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.

What changes when you're building software for agents not for humans? “The experience is going to be defined by the slowest point in that chain. The number one requirement for agentic query patterns is low latency, because they are executing dozens of SQL queries simultaneously across all these different... show more

Harry Stebbings

667,294 subscribers

21,168 views • 2 months ago •via X (Twitter)

Science & Technology Finance

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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

Box CEO Aaron Levie says that the more AI agents companies deploy, the more important the software powering them becomes. "Everybody always made this claim that once you have all these agents, then actually all they really need is a database underneath." "But the problem is that database has to be coordinated against possibly thousands of end users and then possibly tens of thousands of agents." "So the access controls, the business logic, being able to actually render the experience, the security, all these core systems are actually going to become more important in a world of all of these agentic workloads."

Box CEO Aaron Levie says that the more AI agents companies deploy, the more important the software powering them becomes. "Everybody always made this claim that once you have all these agents, then actually all they really need is a database underneath." "But the problem is that database has to be coordinated against possibly thousands of end users and then possibly tens of thousands of agents." "So the access controls, the business logic, being able to actually render the experience, the security, all these core systems are actually going to become more important in a world of all of these agentic workloads."

TBPN

39,787 views • 1 month ago

60-Second SEO: All SEOs should be using the Google Ads "Search Keywords" report to immediately discover the most valuable queries for a business: Google Ads is the only place that you can get actual conversion data at the query level. The sad part is, this is a heavily underutilized report by many in the SEO community. By utilizing PPC data, you're able to see actual data around which queries are the most valuable for your business. To use it requires SEOs to be brave and venture into the Google Ads platform:

60-Second SEO: All SEOs should be using the Google Ads "Search Keywords" report to immediately discover the most valuable queries for a business: Google Ads is the only place that you can get actual conversion data at the query level. The sad part is, this is a heavily underutilized report by many in the SEO community. By utilizing PPC data, you're able to see actual data around which queries are the most valuable for your business. To use it requires SEOs to be brave and venture into the Google Ads platform:

Chris Long

20,901 views • 2 years ago

when we were at facebook, we believed that at some point in the future, most of the transactions on the internet would not be done by humans they would be done by machines that conviction shaped every architectural decision behind sui we built sui for the world we knew was coming a world where machines will be the primary economic actors on the internet and that world is no longer a forecast. it is unfolding right in front of us the internet has reached a tipping point where automated activity, supercharged by AI, now outpaces human interaction non-human traffic now accounts for more than 50% of all global web activity and you can see humans using agentic workflows more and more in their daily lives in the next years, that trend is going to grow exponentially and the volume of financial transactions executed by agents is also going to grow exponentially with it each agentic workload will be running multiple thousand economic transactions a second and this is going to be orders of magnitude higher than what human wallets do today the L1s optimized for human usage patterns, human attention, human accounts, and human patience cannot adapt to where this is going i have always said this if it is not in the foundation, you cannot patch your way to it later and rn, no other L1 has the foundation sui has this is why agentic apps like Beep, Audric, WaterX are choosing sui and this is just a start. more agentic apps will keep landing on sui because agents are optimizers. they will always route through the fastest, cheapest path on the internet and that path is sui we believed it at facebook. we believe it more today than we ever did the agentic economy is inevitable. and it will run on Sui

when we were at facebook, we believed that at some point in the future, most of the transactions on the internet would not be done by humans they would be done by machines that conviction shaped every architectural decision behind sui we built sui for the world we knew was coming a world where machines will be the primary economic actors on the internet and that world is no longer a forecast. it is unfolding right in front of us the internet has reached a tipping point where automated activity, supercharged by AI, now outpaces human interaction non-human traffic now accounts for more than 50% of all global web activity and you can see humans using agentic workflows more and more in their daily lives in the next years, that trend is going to grow exponentially and the volume of financial transactions executed by agents is also going to grow exponentially with it each agentic workload will be running multiple thousand economic transactions a second and this is going to be orders of magnitude higher than what human wallets do today the L1s optimized for human usage patterns, human attention, human accounts, and human patience cannot adapt to where this is going i have always said this if it is not in the foundation, you cannot patch your way to it later and rn, no other L1 has the foundation sui has this is why agentic apps like Beep, Audric, WaterX are choosing sui and this is just a start. more agentic apps will keep landing on sui because agents are optimizers. they will always route through the fastest, cheapest path on the internet and that path is sui we believed it at facebook. we believe it more today than we ever did the agentic economy is inevitable. and it will run on Sui

Adeniyi.sui

24,920 views • 5 months ago

Let Postgres own the Iceberg catalog and delegate analytics to DuckDB. The result => transactional lakehouse updates with fast analytical queries. This isn’t a concept. It’s exactly what pg_lake delivers today. pg_lake combines a set of extensions and components that let you query and modify Iceberg tables (and other lakehouse formats) directly from Postgres. DuckDB is used to accelerate analytical queries and runs in a sidecar process called pgduck_server, which communicates with Postgres during query execution. How it works (diagram below): 1. An application sends a query to Postgres to calculate unrealized PnL (Profit and Loss) for the Disney ticker. 2. Postgres parses the query and identifies the part that computes the average price from historical lakehouse data. 3. That part is forwarded to pgduck_server for accelerated execution. 4. pgduck_server delegates execution to DuckDB, which queries the lakehouse (reusing cached data if available). 5. DuckDB computes the average price and returns it to Postgres. 6. Postgres joins the result with local portfolio data and computes the unrealized PnL. 7. The final result is returned to the application.

Let Postgres own the Iceberg catalog and delegate analytics to DuckDB. The result => transactional lakehouse updates with fast analytical queries. This isn’t a concept. It’s exactly what pg_lake delivers today. pg_lake combines a set of extensions and components that let you query and modify Iceberg tables (and other lakehouse formats) directly from Postgres. DuckDB is used to accelerate analytical queries and runs in a sidecar process called pgduck_server, which communicates with Postgres during query execution. How it works (diagram below): 1. An application sends a query to Postgres to calculate unrealized PnL (Profit and Loss) for the Disney ticker. 2. Postgres parses the query and identifies the part that computes the average price from historical lakehouse data. 3. That part is forwarded to pgduck_server for accelerated execution. 4. pgduck_server delegates execution to DuckDB, which queries the lakehouse (reusing cached data if available). 5. DuckDB computes the average price and returns it to Postgres. 6. Postgres joins the result with local portfolio data and computes the unrealized PnL. 7. The final result is returned to the application.

Denis Magda

28,597 views • 9 months ago

Jensen Huang just said this is the greatest era in history to build software. AI agents will not kill software. They will do the exact opposite: create a massive new wave of software demand. at NVIDIA GTC Taipei 2026 "Click and type. We now replace that with explaining to the AI what we want, our intent, and the AI generates the code or uses tools to produce the necessary output. This is how computers are going to work in the future. This is Agentic AI. For two years, we've been building toward this, and now it has arrived. One of the big breakthroughs, of course, is tool use. A lot of people have said, “Jensen, AI is coming. Agentic AI is coming. Therefore, all the software companies are going to go out of business.” This is exactly the opposite. Because there are going to be so many agents, the world is no longer limited by the number of people. Therefore, those agents are going to use more tools than ever. This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it. This is a big breakthrough. And in fact, what we have done, as you know, what Nvidia’s treasure..." ---- From 'NVIDIA' YT channel (link in comment)

Jensen Huang just said this is the greatest era in history to build software. AI agents will not kill software. They will do the exact opposite: create a massive new wave of software demand. at NVIDIA GTC Taipei 2026 "Click and type. We now replace that with explaining to the AI what we want, our intent, and the AI generates the code or uses tools to produce the necessary output. This is how computers are going to work in the future. This is Agentic AI. For two years, we've been building toward this, and now it has arrived. One of the big breakthroughs, of course, is tool use. A lot of people have said, “Jensen, AI is coming. Agentic AI is coming. Therefore, all the software companies are going to go out of business.” This is exactly the opposite. Because there are going to be so many agents, the world is no longer limited by the number of people. Therefore, those agents are going to use more tools than ever. This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it. This is a big breakthrough. And in fact, what we have done, as you know, what Nvidia’s treasure..." ---- From 'NVIDIA' YT channel (link in comment)

Rohan Paul

16,584 views • 5 months ago

Search built for humans breaks when agents make dozens of queries simultaneously. Rebuilding the engine, not the interface is the real innovation. 62ms latency. $1 per 1,000 calls. Public benchmarks.

Search built for humans breaks when agents make dozens of queries simultaneously. Rebuilding the engine, not the interface is the real innovation. 62ms latency. $1 per 1,000 calls. Public benchmarks.

Out of Context Human Race

48,768 views • 3 months 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 • 11 months ago

susquehanna traded 2.7 billion options contracts in 2023. more than the entire US options industry traded in all of 2007. 3,200 people. 17 offices. estimated $7.2 billion in revenue. trading their own capital. they just put out a video of their mathematicians explaining how they actually think about markets. what they said: "finding patterns is easy. understanding that those patterns reflect something fundamental about data is challenging." on machine learning: "these black boxes find patterns, they make predictions. but these predictions are based in the data that they see, and not in the assumptions that may be true about the world." on AI: "AI itself is a superpower. the challenge is to develop new methodology to insert theory and assumption into the system." but the part that got me was the first twenty seconds. "markets are constantly generating information. people react to that information, they react to each other, and they adjust their behavior." "as a result, the signal is going to be weak. the noise is going to be enormous, and whatever patterns you're going to find might not persist for very long." one of the largest options market makers on earth saying, in their own video, that signal is often weak, the noise is enormous, and the patterns decay. make you understand why constant adapting and research is needed. trading is never a one and done.

susquehanna traded 2.7 billion options contracts in 2023. more than the entire US options industry traded in all of 2007. 3,200 people. 17 offices. estimated $7.2 billion in revenue. trading their own capital. they just put out a video of their mathematicians explaining how they actually think about markets. what they said: "finding patterns is easy. understanding that those patterns reflect something fundamental about data is challenging." on machine learning: "these black boxes find patterns, they make predictions. but these predictions are based in the data that they see, and not in the assumptions that may be true about the world." on AI: "AI itself is a superpower. the challenge is to develop new methodology to insert theory and assumption into the system." but the part that got me was the first twenty seconds. "markets are constantly generating information. people react to that information, they react to each other, and they adjust their behavior." "as a result, the signal is going to be weak. the noise is going to be enormous, and whatever patterns you're going to find might not persist for very long." one of the largest options market makers on earth saying, in their own video, that signal is often weak, the noise is enormous, and the patterns decay. make you understand why constant adapting and research is needed. trading is never a one and done.

Goshawk Trades

14,483 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 🚀

40,562 views • 8 months ago

Parker Conrad on AI’s Role in B2B Software "The fact that these systems can read and the context windows are so large is much more powerful for B2B software than the fact that they can write. 'Generative AI' is a misnomer. It's the ability to ingest all of this information." Parker Conrad in conversation with Y Combinator's Garry Tan

Parker Conrad on AI’s Role in B2B Software "The fact that these systems can read and the context windows are so large is much more powerful for B2B software than the fact that they can write. 'Generative AI' is a misnomer. It's the ability to ingest all of this information." Parker Conrad in conversation with Y Combinator's Garry Tan

Overlap: Business & Tech

29,732 views • 1 year ago

Search was built for humans — one query, one results page. AI agents don’t search that way. They assault problems from dozens of angles simultaneously. Most search APIs are still just the old human workflow wrapped in code. Octen rebuilt the entire stack from the ground up for machines — indexing, ranking, and serving. 62 ms per search. ~$1 per 1,000 requests. The interface changed years ago. The search engine has finally caught up.

Search was built for humans — one query, one results page. AI agents don’t search that way. They assault problems from dozens of angles simultaneously. Most search APIs are still just the old human workflow wrapped in code. Octen rebuilt the entire stack from the ground up for machines — indexing, ranking, and serving. 62 ms per search. ~$1 per 1,000 requests. The interface changed years ago. The search engine has finally caught up.

INTERIOR PORN

61,484 views • 3 months ago

"We're going to have billions of agents that will do transactions at a frequency and velocity that is inconsistent with how humans interact with software and financial systems today.” NEAR Intents is more than cross-chain infrastructure. It’s the money rail for agentic finance.

"We're going to have billions of agents that will do transactions at a frequency and velocity that is inconsistent with how humans interact with software and financial systems today.” NEAR Intents is more than cross-chain infrastructure. It’s the money rail for agentic finance.

NEAR Protocol

67,975 views • 4 months ago

Most of the market is priced for a world that's coming to an end. Traditional software, legacy platforms, much of the SaaS layer of the S&P 500… all built on the assumption that humans will remain the primary customers. AI agents don't buy software the way we do. They don't need dashboards, subscriptions, or logins. And once the buyer changes, so does everything built around them. The investable opportunity ahead is the agentic economy… what gets built for agents as customers. That's where the next wave of capital ends up, and most people aren't positioned for it.

Most of the market is priced for a world that's coming to an end. Traditional software, legacy platforms, much of the SaaS layer of the S&P 500… all built on the assumption that humans will remain the primary customers. AI agents don't buy software the way we do. They don't need dashboards, subscriptions, or logins. And once the buyer changes, so does everything built around them. The investable opportunity ahead is the agentic economy… what gets built for agents as customers. That's where the next wave of capital ends up, and most people aren't positioned for it.

Raoul Pal

215,413 views • 3 months ago

The reason why all those guys were staring at her was because when you were in the presence of another being, that is not a human, they emit a different frequency that is hard to ignore. Ivanka Trump and the rest of her family are not humans. They are pleadians from another star system!

Sensitive content

The reason why all those guys were staring at her was because when you were in the presence of another being, that is not a human, they emit a different frequency that is hard to ignore. Ivanka Trump and the rest of her family are not humans. They are pleadians from another star system!

Charley Griffin

79,417 views • 1 month ago

Old software engineering patterns are coming back because of coding agents. Dax Raad(dax), co-founder of AI coding agent OpenCode, on why DDD is becoming more relevant and less painful: “I think it's the same problem as always, which is how do you make code bases that are easy to work in, scalable, that can flex to new requirements. A lot of the old patterns for me are coming back. We've always been a big domain-driven design company. We did it in a very light way. We're now doing it in a much heavier way because we find that these, kind of boring, enterprisey patterns end up being pretty useful because you have a bunch of idiots on your team now. Coding agents are a bunch of idiots. They are going to work 24/7 and they're going to ship a lot of stuff so you need way more guardrails than you used to. What's nice is some of these old patterns we hated because they were very verbose, they produced reliable code that was modular and safe but they were very verbose and annoying to type out… you're not typing it out anymore. Now you can get the benefits of these patterns without the downsides."

Old software engineering patterns are coming back because of coding agents. Dax Raad(dax), co-founder of AI coding agent OpenCode, on why DDD is becoming more relevant and less painful: “I think it's the same problem as always, which is how do you make code bases that are easy to work in, scalable, that can flex to new requirements. A lot of the old patterns for me are coming back. We've always been a big domain-driven design company. We did it in a very light way. We're now doing it in a much heavier way because we find that these, kind of boring, enterprisey patterns end up being pretty useful because you have a bunch of idiots on your team now. Coding agents are a bunch of idiots. They are going to work 24/7 and they're going to ship a lot of stuff so you need way more guardrails than you used to. What's nice is some of these old patterns we hated because they were very verbose, they produced reliable code that was modular and safe but they were very verbose and annoying to type out… you're not typing it out anymore. Now you can get the benefits of these patterns without the downsides."

The Pragmatic Engineer

175,189 views • 5 months ago

Happy to properly launch Anna, the proactive AI agent for parents! Uncovering a bit of the technology behind the scenes! Building Anna is where I learned: 💾 Memory as plain text sucks. You need structured memory. Like a full-blown PostgreSQL DB that stores your tasks and calendar in a structured manner. Most harnesses are good at coding-related stuff. Let it do the query. Don't let it vibe-search the memory. Let it vibe your SQL query 💭 Dreaming is a useful concept for enhancing memory to feed the LLM context. But DO NOT vibe your dream. Asking your agent to "hey, just dream and keep the relevant memory around" is a recipe for deleting a bunch of important information and keeping trash around. Your dream needs to have some Taxonomy (or better, Ontology). What information is important? For who? With what object? What can they do? And again, these are impossible to describe and act well without a proper schema 🔄 Loop Engineering is important for smoothing out rough edges in the system we build. But even expensive loop engineering with a state-of-the-art model can't out-engineer bad system design. The highest leverage an AI Engineer can do is actually building the right system design, and having an eye on both product delight and engineering scalability There are several more insights that I plan to cover in a dedicated video about Agentic AI Engineering. But it's actually a huge relief that the future of software engineering... is still software engineering

Happy to properly launch Anna, the proactive AI agent for parents! Uncovering a bit of the technology behind the scenes! Building Anna is where I learned: 💾 Memory as plain text sucks. You need structured memory. Like a full-blown PostgreSQL DB that stores your tasks and calendar in a structured manner. Most harnesses are good at coding-related stuff. Let it do the query. Don't let it vibe-search the memory. Let it vibe your SQL query 💭 Dreaming is a useful concept for enhancing memory to feed the LLM context. But DO NOT vibe your dream. Asking your agent to "hey, just dream and keep the relevant memory around" is a recipe for deleting a bunch of important information and keeping trash around. Your dream needs to have some Taxonomy (or better, Ontology). What information is important? For who? With what object? What can they do? And again, these are impossible to describe and act well without a proper schema 🔄 Loop Engineering is important for smoothing out rough edges in the system we build. But even expensive loop engineering with a state-of-the-art model can't out-engineer bad system design. The highest leverage an AI Engineer can do is actually building the right system design, and having an eye on both product delight and engineering scalability There are several more insights that I plan to cover in a dedicated video about Agentic AI Engineering. But it's actually a huge relief that the future of software engineering... is still software engineering

Gogo | Dota for Toxicity

30,766 views • 4 months ago

Introducing Judgment vSQL: Your coding agent SHOULD query all your agent data in standard SQL, with no made-up DSL or limited look-up tools. > Ask your coding agent "Compare my last few agent versions, did anything regress?" > It writes one SQL query that joins your traces, the steps inside them, and the labels our judges gave them > It runs the query in a sandbox you can inspect > It brings back a ranked list of where your agents are failing

Introducing Judgment vSQL: Your coding agent SHOULD query all your agent data in standard SQL, with no made-up DSL or limited look-up tools. > Ask your coding agent "Compare my last few agent versions, did anything regress?" > It writes one SQL query that joins your traces, the steps inside them, and the labels our judges gave them > It runs the query in a sandbox you can inspect > It brings back a ranked list of where your agents are failing

Judgment Labs

12,627 views • 3 days ago

It is to be clarified none of the staff involved in the ongoing query are missing or absconding. -CPRO/SER

It is to be clarified none of the staff involved in the ongoing query are missing or absconding. -CPRO/SER

Spokesperson Railways

1,468,212 views • 3 years ago