping for a beta before Christmas for everyone. Thank you all for your continued support and interest in these ports! 🙂

Hello everyone, i've been very very busy with the Contra Force port. Specifically, this IRQ sequence in stage 4 which i've converted to HDMA. Hands down, the most difficult split screen i've worked on in all my years. The part that stinks about this, is the developers have the construction of the additonal sequences like this, different from this one i've worked on. So all of the wing-to-wing sequences in this have to be different from the on i've just done here. Once this level is complete, it's full speed ahead. I'm hoping for a beta before Christmas for everyone. Thank you all for your continued support and interest in these ports! 🙂

infidelity

11,106 views • 8 months ago

Whitelist Database — BIG UPDATE 🎯 Spent a lot of time on this. Today we finally ship it. The Database became a full daily tool, not just for retro hunting. Here is everything that changed 👇 Main page: Now organized by narratives: Prediction, Perp, DeFi and more. Each project has current actions, investments, TVL and Twitter in one row. 📰 News feed with latest project updates all with dates and exact steps. Sections: • PerpDex Metrics: volume, OI, fees 30D across all platforms + fee breakdown • Crypto Tools: research, on-chain analytics, every tool in one place • AI Learning Materials: articles, prompts, agent courses, Claude Code breakdowns • Crypto Calendar: all deadlines and claims on one screen, Google and Apple Calendar integration • Airdrop Archive: database of all past drops with real results 👉 Go check: One place for active farming, analytics, deadlines and learning. Works for beginners and experienced players equally. This is not the final version. We keep building and your feedback shapes what comes next. If the database helped you 🔁 and QRT this tweet. Follow Whitelist Media don't miss out on new projects.

Whitelist Database — BIG UPDATE 🎯 Spent a lot of time on this. Today we finally ship it. The Database became a full daily tool, not just for retro hunting. Here is everything that changed 👇 Main page: Now organized by narratives: Prediction, Perp, DeFi and more. Each project has current actions, investments, TVL and Twitter in one row. 📰 News feed with latest project updates all with dates and exact steps. Sections: • PerpDex Metrics: volume, OI, fees 30D across all platforms + fee breakdown • Crypto Tools: research, on-chain analytics, every tool in one place • AI Learning Materials: articles, prompts, agent courses, Claude Code breakdowns • Crypto Calendar: all deadlines and claims on one screen, Google and Apple Calendar integration • Airdrop Archive: database of all past drops with real results 👉 Go check: One place for active farming, analytics, deadlines and learning. Works for beginners and experienced players equally. This is not the final version. We keep building and your feedback shapes what comes next. If the database helped you 🔁 and QRT this tweet. Follow Whitelist Media don't miss out on new projects.

Whitelist Media

29,034 views • 3 months ago

$Google open-sourced MCP Toolbox for Databases. I gave it access to everything else. For context, Google's MCP Toolbox for Databases is an open-source server that lets AI agents securely query structured databases like PostgreSQL and MySQL through the MCP protocol However, most enterprise knowledge doesn't actually live in databases. It's scattered across emails, Slack threads, GitHub repos, Salesforce records, customer reviews, and internal docs. So Agents can't see any of it, which means they're working with a fraction of the context they need. I fixed that using MindsDB. It acts as a universal SQL layer that sits on top of all your data sources: structured, semi-structured, and unstructured. This means you can query Salesforce, Gmail, GitHub, S3 files, Jira, and 200+ more sources using SQL syntax. The clever part is how it connects to the MCP Toolbox. MindsDB exposes everything through MySQL, so from the Agent's perspective, it's just running SQL and getting context back. It doesn't know or care that the data came from five different sources behind the scenes. This setup unlocks some powerful capabilities: → One SQL interface for dozens of enterprise sources → Cross-datasource joins (combine GitHub and CRM data in a single query) → Built-in ML capabilities for working with unstructured data → Simple MCP tools that now have massively expanded reach In the video below, the Agent queries GitHub data and a customer review database in one SQL query. So what used to require ETL pipelines and weeks of engineering effort now happens instantly. At the end of the day, AI agents are only as useful as the data they can access. This gives them a lot more to work with. I have shared the GitHub repo in the replies, where you can find more details about this.$

Google open-sourced MCP Toolbox for Databases. I gave it access to everything else. For context, Google's MCP Toolbox for Databases is an open-source server that lets AI agents securely query structured databases like PostgreSQL and MySQL through the MCP protocol However, most enterprise knowledge doesn't actually live in databases. It's scattered across emails, Slack threads, GitHub repos, Salesforce records, customer reviews, and internal docs. So Agents can't see any of it, which means they're working with a fraction of the context they need. I fixed that using MindsDB. It acts as a universal SQL layer that sits on top of all your data sources: structured, semi-structured, and unstructured. This means you can query Salesforce, Gmail, GitHub, S3 files, Jira, and 200+ more sources using SQL syntax. The clever part is how it connects to the MCP Toolbox. MindsDB exposes everything through MySQL, so from the Agent's perspective, it's just running SQL and getting context back. It doesn't know or care that the data came from five different sources behind the scenes. This setup unlocks some powerful capabilities: → One SQL interface for dozens of enterprise sources → Cross-datasource joins (combine GitHub and CRM data in a single query) → Built-in ML capabilities for working with unstructured data → Simple MCP tools that now have massively expanded reach In the video below, the Agent queries GitHub data and a customer review database in one SQL query. So what used to require ETL pipelines and weeks of engineering effort now happens instantly. At the end of the day, AI agents are only as useful as the data they can access. This gives them a lot more to work with. I have shared the GitHub repo in the replies, where you can find more details about this.

Akshay 🚀

39,331 views • 5 months ago

A DEVELOPER FOUND SEVEN WAYS TO TAKE DOWN A PRODUCTION DATABASE THAT ALL LOOK EXACTLY LIKE NORMAL, INNOCENT CODE AND ALMOST EVERY TEAM IS SHIPPING AT LEAST ONE OF THEM RIGHT NOW 17 minutes from Josh Berkus, one of the people who actually maintains PostgreSQL, walking through the quiet mistakes that turn a healthy database into a 3am outage. -> The moment it lands, you realize none of these are exotic attacks. They're ordinary-looking decisions -- a query that locks a table, a connection that never closes, a setting no one ever questioned -- that work perfectly until the day they don't, and then they take everything down with them. The scary part isn't that the database breaks. It's how normal the code looks right up until it does. A query that runs in 5ms on your laptop and 5 minutes on prod. A migration that silently locks the whole table. A connection pool that runs dry the moment real traffic shows up. Every one of them passed review. Writing SQL that runs was never the hard part -> writing SQL that survives production is. And now that an AI agent is generating and firing queries at your real database faster than anyone can read them, every one of those seven landmines is one autocomplete away -- and the only person who can stop it is the one who already knows where they're buried. Your database doesn't go down because someone attacked it. It goes down because something that looked completely normal finally caught up with it. Save and Watch it today. You'll see the next outage coming before it lands ↓

A DEVELOPER FOUND SEVEN WAYS TO TAKE DOWN A PRODUCTION DATABASE THAT ALL LOOK EXACTLY LIKE NORMAL, INNOCENT CODE AND ALMOST EVERY TEAM IS SHIPPING AT LEAST ONE OF THEM RIGHT NOW 17 minutes from Josh Berkus, one of the people who actually maintains PostgreSQL, walking through the quiet mistakes that turn a healthy database into a 3am outage. -> The moment it lands, you realize none of these are exotic attacks. They're ordinary-looking decisions -- a query that locks a table, a connection that never closes, a setting no one ever questioned -- that work perfectly until the day they don't, and then they take everything down with them. The scary part isn't that the database breaks. It's how normal the code looks right up until it does. A query that runs in 5ms on your laptop and 5 minutes on prod. A migration that silently locks the whole table. A connection pool that runs dry the moment real traffic shows up. Every one of them passed review. Writing SQL that runs was never the hard part -> writing SQL that survives production is. And now that an AI agent is generating and firing queries at your real database faster than anyone can read them, every one of those seven landmines is one autocomplete away -- and the only person who can stop it is the one who already knows where they're buried. Your database doesn't go down because someone attacked it. It goes down because something that looked completely normal finally caught up with it. Save and Watch it today. You'll see the next outage coming before it lands ↓

slash1s

22,268 views • 2 months ago

You (with zero coding experience) can now create websites from scratch using AI in less than 20 minutes with this template: In this video and I walk you through the process of: 1. setting up the Template on Claude Projects and how to connect your Replit (Code Base) to your Google Firebase (Database, Storage, Auth). 2. Using the template to turn one of your ideas into a working web app with: -----> Clean Stylized Front End -----> Database -----> Storage, -----> User Sign in + Profile Page -----> File + Post Uploads In less than 20 min. The best part is... Next week we will show you how to create API endpoints, and you'll be able to create full web apps with multiple AI features. Sections of this video ---------- 00:00 Introduction 02:28 Template Set Up 17:47 Building App with the Template

Riley Brown

122,604 views • 2 years ago

Your agents can't keep up with real-time data. Especially when it's scattered across dozens of sources. Most teams waste weeks building custom connectors for every database, API, and data warehouse. Then they build ETL pipelines to sync everything. By the time your agent retrieves the data, it's already outdated. Picture this: Your Postgres database updated 5 minutes ago. Your MongoDB collection changed 2 minutes ago. Your agent is still pulling from yesterday's snapshot. This is why most production RAG systems fail. There's a better approach: MindsDB is an open-source AI platform with a federated data engine that lets you query multiple data sources in real-time using SQL - without moving any data. Here's what makes it different: ↳ Your data stays in place. No ETL pipelines or data duplication ↳ Query Postgres, MongoDB, REST APIs, and more using consistent SQL ↳ JOIN across different sources in real-time with a unified interface ↳ Works with both structured and un-structured data And here's the best part: You don't even need to write SQL. Just describe what you want in plain English, and MindsDB converts it to SQL automatically. The system does all the heavy lifting. The breakthrough for AI agents is simple: When data updates at the source, your agent gets fresh results immediately. No sync delays. No stale embeddings. No custom code for each integration. You can literally write a SQL query that joins a Postgres table with a MongoDB collection and gets live results. This is what production AI applications need but rarely get. In this video, I give you a complete walkthrough of what we just discussed and how to actually do it. Make sure you watch this till the end. I've shared the link to MindsDB's GitHub repo in the next tweet!

Your agents can't keep up with real-time data. Especially when it's scattered across dozens of sources. Most teams waste weeks building custom connectors for every database, API, and data warehouse. Then they build ETL pipelines to sync everything. By the time your agent retrieves the data, it's already outdated. Picture this: Your Postgres database updated 5 minutes ago. Your MongoDB collection changed 2 minutes ago. Your agent is still pulling from yesterday's snapshot. This is why most production RAG systems fail. There's a better approach: MindsDB is an open-source AI platform with a federated data engine that lets you query multiple data sources in real-time using SQL - without moving any data. Here's what makes it different: ↳ Your data stays in place. No ETL pipelines or data duplication ↳ Query Postgres, MongoDB, REST APIs, and more using consistent SQL ↳ JOIN across different sources in real-time with a unified interface ↳ Works with both structured and un-structured data And here's the best part: You don't even need to write SQL. Just describe what you want in plain English, and MindsDB converts it to SQL automatically. The system does all the heavy lifting. The breakthrough for AI agents is simple: When data updates at the source, your agent gets fresh results immediately. No sync delays. No stale embeddings. No custom code for each integration. You can literally write a SQL query that joins a Postgres table with a MongoDB collection and gets live results. This is what production AI applications need but rarely get. In this video, I give you a complete walkthrough of what we just discussed and how to actually do it. Make sure you watch this till the end. I've shared the link to MindsDB's GitHub repo in the next tweet!

Akshay 🚀

65,672 views • 9 months ago

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. 2. The connector ecosystem to load data from unstructured data sources is very immature. 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. The goal of a RAG Pipeline is to solve these problems. The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. At a high level, there are four different stages in the architecture of a RAG pipeline: 1. Ingestion: Here is where the pipeline loads the information from the data source. 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. 3. Transform: Where the pipeline chunks the data and generates document embeddings. 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. There are different rabbit holes at each one of these stages. Here are three of them: 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. If you have a few documents lying around, set up a free account and give it a try.

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. 2. The connector ecosystem to load data from unstructured data sources is very immature. 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. The goal of a RAG Pipeline is to solve these problems. The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. At a high level, there are four different stages in the architecture of a RAG pipeline: 1. Ingestion: Here is where the pipeline loads the information from the data source. 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. 3. Transform: Where the pipeline chunks the data and generates document embeddings. 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. There are different rabbit holes at each one of these stages. Here are three of them: 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. If you have a few documents lying around, set up a free account and give it a try.

Santiago

40,441 views • 1 year ago

Just built a customer support agent because my VA is one scam allegation away from a mental breakdown. This AI slave handles every customer tantrum. Connects to email, pulls Shopify data, and responds in your brand voice minus the trauma. Follow, RT + Comment "support" for the workflow. (Need to do all 3 or my agent won't find your handle to send the DM, give it 20 mins) - Complete setup walkthrough + node-by-node breakdown - Auto-labels emails so you know which Karens to avoid - Pulls customer + order info from Shopify instantly - Responds with your exact brand tone (without the sarcasm) - Accesses brand identity through Pinecone vector memory - Never threatens to quit or asks for a raise Why pay humans to get emotionally destroyed by customers when AI can take the beating instead?

Nozz

38,044 views • 1 year ago

I've been using Claude Code for non-coding tasks, like sorting emails and analyzing my spending This was annoying to setup because Claude doesn’t have the right context - it can’t see my email or my credit card statements So we built a virtual filesystem that turns all of my data sources (gmail, notion, gdrive and more) into local folders on my computer I can just describe what I need (e.g. "invoices from the last week") and a folder appears on my computer with exactly those files This gives Claude context, but it also gives it memory - since it has a local filesystem that syncs in the background, it continuously gets access to my data The more things you expose as files, the more Claude can do for you

I've been using Claude Code for non-coding tasks, like sorting emails and analyzing my spending This was annoying to setup because Claude doesn’t have the right context - it can’t see my email or my credit card statements So we built a virtual filesystem that turns all of my data sources (gmail, notion, gdrive and more) into local folders on my computer I can just describe what I need (e.g. "invoices from the last week") and a folder appears on my computer with exactly those files This gives Claude context, but it also gives it memory - since it has a local filesystem that syncs in the background, it continuously gets access to my data The more things you expose as files, the more Claude can do for you

Eli Mernit

67,006 views • 6 months ago

The guy who vibe-coded his own food discovery app just dropped 4 solid security basics. If you're building your own app with AI, you need this so you don't get hacked on day one: 1. Hide your API keys Keep your OpenAI or Stripe keys off the frontend to prevent them from being stolen. Tell Claude: "Move all API keys to the server and use environment variables." 2. Input Validation Stop people from pasting malicious code into your search bars to break your database. Tell Claude Code: "Sanitize all user inputs." 3. Don't invent your own auth Building login systems from scratch is too risky. Use trusted platforms instead. Tell Claude Code: "Integrate Supabase for authentication." 4. Rate limiting Prevent trolls from crashing your server with 10,000 requests per minute. Tell Claude Code: "Add rate limiting to my API routes." Too many people vibe-coding right now make these exact mistakes and wake up to drained API budgets or wiped databases. Get the security right first. Once your foundation is solid, you can build literally anything. A friend of mine just shared a crazy guide on how to build an entire social network like X in a certain niche with Claude Code in 4 weeks. check it out below 👇

The guy who vibe-coded his own food discovery app just dropped 4 solid security basics. If you're building your own app with AI, you need this so you don't get hacked on day one: 1. Hide your API keys Keep your OpenAI or Stripe keys off the frontend to prevent them from being stolen. Tell Claude: "Move all API keys to the server and use environment variables." 2. Input Validation Stop people from pasting malicious code into your search bars to break your database. Tell Claude Code: "Sanitize all user inputs." 3. Don't invent your own auth Building login systems from scratch is too risky. Use trusted platforms instead. Tell Claude Code: "Integrate Supabase for authentication." 4. Rate limiting Prevent trolls from crashing your server with 10,000 requests per minute. Tell Claude Code: "Add rate limiting to my API routes." Too many people vibe-coding right now make these exact mistakes and wake up to drained API budgets or wiped databases. Get the security right first. Once your foundation is solid, you can build literally anything. A friend of mine just shared a crazy guide on how to build an entire social network like X in a certain niche with Claude Code in 4 weeks. check it out below 👇

Spivach

11,103 views • 2 months ago

Big moment for Postgres! AI coding tools have been surprisingly bad at writing Postgres code. Not because the models are dumb, but because of how they learned SQL in the first place. LLMs are trained on the internet, which is full of outdated Stack Overflow answers and quick-fix tutorials. So when you ask an AI to generate a schema, it gives you something that technically runs but misses decades of Postgres evolution, like: - No GENERATED ALWAYS AS IDENTITY (added in PG10) - No expression or partial indexes - No NULLS NOT DISTINCT (PG15) - Missing CHECK constraints and proper foreign keys - Generic naming that tells you nothing But this is actually a solvable problem. You can teach AI tools to write better Postgres by giving them access to the right documentation at inference time. This exact solution is actually implemented in the newly released pg-aiguide by Tiger Data - Creators of TimescaleDB, which is an open-source MCP server that provides coding tools access to 35 years of Postgres expertise. In a gist, the MCP server enables: - Semantic search over the official PostgreSQL manual (version-aware, so it knows PG14 vs PG17 differences) - Curated skills with opinionated best practices for schema design, indexing, and constraints. I ran an experiment with Claude Code to see how well this works, and worked with the team to put this together. Prompt: "Generate a schema for an e-commerce site twice, one with the MCP server disabled, one with it enabled. Finally, run an assessment to compare the generated schemas." The run with the MCP server led to: - 420% more indexes (including partial and expression indexes) - 235% more constraints - 60% more tables (proper normalization) - 11 automation functions and triggers - Modern PG17 patterns throughout The MCP-assisted schema had proper data integrity, performance optimizations baked in, and followed naming conventions that actually make sense in production. pg-aiguide works with Claude Code, Cursor, VS Code, and any MCP-compatible tool. It's free and fully open source. I have shared the repo in the replies!

Big moment for Postgres! AI coding tools have been surprisingly bad at writing Postgres code. Not because the models are dumb, but because of how they learned SQL in the first place. LLMs are trained on the internet, which is full of outdated Stack Overflow answers and quick-fix tutorials. So when you ask an AI to generate a schema, it gives you something that technically runs but misses decades of Postgres evolution, like: - No GENERATED ALWAYS AS IDENTITY (added in PG10) - No expression or partial indexes - No NULLS NOT DISTINCT (PG15) - Missing CHECK constraints and proper foreign keys - Generic naming that tells you nothing But this is actually a solvable problem. You can teach AI tools to write better Postgres by giving them access to the right documentation at inference time. This exact solution is actually implemented in the newly released pg-aiguide by Tiger Data - Creators of TimescaleDB, which is an open-source MCP server that provides coding tools access to 35 years of Postgres expertise. In a gist, the MCP server enables: - Semantic search over the official PostgreSQL manual (version-aware, so it knows PG14 vs PG17 differences) - Curated skills with opinionated best practices for schema design, indexing, and constraints. I ran an experiment with Claude Code to see how well this works, and worked with the team to put this together. Prompt: "Generate a schema for an e-commerce site twice, one with the MCP server disabled, one with it enabled. Finally, run an assessment to compare the generated schemas." The run with the MCP server led to: - 420% more indexes (including partial and expression indexes) - 235% more constraints - 60% more tables (proper normalization) - 11 automation functions and triggers - Modern PG17 patterns throughout The MCP-assisted schema had proper data integrity, performance optimizations baked in, and followed naming conventions that actually make sense in production. pg-aiguide works with Claude Code, Cursor, VS Code, and any MCP-compatible tool. It's free and fully open source. I have shared the repo in the replies!

Avi Chawla

187,048 views • 7 months ago

Quick demo of Zero’s new background queries. Zero’s sync is query-based. Rather than specifying what data you want using rules or some other separate system, you just use queries. Right inside the client app, you do a query using a full sql-style language. You get filters, subqueries , limits, etc. Zero syncs the data backing these queries to the client. It’s important to realize Zero isn’t really a cache. It’s a replica. It’s eagerly replicating a precise snapshot of a slice of your database - the slice covered by the queries you have open. So there is never stale data in Zero. When you close a query we delete the rows uniquely returned by that query because we can no longer keep them up to date. Of course that kind of sucks for the common case of doing a query, navigating, then pressing “back”. Ideally we want that back nav to be fast. To address this Zero 0.17 adds background queries. You can add a ttl to a query and it will keep running and syncing in the background. This is much different than normal caching because this data stays up to date. If you make the same query again, the results will be *instantly* available *and already up to date with server*. If you make a different query the data from the background query is used client-side to answer the new query instantly if possible. This all happens completely automatically. Just by adding the ttl flag.

Quick demo of Zero’s new background queries. Zero’s sync is query-based. Rather than specifying what data you want using rules or some other separate system, you just use queries. Right inside the client app, you do a query using a full sql-style language. You get filters, subqueries , limits, etc. Zero syncs the data backing these queries to the client. It’s important to realize Zero isn’t really a cache. It’s a replica. It’s eagerly replicating a precise snapshot of a slice of your database - the slice covered by the queries you have open. So there is never stale data in Zero. When you close a query we delete the rows uniquely returned by that query because we can no longer keep them up to date. Of course that kind of sucks for the common case of doing a query, navigating, then pressing “back”. Ideally we want that back nav to be fast. To address this Zero 0.17 adds background queries. You can add a ttl to a query and it will keep running and syncing in the background. This is much different than normal caching because this data stays up to date. If you make the same query again, the results will be instantly available and already up to date with server. If you make a different query the data from the background query is used client-side to answer the new query instantly if possible. This all happens completely automatically. Just by adding the ttl flag.

Aaron Boodman

18,808 views • 1 year ago

Web scraping is a critical skill, and yet nobody talks about it. How do you think companies are training their Large Language Models? Where do you think the data comes from? But web scraping goes beyond all of that. Imagine giving an AI agent access to any public online data in real time! I like to call this "web-scrapping on demand", and I'm pretty sure it's going to unlock unlimited power for AI applications. I recorded a quick video to show you how you can do this using Apify. I've talked about them before, and they are collaborating with me on this post. They have one of the best open-source web scraping and browser automation libraries out there: But it gets much better than this! You can use MCP to connect your AI Agents and applications to the Apify platform and use any specialized actor on demand to scrape and process online data. In the video, I used Cursor to scrape LinkedIn posts with the words "Machine Learning" in real time. Worked like a charm with no code needed! Here is a link to the platform: Think about this: You can now feed your AI applications with any public data on demand! We aren't ready for what's coming.

Web scraping is a critical skill, and yet nobody talks about it. How do you think companies are training their Large Language Models? Where do you think the data comes from? But web scraping goes beyond all of that. Imagine giving an AI agent access to any public online data in real time! I like to call this "web-scrapping on demand", and I'm pretty sure it's going to unlock unlimited power for AI applications. I recorded a quick video to show you how you can do this using Apify. I've talked about them before, and they are collaborating with me on this post. They have one of the best open-source web scraping and browser automation libraries out there: But it gets much better than this! You can use MCP to connect your AI Agents and applications to the Apify platform and use any specialized actor on demand to scrape and process online data. In the video, I used Cursor to scrape LinkedIn posts with the words "Machine Learning" in real time. Worked like a charm with no code needed! Here is a link to the platform: Think about this: You can now feed your AI applications with any public data on demand! We aren't ready for what's coming.

Santiago

101,473 views • 1 year ago

I built an app in Softr for the HVAC industry to solve some crucial problems. The problem is that those in the HVAC industry and similar industries like construction, plumbing, and electrical do not have one source of truth where: 1. Their clients can request for thier services. 2. Clients can be onboarded after they make a payment. 3. They store the information and bio data of their technicians. 4. They assign tasks to their technicians. 5. Technicians can track onsite jobs with pictures in real time of when working. 6. Clients see the progress of their projects. 7. Invoices and quotations from paid clients can be tracked. 8. Technicians borrow assets from the company, and they can be tracked. 9. There is a database where every individual, from technicians to admin and clients, are all stored. 10. Login details from every individual are secured and they can only see things that are their business without seeing that of another person, be ita technician or a client. These and many more are what people in these industries face as a challenge. I came up with a solution that addresses all these problems. I built a workflow that also auto-populated the users table in the database with technicians and clients when the records are filled in the technician and client tables, respectively. There is also a workflow that sends an email to the admin when a client makes a request from the portal. Taking advantage of the database, workflow, and portal gave a full-blown application for the HVAC industry. If you are in the construction, plumbing, electrical, or HVAC industry and you need a similar build, reach out, and I will be more than happy to replicate this for you or something similar in Softr.

I built an app in Softr for the HVAC industry to solve some crucial problems. The problem is that those in the HVAC industry and similar industries like construction, plumbing, and electrical do not have one source of truth where: 1. Their clients can request for thier services. 2. Clients can be onboarded after they make a payment. 3. They store the information and bio data of their technicians. 4. They assign tasks to their technicians. 5. Technicians can track onsite jobs with pictures in real time of when working. 6. Clients see the progress of their projects. 7. Invoices and quotations from paid clients can be tracked. 8. Technicians borrow assets from the company, and they can be tracked. 9. There is a database where every individual, from technicians to admin and clients, are all stored. 10. Login details from every individual are secured and they can only see things that are their business without seeing that of another person, be ita technician or a client. These and many more are what people in these industries face as a challenge. I came up with a solution that addresses all these problems. I built a workflow that also auto-populated the users table in the database with technicians and clients when the records are filled in the technician and client tables, respectively. There is also a workflow that sends an email to the admin when a client makes a request from the portal. Taking advantage of the database, workflow, and portal gave a full-blown application for the HVAC industry. If you are in the construction, plumbing, electrical, or HVAC industry and you need a similar build, reach out, and I will be more than happy to replicate this for you or something similar in Softr.

Ada || Airtable, Zapier & Make.com

26,724 views • 8 months ago

how to use firecrawl to give your AI eyes and actually build startups that outperform 99% of apps: 1. your AI is smart but blind. it can't go to a website, read a page, or grab data on its own. firecrawl fixes that. you put in a URL. you get back clean markdown, structured JSON, screenshots. feed it to any model. 2. three lines of code. that's it. no proxies. no anti-bot detection. no custom scrapers that break when a site changes. one API call. clean data back in seconds. works on 98%+ of sites. 3. firecrawl has six core capabilities: scrape a single page. crawl an entire site. map all URLs on a domain. search google and return full content. an agent endpoint where you describe what you want and it goes and finds it. and a browser sandbox where AI controls a real browser like filling forms, clicking buttons, handles logins. 4. the agent endpoint is wild. you can say "find all of YC's winter 24 dev tool companies and their founders and emails" and get back structured data. or "compare pricing tiers across stripe, square, and paypal" and get a side-by-side table. 5. the browser sandbox lets your AI stay logged in across sessions, navigate pagination, watch live as it browses. this is computer use without building the infrastructure yourself. 6. think of it in layers. every builder needs: an agent harness (claude code, cursor, codex), a search layer (perplexity, exa), a web data layer (firecrawl), an ops brain (obsidian, notion), and an outbound stack. the web data layer is the one most people are sleeping on. 7. this is the AWS moment for web data. in 2006 building a web app meant buying servers and managing racks. AWS said one API call, use our servers. some of the biggest companies of the last decade were built on that. firecrawl is doing the same thing for web data in 2026. 8. the framework i'd use for coming up with startup ideas building with clean data: take a massive horizontal platform. rebuild it for one niche using firecrawl. the vertical version always wins because people want specific, not generic. price for outcome. 9. a year ago firecrawl posted a job listing that said "please only apply if you're an AI agent." content creator agents. customer support agents. junior dev agents. it looked weird. it was a signal for where this is all going. the people who understand how to get clean web data, wrap it around an LLM, and package it as a product are the the ones with a 12-month head start. i use Firecrawl with Idea Browser . once you see what's possible with structured web data, you can't unsee it. episode is live on The Startup Ideas Podcast (SIP) 🧃 (full breakdown there) i tried to explain this as clear as possible for even the non technical. send it to a builder friend. watch

how to use firecrawl to give your AI eyes and actually build startups that outperform 99% of apps: 1. your AI is smart but blind. it can't go to a website, read a page, or grab data on its own. firecrawl fixes that. you put in a URL. you get back clean markdown, structured JSON, screenshots. feed it to any model. 2. three lines of code. that's it. no proxies. no anti-bot detection. no custom scrapers that break when a site changes. one API call. clean data back in seconds. works on 98%+ of sites. 3. firecrawl has six core capabilities: scrape a single page. crawl an entire site. map all URLs on a domain. search google and return full content. an agent endpoint where you describe what you want and it goes and finds it. and a browser sandbox where AI controls a real browser like filling forms, clicking buttons, handles logins. 4. the agent endpoint is wild. you can say "find all of YC's winter 24 dev tool companies and their founders and emails" and get back structured data. or "compare pricing tiers across stripe, square, and paypal" and get a side-by-side table. 5. the browser sandbox lets your AI stay logged in across sessions, navigate pagination, watch live as it browses. this is computer use without building the infrastructure yourself. 6. think of it in layers. every builder needs: an agent harness (claude code, cursor, codex), a search layer (perplexity, exa), a web data layer (firecrawl), an ops brain (obsidian, notion), and an outbound stack. the web data layer is the one most people are sleeping on. 7. this is the AWS moment for web data. in 2006 building a web app meant buying servers and managing racks. AWS said one API call, use our servers. some of the biggest companies of the last decade were built on that. firecrawl is doing the same thing for web data in 2026. 8. the framework i'd use for coming up with startup ideas building with clean data: take a massive horizontal platform. rebuild it for one niche using firecrawl. the vertical version always wins because people want specific, not generic. price for outcome. 9. a year ago firecrawl posted a job listing that said "please only apply if you're an AI agent." content creator agents. customer support agents. junior dev agents. it looked weird. it was a signal for where this is all going. the people who understand how to get clean web data, wrap it around an LLM, and package it as a product are the the ones with a 12-month head start. i use Firecrawl with Idea Browser . once you see what's possible with structured web data, you can't unsee it. episode is live on The Startup Ideas Podcast (SIP) 🧃 (full breakdown there) i tried to explain this as clear as possible for even the non technical. send it to a builder friend. watch

GREG ISENBERG

135,017 views • 4 months ago

6 months ago, building an app required: - 6 months of development - $300K budget - Team of 5 developers - Constant manual debugging Today, I'm helping a 17-year-old build one in a week. Workflow: ChatGPT -> Lovable -> Supabase -> Cursor Step-by-step how: 1/ Write your PRD first. This is non-negotiable. Clear requirements on paper = 10x faster execution with AI. We spent 30 minutes documenting exactly what PostPal needed to do. Then gave it to ChatGPT: "Create a Lovable prompt from this PRD." Copy. Paste. Done. 2/ Your first prompt sets everything. That initial Lovable prompt? It's your foundation. Give it the full high-level vision. Every feature. Every flow. Lovable uses this context for everything that follows. Get this wrong and you'll rebuild from scratch. 3/ Database first, frontend second. Biggest mistake I see: Building the entire UI, then trying to connect data. Set up Supabase immediately. Create your tables. Configure role-level security. Build backend and frontend together, not separately. 4/ Go feature by feature. Don't attack all screens at once. Pick one core feature. Build it completely. Connect it to your database. Test it. Then move to the next. Each feature should be fully functional before moving on. 5/ Chat mode is your debugging superpower. When something breaks (it will): → Use chat mode to diagnose → Let it explain the issue → Switch to agent mode to fix Chat mode for understanding. Agent mode for implementing. This combo saved us hours. 6/ Security isn't optional. Before deploying: → Enable row-level security → Secure your edge functions → Check your API endpoints → Run Lovable's security check Takes 5 minutes. Saves you from disasters. The result? A fully functional app. Not a prototype. Not a demo. A real product with authentication, database, and payments. The game has completely changed. While others debate if AI will replace developers... We're shipping products before lunch. The tools are here. The playbook is proven. The only question is: what will you build? Time to ship.

6 months ago, building an app required: - 6 months of development - $300K budget - Team of 5 developers - Constant manual debugging Today, I'm helping a 17-year-old build one in a week. Workflow: ChatGPT -> Lovable -> Supabase -> Cursor Step-by-step how: 1/ Write your PRD first. This is non-negotiable. Clear requirements on paper = 10x faster execution with AI. We spent 30 minutes documenting exactly what PostPal needed to do. Then gave it to ChatGPT: "Create a Lovable prompt from this PRD." Copy. Paste. Done. 2/ Your first prompt sets everything. That initial Lovable prompt? It's your foundation. Give it the full high-level vision. Every feature. Every flow. Lovable uses this context for everything that follows. Get this wrong and you'll rebuild from scratch. 3/ Database first, frontend second. Biggest mistake I see: Building the entire UI, then trying to connect data. Set up Supabase immediately. Create your tables. Configure role-level security. Build backend and frontend together, not separately. 4/ Go feature by feature. Don't attack all screens at once. Pick one core feature. Build it completely. Connect it to your database. Test it. Then move to the next. Each feature should be fully functional before moving on. 5/ Chat mode is your debugging superpower. When something breaks (it will): → Use chat mode to diagnose → Let it explain the issue → Switch to agent mode to fix Chat mode for understanding. Agent mode for implementing. This combo saved us hours. 6/ Security isn't optional. Before deploying: → Enable row-level security → Secure your edge functions → Check your API endpoints → Run Lovable's security check Takes 5 minutes. Saves you from disasters. The result? A fully functional app. Not a prototype. Not a demo. A real product with authentication, database, and payments. The game has completely changed. While others debate if AI will replace developers... We're shipping products before lunch. The tools are here. The playbook is proven. The only question is: what will you build? Time to ship.

Jacob Klug

40,338 views • 1 year ago

EVERYTHING you NEED to know about Jack Dorsey's AI agent "Slack killer" Buzz (set up, use-cases etc in 38 mins) What we get into: 1. What Buzz actually is and should founders switch from Slack? 2. How to swap the model under any agent and keep all your context? 3. How to talk to your agents live with audio huddles? 4. How to get agents to build and deploy real apps for you, like a full CRM from one ask? 5. How to set up the context loop that feeds your live app data back to your agents? 6. How to share compute so a few people split one machine running a local model? 7. Who it's actually for right now, and what's still rough? Full breakdown on the pod The Startup Ideas Podcast (SIP) 🧃. Thanks to Vinny for jumping on and clearly explaining jack and team's latest product. My TLDR take is Buzz is a glimpse into the future of work. Some of you will roll your eyes at that, and I get it, it's alpha software and it's slow in places. But the core idea, that your context is the foundation and agents build out from there, is right, and that's worth seeing early. Watch Curious what you think

EVERYTHING you NEED to know about Jack Dorsey's AI agent "Slack killer" Buzz (set up, use-cases etc in 38 mins) What we get into: 1. What Buzz actually is and should founders switch from Slack? 2. How to swap the model under any agent and keep all your context? 3. How to talk to your agents live with audio huddles? 4. How to get agents to build and deploy real apps for you, like a full CRM from one ask? 5. How to set up the context loop that feeds your live app data back to your agents? 6. How to share compute so a few people split one machine running a local model? 7. Who it's actually for right now, and what's still rough? Full breakdown on the pod The Startup Ideas Podcast (SIP) 🧃. Thanks to Vinny for jumping on and clearly explaining jack and team's latest product. My TLDR take is Buzz is a glimpse into the future of work. Some of you will roll your eyes at that, and I get it, it's alpha software and it's slow in places. But the core idea, that your context is the foundation and agents build out from there, is right, and that's worth seeing early. Watch Curious what you think

GREG ISENBERG

548,574 views • 14 days ago