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.

ok this is something I keep thinking about and haven't seen anyone actually say out loud agents made me personally so much faster at my job, like genuinely different person levels of output but the companies I've worked at as a whole? nothing. Maybe a little and I think... it's because none of that context ever left my head. The agent knew what I knew about the account, not what the company knew, so it dies with me instead of compounding for the team that's basically the exact problem Lightfield is fixing. instead of reps manually logging notes, it ingests every call, email, and slack to build a live customer world model that both humans and agents work from. they just announced a $47M series A led by a16z.show more

Chidanand Tripathi

116,491 subscribers

99,689 views • 6 days ago •via X (Twitter)

News & Politics Education Science & Technology

Anya Rossi• Live Now

Private livecam show

30 Comments

Zifan Carter6 days ago

This is a great perspective!

Alice The Ai Expert5 days ago

You nailed the real bottleneck personal productivity means nothing if context dies with you, and a live customer world model that compounds for the whole team is exactly the fix we need!

SOUL♡6 days ago

Wait this is actually a really good point

Rehan6 days ago

Turning tribal knowledge into shared machine-readable context is a huge unlock

Jyoti Soni5 days ago

The interesting part isn’t just capturing conversations, it’s turning those conversations into usable organizational memory

Abigail Parker6 days ago

The real AI bottleneck isn’t intelligence, it’s access to the right context

Aaliya5 days ago

Personal gains vs company gains is the whole story

Aria Tech5 days ago

Finally agents that learn from the whole company not just you

Mujeeb Ahmed6 days ago

Individual speed vs organizational speed are two completely different games

Elise Tech Ai5 days ago

Love this — so clean and inspiring!

Shubham Singh6 days ago

Context that stays trapped in individual employees is one of the biggest hidden costs in modern companies

Dhaval Makwana6 days ago

Their journey is amazing

Ella Tech & Tool5 days ago

So real 👏 Individual speed team speed. This fixes it

Iris Hayes2 days ago

The strongest AI systems won’t just generate output, they’ll understand

Iris Hayes5 days ago

The strongest AI systems won’t just generate output, they’ll understand

Fakhr6 days ago

This seems a big announcement

Alan6 days ago

The irony is we finally have tools that can scale individual expertise but the expertise itself stays siloed

Aria Arooj5 days ago

That's a really smart take. It's great that Lightfield is addressing that knowledge gap.

Ismail Khan6 days ago

The compounding context moat is probably the most interesting part of this

Saberin Samarat5 days ago

Amazing

Swati5 days ago

The strongest AI systems won’t just generate output, they’ll understand

Professional_Tech_AI6 days ago

Amazing

Parul Gautam6 days ago

Nobody is talking about this enough

tejtejshawirajd6 days ago

This explains why my team's AI adoption looked great on paper but changed nothing operationally

shamim Reza6 days ago

Great

DILESH GAUTAM6 days ago

$47M makes sense when the ambition is to become the context layer between a company, its people, and its agents

AI with Durga 🚀6 days ago

The next generation of CRM probably looks less like a database and more like a living model of the business

Max6 days ago

Really enjoyed this. Simple, thoughtful, and beautifully put together.

Manish Kumar Shah6 days ago

This is the knowledge transfer problem nobody talks about. You leave, the AI context leaves with you

Markandey Sharma6 days ago

The knowledge just evaporates when people leave

Related Videos

CRM has always been weird. Humans do the work → then manually update the CRM about the work. Lightfield is flipping that model. Instead of asking reps to keep the CRM updated, it builds the customer context from calls, emails, Slack, LinkedIn, etc. Then agents can actually work from that context. This feels much closer to what an AI-native CRM should be. $47M Series A led by a16z is a pretty strong signal too.

CRM has always been weird. Humans do the work → then manually update the CRM about the work. Lightfield is flipping that model. Instead of asking reps to keep the CRM updated, it builds the customer context from calls, emails, Slack, LinkedIn, etc. Then agents can actually work from that context. This feels much closer to what an AI-native CRM should be. $47M Series A led by a16z is a pretty strong signal too.

Kshitij Mishra | AI & Tech

22,877 views • 6 days ago

Today we're announcing Lightfield's $47M Series A led by a16z to reimagine CRM as a world model of a business. For agents to do customer-facing work, they need to understand how your business actually works. Salesforce wasn't designed for this. It was built 20+ years ago for humans to update records. Layer agentic processes on top and you get low quality output, because the underlying data is incomplete and lacks the structure agents need. Lightfield updates itself from every interaction, forming a trustworthy model of your business for people and agents. Since launching last November, 5,000+ companies have signed up - and we're ripping out legacy CRM at mature organizations with hundreds of users. Companies on Lightfield grow faster than their competitors. It finds prospects that look like your best customers and books meetings with them. It captures commitments from every conversation and automates follow-ups. It diagnoses weaknesses in your funnel and learns from your best sellers to codify what works. The companies of the future will run on a business world model, not a Salesforce-era database. Our mission is to put that capability in the hands of every employee, and every agent, at every company.

Today we're announcing Lightfield's $47M Series A led by a16z to reimagine CRM as a world model of a business. For agents to do customer-facing work, they need to understand how your business actually works. Salesforce wasn't designed for this. It was built 20+ years ago for humans to update records. Layer agentic processes on top and you get low quality output, because the underlying data is incomplete and lacks the structure agents need. Lightfield updates itself from every interaction, forming a trustworthy model of your business for people and agents. Since launching last November, 5,000+ companies have signed up - and we're ripping out legacy CRM at mature organizations with hundreds of users. Companies on Lightfield grow faster than their competitors. It finds prospects that look like your best customers and books meetings with them. It captures commitments from every conversation and automates follow-ups. It diagnoses weaknesses in your funnel and learns from your best sellers to codify what works. The companies of the future will run on a business world model, not a Salesforce-era database. Our mission is to put that capability in the hands of every employee, and every agent, at every company.

Keith Peiris

1,324,500 views • 6 days ago

startups buy salesforce or hubspot by default because that's just what you do when you scale. the problem is those systems were built for reps manually typing notes. slapping ai agents on top of subjective, incomplete data is a bottleneck. lightfield actually rebuilt the crm for the agent era. full api and mcp access turns it into infrastructure. 5,000+ companies already moved. i've been working with the lightfield team, and their $47m series a is pure signal. opinions are mine.

startups buy salesforce or hubspot by default because that's just what you do when you scale. the problem is those systems were built for reps manually typing notes. slapping ai agents on top of subjective, incomplete data is a bottleneck. lightfield actually rebuilt the crm for the agent era. full api and mcp access turns it into infrastructure. 5,000+ companies already moved. i've been working with the lightfield team, and their $47m series a is pure signal. opinions are mine.

kai.

13,404 views • 6 days ago

“Because I think a lot of people are familiar with you know, pop stars have these alter egos on stage and then they're also a little bit potentially different behind the scenes. Can you talk about what the difference is between those two personas?” ROSÉ: I think, you know, like I started off as, my whole career started as Blackpink and I feel like it was so much fun creating this character on stage because I'm just from like Australia, like in my bedroom, but like it was so much fun creating this like pop star, like character. It was so much fun. And then I think creating my first solo album, it was my discover of like, you know, who am I? And like when I was naming the album, I really thought a lot about it. There was like options like, you know, number one girl. And then a lot of people did like, what about Rosie? And at first I was like, it seems a bit like narcissistic. I'm not sure. And then it slowly grew on me. And then, you know, just the idea of it being Rosie because Rosé has been such a big part of my life. And that's what we present ourselves as Blackpink, Blackpink Rosé. And I felt like this was very opposite. And so I noticed that it was closer to kind of introducing a different version of me, like because it combined all the stories I would talk about with my friends and family. And they call me Rosie at home. And of course, the online name that the company had made for me from at the beginning of Blackpink, I remember when it happened was like the day before they released my picture, profile picture, they were like, Rosé. And like the name got announced.

rosie

47,583 views • 7 months ago

Q: “Because I think a lot of people are familiar with, you know, pop stars have these alter egos on stage and then they're also a little bit potentially different behind the scenes. Can you talk about what the difference is between those two personas?” ROSÉ: “I think, you know, like I started off as, my whole career started as Blackpink and I feel like it was so much fun creating this character on stage because I'm just from like Australia, like in my bedroom, but like it was so much fun creating this like pop star, like character. It was so much fun. And then I think creating my first solo album, it was my discover of like, you know, who am I? And like when I was naming the album, I really thought a lot about it. There was like options like, you know, number one girl. And then a lot of people did like, what about Rosie? And at first I was like, it seems a bit like narcissistic. ..I'm not sure. And then it slowly grew on me. And then, you know, just the idea of it being Rosie because Rosé has been such a big part of my life. And that's what we present ourselves as Blackpink, Blackpink Rosé. And I felt like this was very opposite. And so I noticed that it was closer to kind of introducing a different version of me, like because it combined all the stories I would talk about with my friends and family. And they call me Rosie at home. And of course, the online name that the company had made for me from at the beginning of Blackpink, I remember when it happened was like the day before they released my picture, profile picture, they were like, Rosé. And like the name got announced.”

hiro

35,872 views • 7 months ago

Airtable's Howie Liu says that basically everyone will need to graduate from being ICs to ICs that manage teams of 20-30 agents: "The best developers today don't just sit there in front of their IDEs and synchronously talk to their agent." "[Instead], you have like 30 separate branches that are each being worked on by a different agent. And you can have the agents continue to update the branches based on human and other agent feedback." "And I think this whole idea of it taking hours for that entire loop to complete — agent pushes some changes, the changes get feedback from other agents or humans, the agent responds to that — that whole loop could be hours, not just minutes. So you're not going to just sit there and watch it one at a time." "But the powerful thing about this is, each one is still actually operating faster than a human engineer. One agent on one branch can do the work of maybe three humans, operating 3x as fast. So it's like a 10x leverage factor just for one agent." "But the best engineers are now able to multitask and say, 'I'm going to oversee my own little team of 20-30 agents working concurrently.'" "Everyone needs to graduate from being an IC to an IC manager of agents. Meaning, if you're a VC analyst, your job should no longer be to go synchronously research one company. You need to go and research like 30 companies, and do them all faster, better, and higher quality than you could before." "That's the greatest leap that is going to be challenging for a lot of people in a lot of roles. Because it's a totally different mentality in how you operate, and what your role is."

Airtable's Howie Liu says that basically everyone will need to graduate from being ICs to ICs that manage teams of 20-30 agents: "The best developers today don't just sit there in front of their IDEs and synchronously talk to their agent." "[Instead], you have like 30 separate branches that are each being worked on by a different agent. And you can have the agents continue to update the branches based on human and other agent feedback." "And I think this whole idea of it taking hours for that entire loop to complete — agent pushes some changes, the changes get feedback from other agents or humans, the agent responds to that — that whole loop could be hours, not just minutes. So you're not going to just sit there and watch it one at a time." "But the powerful thing about this is, each one is still actually operating faster than a human engineer. One agent on one branch can do the work of maybe three humans, operating 3x as fast. So it's like a 10x leverage factor just for one agent." "But the best engineers are now able to multitask and say, 'I'm going to oversee my own little team of 20-30 agents working concurrently.'" "Everyone needs to graduate from being an IC to an IC manager of agents. Meaning, if you're a VC analyst, your job should no longer be to go synchronously research one company. You need to go and research like 30 companies, and do them all faster, better, and higher quality than you could before." "That's the greatest leap that is going to be challenging for a lot of people in a lot of roles. Because it's a totally different mentality in how you operate, and what your role is."

TBPN

35,595 views • 4 months ago

Coinbase CEO Explains “Reverse Prompting” and the Rise of the AI CEO Brian Armstrong: “One of the big pushes we made in the last year was we got our own internal hosted AI model that was connected to all of our data sources, right?” “So it's like every Slack message, every Google doc, Salesforce data, Confluence, you know.” “So now the data is all aggregated and I've started to ask it really… it's not just like prompting it, ‘Hey, can you write this kind of memo for me,’ or something.” “I'm asking these AI agents now, ‘As CEO, what should I be aware of in the company that I might not be aware of?’ And it'll tell me, ‘Did you know that there's actually disagreement on this team about the strategy?’ And I was like, actually, I didn't know that.” “This is like reverse prompting. So instead of telling the AI agent what you want it to do, you ask it what you should be thinking more about.” @jason: “It's a mentor. It's a coach.” Brian: “Yeah. Like, what could make me a better CEO? And it's like, ‘Well, I looked at how you spent your time in the last quarter and here's how you said that you wanted to spend it, but you actually spent 32% of your time on this instead of 20%.’” “I've asked it other questions like, ‘What's the thing that I changed my mind on the most over the last year?’ Things like that.” “It'll prompt you with information you should be thinking about instead of the other way around.” Thanks to our partner for making this happen!: Our episode is sponsored by the New York Stock Exchange - a modern marketplace and exchange for building the future. It all happens at the NYSE 🏛.

Coinbase CEO Explains “Reverse Prompting” and the Rise of the AI CEO Brian Armstrong: “One of the big pushes we made in the last year was we got our own internal hosted AI model that was connected to all of our data sources, right?” “So it's like every Slack message, every Google doc, Salesforce data, Confluence, you know.” “So now the data is all aggregated and I've started to ask it really… it's not just like prompting it, ‘Hey, can you write this kind of memo for me,’ or something.” “I'm asking these AI agents now, ‘As CEO, what should I be aware of in the company that I might not be aware of?’ And it'll tell me, ‘Did you know that there's actually disagreement on this team about the strategy?’ And I was like, actually, I didn't know that.” “This is like reverse prompting. So instead of telling the AI agent what you want it to do, you ask it what you should be thinking more about.” @jason: “It's a mentor. It's a coach.” Brian: “Yeah. Like, what could make me a better CEO? And it's like, ‘Well, I looked at how you spent your time in the last quarter and here's how you said that you wanted to spend it, but you actually spent 32% of your time on this instead of 20%.’” “I've asked it other questions like, ‘What's the thing that I changed my mind on the most over the last year?’ Things like that.” “It'll prompt you with information you should be thinking about instead of the other way around.” Thanks to our partner for making this happen!: Our episode is sponsored by the New York Stock Exchange - a modern marketplace and exchange for building the future. It all happens at the NYSE 🏛.

The All-In Podcast

80,524 views • 7 months ago

lando: “dementia is not something that just people have as they get older. you can be born with it, young people can have it. and it affects over 50 million people around the world. so it's something that none of us want to have. and i'm a guy that my whole life is about memories. it's about creating those pictures in your mind. and the last thing i ever want to do is lose that as i get older. that's what everything in my life is about. so it's cool that i can go out and track. i can have my fun. i can go and race. but there's a kind of second meaning behind it all. and at the same time, i get to do something good for the world. and that's something that i love” ❤️❤️

lando: “dementia is not something that just people have as they get older. you can be born with it, young people can have it. and it affects over 50 million people around the world. so it's something that none of us want to have. and i'm a guy that my whole life is about memories. it's about creating those pictures in your mind. and the last thing i ever want to do is lose that as i get older. that's what everything in my life is about. so it's cool that i can go out and track. i can have my fun. i can go and race. but there's a kind of second meaning behind it all. and at the same time, i get to do something good for the world. and that's something that i love” ❤️❤️

ray

58,749 views • 3 months ago

So when the video of Sam Mugumya leaked last week, the military (and the state) instead of releasing him is threatening me. Anyway, sometimes it’s even hard to tell if it is the military or the state because of the decentralized impunity… but I have received a couple of calls; one from someone that said works with “special forces” identified himself as Elly Tumwine and was demanding to know who gave me that video. I told the person that even if I knew its source my training as a journalist wouldn’t allow me divulge sources but I didn’t even know its source because I got it from social media. The person insisted that I was the first to share it and that they have technology to show that. A couple of days later I received another call. This time there were no introductions but the person said they are concerned about my life although they “like the work I do” but publishing that video of Mugumya “was not wise”. Yesterday, I was told (by a different person that doesn’t know about these calls) of a plan to abduct me because the video I shared has caused so much anger and led to some reshuffle.. I am both informing the state that is supposed to protect its citizens of these threats and Ugandans. #SaveSamMugumya #JusticeForSamMugumya

So when the video of Sam Mugumya leaked last week, the military (and the state) instead of releasing him is threatening me. Anyway, sometimes it’s even hard to tell if it is the military or the state because of the decentralized impunity… but I have received a couple of calls; one from someone that said works with “special forces” identified himself as Elly Tumwine and was demanding to know who gave me that video. I told the person that even if I knew its source my training as a journalist wouldn’t allow me divulge sources but I didn’t even know its source because I got it from social media. The person insisted that I was the first to share it and that they have technology to show that. A couple of days later I received another call. This time there were no introductions but the person said they are concerned about my life although they “like the work I do” but publishing that video of Mugumya “was not wise”. Yesterday, I was told (by a different person that doesn’t know about these calls) of a plan to abduct me because the video I shared has caused so much anger and led to some reshuffle.. I am both informing the state that is supposed to protect its citizens of these threats and Ugandans. #SaveSamMugumya #JusticeForSamMugumya

Agather Atuhaire

93,933 views • 1 month ago

Campos: I'd say pretty much everyone in the room supported what I had to say...I think it's less of a question of if they supported me, and more about their willingness to say the quiet part out loud. I think it's very easy for me to make those kinds of remarks when my livelihood does not rely on corporate media and whoever is pulling the strings at every outlet. So it's a lot scarier for them to speak out against the direction of CBS, especially those who work directly under it. But that's not to say that they don't oppose what's going on. It's just that oftentimes they lack the courage, or there's too much on the line for them to say something about it. And that's not me saying it's a good thing that they're not saying anything — it's just the reality.

Campos: I'd say pretty much everyone in the room supported what I had to say...I think it's less of a question of if they supported me, and more about their willingness to say the quiet part out loud. I think it's very easy for me to make those kinds of remarks when my livelihood does not rely on corporate media and whoever is pulling the strings at every outlet. So it's a lot scarier for them to speak out against the direction of CBS, especially those who work directly under it. But that's not to say that they don't oppose what's going on. It's just that oftentimes they lack the courage, or there's too much on the line for them to say something about it. And that's not me saying it's a good thing that they're not saying anything — it's just the reality.

MeidasTouch

60,848 views • 3 months ago

“So originally, Paint by Numbers was like track one of the album. And at that time, the album was very different. It was like sonically sounding very different. It was like very introspective. I think I was really starting to feel like, you know, I think I loved the idea of opening the album with, oh, what a gift it is to be noticed, but it's nothing to do with me. I just loved, I was like so dedicated to that being the opening line. And I felt so like powerful in a lot of ways to be able to acknowledge that it's not really about me, you know. I mean the opening, the whole opening of the song is, oh, what a gift is to be noticed, but it's nothing to do with me. You've got to wonder if there's a reason to believe it's a lifetime of learning to Paint By Numbers and watching colors run.” - Harry about ‘Paint by Numbers’ on Q

“So originally, Paint by Numbers was like track one of the album. And at that time, the album was very different. It was like sonically sounding very different. It was like very introspective. I think I was really starting to feel like, you know, I think I loved the idea of opening the album with, oh, what a gift it is to be noticed, but it's nothing to do with me. I just loved, I was like so dedicated to that being the opening line. And I felt so like powerful in a lot of ways to be able to acknowledge that it's not really about me, you know. I mean the opening, the whole opening of the song is, oh, what a gift is to be noticed, but it's nothing to do with me. You've got to wonder if there's a reason to believe it's a lifetime of learning to Paint By Numbers and watching colors run.” - Harry about ‘Paint by Numbers’ on Q

HSNews

179,234 views • 6 months ago

Wan'Dale Robinson was asked if he's thought about being a free agent at the end of the season: "I try not to think about it too much. Obviously, I have family and friends that'll call and say something about it, but at the end of the day, I’m just trying to go out there and play my best ball. I'll let my agents handle that whenever the time comes. Just trying to help this team."

Wan'Dale Robinson was asked if he's thought about being a free agent at the end of the season: "I try not to think about it too much. Obviously, I have family and friends that'll call and say something about it, but at the end of the day, I’m just trying to go out there and play my best ball. I'll let my agents handle that whenever the time comes. Just trying to help this team."

SNY Giants

173,321 views • 9 months ago

There's so much focus on "how can AI do my work for me?" I think the more important question is "what work can I now do with AI that I would have never attempted before?" Earlier this year I wrote freestiler, a vector tiling engine for R and Python, with the help of Claude and Codex. I knew what the ideal engine looked like and how it would work at a high level. I didn't know how to put it together, and I don't know Rust, the language I wanted under the hood. Previously I would never have attempted this project as the ROI wasn't there. It would have taken me a year or more to learn the internals of a vector tiling engine and enough Rust to implement one. With Opus-level models, I could take it on. freestiler now powers all my vector tiling pipelines, including the map below rendering 143 million jobs from LODES, and it has 114 GitHub stars. Building this way has required a different set of skills. I don't review the code line by line. I set up adversarial agents to do that and write the test suites. What I review is the architecture, the behavior, and the results. Agent teams surface findings and explain their reasoning; I evaluate and critique. My job isn't to stress over code formatting, but instead to focus on questions like whether the engine is designed right, whether the output is correct, and if the UX makes sense. This means that I haven't "replaced my work." I've taken on entirely new work, with the help of agents, that I would have never done otherwise. It has taken some getting used to shipping code I haven't personally typed. In the old way of working, I built understanding through writing that code. Now I build understanding through managing the project - writing a spec, reviewing structure, evaluating UX. And that's helped me think a whole lot bigger in terms of what I can now do.

There's so much focus on "how can AI do my work for me?" I think the more important question is "what work can I now do with AI that I would have never attempted before?" Earlier this year I wrote freestiler, a vector tiling engine for R and Python, with the help of Claude and Codex. I knew what the ideal engine looked like and how it would work at a high level. I didn't know how to put it together, and I don't know Rust, the language I wanted under the hood. Previously I would never have attempted this project as the ROI wasn't there. It would have taken me a year or more to learn the internals of a vector tiling engine and enough Rust to implement one. With Opus-level models, I could take it on. freestiler now powers all my vector tiling pipelines, including the map below rendering 143 million jobs from LODES, and it has 114 GitHub stars. Building this way has required a different set of skills. I don't review the code line by line. I set up adversarial agents to do that and write the test suites. What I review is the architecture, the behavior, and the results. Agent teams surface findings and explain their reasoning; I evaluate and critique. My job isn't to stress over code formatting, but instead to focus on questions like whether the engine is designed right, whether the output is correct, and if the UX makes sense. This means that I haven't "replaced my work." I've taken on entirely new work, with the help of agents, that I would have never done otherwise. It has taken some getting used to shipping code I haven't personally typed. In the old way of working, I built understanding through writing that code. Now I build understanding through managing the project - writing a spec, reviewing structure, evaluating UX. And that's helped me think a whole lot bigger in terms of what I can now do.

Kyle Walker

13,867 views • 2 months ago

#RM talking about being a leader! “It’s still hard because I was the first um the member of the team, the band. And the label did give me a lot of burden to put the team together as a team. And we had such different backgrounds from different cities and different tastes, different dreams. So I think I was really like overwhelming or very like a powerful type of like bossy type of leader for the first like eight, 9 years. But as the team got bigger and they have their own names and careers, it just didn't work out anymore. Of course, they grew up a lot also. After that, I've changed the way to communicate. And I think a leader is just like this. For example, everybody is lying on the couch and the window is open and it's too cold. So somebody has to close it but nobody wants to because it's too comfy here lying on the couch, it's so annoying. If one single person has to stand off and get off the couch and walk a few steps to close the door then i think that's what a leader does for every part of the team. That’s all” RM AT FASHION NEUROSIS #RMxFASHIONNEUROSIS #RM

#RM talking about being a leader! “It’s still hard because I was the first um the member of the team, the band. And the label did give me a lot of burden to put the team together as a team. And we had such different backgrounds from different cities and different tastes, different dreams. So I think I was really like overwhelming or very like a powerful type of like bossy type of leader for the first like eight, 9 years. But as the team got bigger and they have their own names and careers, it just didn't work out anymore. Of course, they grew up a lot also. After that, I've changed the way to communicate. And I think a leader is just like this. For example, everybody is lying on the couch and the window is open and it's too cold. So somebody has to close it but nobody wants to because it's too comfy here lying on the couch, it's so annoying. If one single person has to stand off and get off the couch and walk a few steps to close the door then i think that's what a leader does for every part of the team. That’s all” RM AT FASHION NEUROSIS #RMxFASHIONNEUROSIS #RM

BTS Charts & News

1,048,102 views • 1 month ago

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.

The Startup Ideas Podcast (SIP) 🧃

13,598 views • 3 months ago

Your portfolio just got a team of Wall Street analysts today 👏 A while back, a friend shared this idea of an AI analyst that's always monitoring your portfolio for insights, patterns, and behaviors. I haven't been able to get it out of my head since. I've been experimenting with different forms and UIs to build this exact thing out, and we've finally launched the first version of how we want to build agents at Rallies. Our new agents tool gives you access to 20+ agents that monitor your portfolio all day and send notes when something meaningful happens. Think of it like email, except the messages are coming from agents with access to a lot of financial data and your portfolio.

Your portfolio just got a team of Wall Street analysts today 👏 A while back, a friend shared this idea of an AI analyst that's always monitoring your portfolio for insights, patterns, and behaviors. I haven't been able to get it out of my head since. I've been experimenting with different forms and UIs to build this exact thing out, and we've finally launched the first version of how we want to build agents at Rallies. Our new agents tool gives you access to 20+ agents that monitor your portfolio all day and send notes when something meaningful happens. Think of it like email, except the messages are coming from agents with access to a lot of financial data and your portfolio.

Rallies

10,312 views • 5 months ago

Tyler, The Creator explains that the concept of ‘CHROMAKOPIA’ was born from the question: “Where is my home?” “So I start thinking of home and then I was like: ‘What is home when I think about it in a physical sense?’ And I'm like: ‘Oh, it's my mom, being in the house with her’. What does that mean? Her telling me little tidbits about life. That's why she narrates the album, because that's home for me.”

Tyler, The Creator explains that the concept of ‘CHROMAKOPIA’ was born from the question: “Where is my home?” “So I start thinking of home and then I was like: ‘What is home when I think about it in a physical sense?’ And I'm like: ‘Oh, it's my mom, being in the house with her’. What does that mean? Her telling me little tidbits about life. That's why she narrates the album, because that's home for me.”

Archive Tyler, The Creator

40,330 views • 5 months ago

Indiana Fever guard Sophie Cunningham suggested that WNBA Commissioner Cathy Engelbert could be OUT as commissioner by the END of the year after the organization FAILED to define what a woman is. “You do have to have a person in power who is bold, who is confident, who wants the best for the players and not maybe for themselves all the time. So I do feel like, as a whole, that could be a position that's maybe open at the end of the year, but that's not my call,” Cunningham told USA Today. “People are like, ‘You have a platform. Use it,’ and then once you use it, it's like, ‘Go back to playing basketball.’ I think the reason why I stated that is because you go into media, and it's not anything even about basketball. I think I could do both.” “Ask me about what's going on and what I said. And also ask me how great my teammates are doing, how great our team is doing, how great the league is doing.”

Indiana Fever guard Sophie Cunningham suggested that WNBA Commissioner Cathy Engelbert could be OUT as commissioner by the END of the year after the organization FAILED to define what a woman is. “You do have to have a person in power who is bold, who is confident, who wants the best for the players and not maybe for themselves all the time. So I do feel like, as a whole, that could be a position that's maybe open at the end of the year, but that's not my call,” Cunningham told USA Today. “People are like, ‘You have a platform. Use it,’ and then once you use it, it's like, ‘Go back to playing basketball.’ I think the reason why I stated that is because you go into media, and it's not anything even about basketball. I think I could do both.” “Ask me about what's going on and what I said. And also ask me how great my teammates are doing, how great our team is doing, how great the league is doing.”

RedWave Press

50,985 views • 26 days ago