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.

Semantic search alone doesn't cut it. Neither does brute-force grep. Agents need both. Today we're shipping the Retrieval Harness in LlamaParse Index: semantic search, server-side grep, and file-level navigation working together in a single agent reasoning loop. 🦙🌤️ Grep a file, list what's in an index, read past a... show more

LlamaIndex 🦙

117,203 subscribers

29,181 views • 17 days 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

Give Claude Code a semantic filesystem 🗃️🛠️ Giving Claude Code access to the right CLI tools over your filesystem turns it into a general agent capable of automating far more knowledge work beyond code - it can do dynamic financial/legal/medical/technical/backoffice analysis over any subset of documents. With our latest release of semtools 💫, you can now manually or *agentically* create a persistent workspace over any subset of files. This gives Claude Code the ability to get blazing-fast, local semantic search over any data, while still allowing it to chain with commands like grep/cat/etc. so that it can load in dynamic context instead of naive top-k vector search. The coding agent can dynamically index data and use those indexes, instead of having to rebuild it every time. So you get the benefits of fast search along with agentic reasoning over CLI tools mentioned above. Come check it out!

Give Claude Code a semantic filesystem 🗃️🛠️ Giving Claude Code access to the right CLI tools over your filesystem turns it into a general agent capable of automating far more knowledge work beyond code - it can do dynamic financial/legal/medical/technical/backoffice analysis over any subset of documents. With our latest release of semtools 💫, you can now manually or agentically create a persistent workspace over any subset of files. This gives Claude Code the ability to get blazing-fast, local semantic search over any data, while still allowing it to chain with commands like grep/cat/etc. so that it can load in dynamic context instead of naive top-k vector search. The coding agent can dynamically index data and use those indexes, instead of having to rebuild it every time. So you get the benefits of fast search along with agentic reasoning over CLI tools mentioned above. Come check it out!

Jerry Liu

77,373 views • 9 months ago

Filesystems vs Vector search is the new MCP vs CLI. Claude uses agentic search. And Dens Sumesh at mintlify like filesystems too. but Retrieval is still used by Notion, Cursor, and others. We hit the cafes of SF to see what people want. - The debate is hot. Filesystems won by 1 point - filesystems feel very simple and intuitive. - RAG requires embedding, vector search and other stuff filesystems won. Introducing SMFS - Supermemory Filesystem we brought the best of these worlds into one single product - it's a filesystem, but agent can also do semantic search using grep. live today. Try it! Works with any sandbox, you mount and sync with cloud, it has a sync engine built in, all filetypes supported - even images and videos can be grepped. So, what do you choose - Filesystems, or vector search? we have both!

Filesystems vs Vector search is the new MCP vs CLI. Claude uses agentic search. And Dens Sumesh at mintlify like filesystems too. but Retrieval is still used by Notion, Cursor, and others. We hit the cafes of SF to see what people want. - The debate is hot. Filesystems won by 1 point - filesystems feel very simple and intuitive. - RAG requires embedding, vector search and other stuff filesystems won. Introducing SMFS - Supermemory Filesystem we brought the best of these worlds into one single product - it's a filesystem, but agent can also do semantic search using grep. live today. Try it! Works with any sandbox, you mount and sync with cloud, it has a sync engine built in, all filetypes supported - even images and videos can be grepped. So, what do you choose - Filesystems, or vector search? we have both!

Dhravya Shah

153,119 views • 2 months ago

Turn Claude Code into a Financial Analyst 🤖💹 In this video we point Claude Code at a bucket of 10k filing PDFs, and have it perform complex analysis across the entire set of docs! Claude Code doesn’t have file understanding out of the box (it kind of does, but it’s terrible / doesn’t work over long PDFs). We equipped Claude Code with targeted tools for file parsing and efficient search, courtesy of our recently released `semtools`. It’s way faster/more versatile than naive RAG 💡. You get super-fast in-mem keyword/semantic search, and Claude Code can combine this with standard file tools like grep and `Read` to load in dynamic context instead of fixed chunks. You can do this in seconds. Just install `semtools`, add it to your and point Claude to any bucket of files you want to analyze. SemTools (s/o Logan Markewich): File parsing courtesy of LlamaCloud:

Turn Claude Code into a Financial Analyst 🤖💹 In this video we point Claude Code at a bucket of 10k filing PDFs, and have it perform complex analysis across the entire set of docs! Claude Code doesn’t have file understanding out of the box (it kind of does, but it’s terrible / doesn’t work over long PDFs). We equipped Claude Code with targeted tools for file parsing and efficient search, courtesy of our recently released `semtools`. It’s way faster/more versatile than naive RAG 💡. You get super-fast in-mem keyword/semantic search, and Claude Code can combine this with standard file tools like grep and `Read` to load in dynamic context instead of fixed chunks. You can do this in seconds. Just install `semtools`, add it to your and point Claude to any bucket of files you want to analyze. SemTools (s/o Logan Markewich): File parsing courtesy of LlamaCloud:

Jerry Liu

32,804 views • 10 months ago

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

159,484 views • 4 months ago

🚀 Introducing the World's First Full Agentic Download Agent & AI Drive! 💬 One prompt does it all: search, download, organize files instantly 🗂️ Support download any file: PDFs, images, videos, music, Office documents and more 💡 Integrated Super Agents in AI Drive: process your saved files with AI Try it now: #AItool #Genspark #GENSPEED

🚀 Introducing the World's First Full Agentic Download Agent & AI Drive! 💬 One prompt does it all: search, download, organize files instantly 🗂️ Support download any file: PDFs, images, videos, music, Office documents and more 💡 Integrated Super Agents in AI Drive: process your saved files with AI Try it now: #AItool #Genspark #GENSPEED

Genspark

211,905 views • 1 year ago

Introducing the Knowledge Agent Template Vercel dropped the Chat SDK so we built a full template on top of it that you can deploy in one click. Here's what's inside: • Add your sources: GitHub repos, YouTube, etc. directly from the UI • File-based agent using grep/find/cat • Powered by Vercel Workflow + Sandbox • Multi-platform: web chat, GitHub bot, Discord bot, and more • Comes with skills to edit your project, add sources, create agents Deploy, add a source, ask questions. Your knowledge base is live and always in sync. This is just scratching the surface. There's way more packed in this template, and I'll be breaking down the features all week. Links in the below 👇

Introducing the Knowledge Agent Template Vercel dropped the Chat SDK so we built a full template on top of it that you can deploy in one click. Here's what's inside: • Add your sources: GitHub repos, YouTube, etc. directly from the UI • File-based agent using grep/find/cat • Powered by Vercel Workflow + Sandbox • Multi-platform: web chat, GitHub bot, Discord bot, and more • Comes with skills to edit your project, add sources, create agents Deploy, add a source, ask questions. Your knowledge base is live and always in sync. This is just scratching the surface. There's way more packed in this template, and I'll be breaking down the features all week. Links in the below 👇

Hugo

54,481 views • 4 months ago

New AI Agentic course! Learn to use LangGraph to build single and multi-agent LLM applications in AI Agents in LangGraph. This short course, taught by LangChain founder Harrison Chase Harrison Chase and Tavily founder @weiss_rotem, shows how to integrate agentic search to enhance an agent's knowledge with query-focused answers in predictable formats. Also learn to implement agentic memory to save state for reasoning and debugging, and see how human-in-the-loop input can guide agents at key junctures. You'll build an agent from scratch, then reconstruct it with LangGraph to thoroughly understand the framework. Finally, you'll build a sophisticated essay-writing agent that incorporates all the learnings from the course. Sign up here!

New AI Agentic course! Learn to use LangGraph to build single and multi-agent LLM applications in AI Agents in LangGraph. This short course, taught by LangChain founder Harrison Chase Harrison Chase and Tavily founder @weiss_rotem, shows how to integrate agentic search to enhance an agent's knowledge with query-focused answers in predictable formats. Also learn to implement agentic memory to save state for reasoning and debugging, and see how human-in-the-loop input can guide agents at key junctures. You'll build an agent from scratch, then reconstruct it with LangGraph to thoroughly understand the framework. Finally, you'll build a sophisticated essay-writing agent that incorporates all the learnings from the course. Sign up here!

Andrew Ng

152,534 views • 2 years ago

HERMES AGENT JUST LAUNCHED A NATIVE DESKTOP APP. macOS. WINDOWS. LINUX. DOWNLOAD, OPEN, START. Hermes Desktop is now in public preview. first demoed at Jensen's GTC keynote. native app with: → side-by-side preview pane → built-in file browser → integrated voice and TTS → image generation built in → multi-model reasoning → same data directory as CLI → switch between Desktop and CLI anytime what your agent can do from the app: → persistent memory across sessions → natural-language cron jobs → isolated subagents with zero-context-cost → browser automation and web search → 27+ messaging platforms from one gateway → 5 sandbox backends with container hardening (local, Docker, SSH, Singularity, Modal) open source. MIT license. v0.15.2. download link in the comments. full Hermes setup guide in the article 👇

HERMES AGENT JUST LAUNCHED A NATIVE DESKTOP APP. macOS. WINDOWS. LINUX. DOWNLOAD, OPEN, START. Hermes Desktop is now in public preview. first demoed at Jensen's GTC keynote. native app with: → side-by-side preview pane → built-in file browser → integrated voice and TTS → image generation built in → multi-model reasoning → same data directory as CLI → switch between Desktop and CLI anytime what your agent can do from the app: → persistent memory across sessions → natural-language cron jobs → isolated subagents with zero-context-cost → browser automation and web search → 27+ messaging platforms from one gateway → 5 sandbox backends with container hardening (local, Docker, SSH, Singularity, Modal) open source. MIT license. v0.15.2. download link in the comments. full Hermes setup guide in the article 👇

YanXbt

24,905 views • 1 month ago

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Avi Chawla

11,927 views • 3 months ago

Beyond Reading — AI with Eyes 👁️👁️ AI agents can already read the web. Now, we’re giving them eyes. This week, we demoed Semantic Video Search — powered by the UpRock Network. Not transcript search. Not keyword matching. Real multimodal intelligence across video, audio, frames, timestamps, and context. The demo: We asked UpRock to search across 100+ hours of livestream history. In seconds, it found: → the exact moment → the visual context → the timestamp → the story behind Jesse’s heart-shaped glasses 🕶️ This is what AI search is becoming. Drop in a YouTube video, TikTok, X video, earnings call, competitor demo, or 3-hour conference talk. Don’t just get a summary. Get structured intelligence your AI agent can actually reason over. What makes UpRock different is what’s underneath: 3M+ real devices. 190+ countries. Real phones. Real locations. Ground-truth access. No datacenter proxy games. No synthetic traffic. No stale scrape layer. Just the internet as real users see it. Semantic Video Search is coming soon for UpRock business customers. Building AI agents, research workflows, media intelligence tools, or multimodal search products? Get in touch → ⚡

Beyond Reading — AI with Eyes 👁️👁️ AI agents can already read the web. Now, we’re giving them eyes. This week, we demoed Semantic Video Search — powered by the UpRock Network. Not transcript search. Not keyword matching. Real multimodal intelligence across video, audio, frames, timestamps, and context. The demo: We asked UpRock to search across 100+ hours of livestream history. In seconds, it found: → the exact moment → the visual context → the timestamp → the story behind Jesse’s heart-shaped glasses 🕶️ This is what AI search is becoming. Drop in a YouTube video, TikTok, X video, earnings call, competitor demo, or 3-hour conference talk. Don’t just get a summary. Get structured intelligence your AI agent can actually reason over. What makes UpRock different is what’s underneath: 3M+ real devices. 190+ countries. Real phones. Real locations. Ground-truth access. No datacenter proxy games. No synthetic traffic. No stale scrape layer. Just the internet as real users see it. Semantic Video Search is coming soon for UpRock business customers. Building AI agents, research workflows, media intelligence tools, or multimodal search products? Get in touch → ⚡

UpRock

128,095 views • 1 month ago

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

forloop

226,054 views • 4 months ago

🚨 Tiger Data - Creators of TimescaleDB (Yes! the team behind TimescaleDB) is quietly revolutionizing how we build agents. The Old Way: Glueing together Postgres + Vector DBs + Search tools = complexity. The New Way: Tiger Data’s Agentic Postgres handles it all natively 🔥 What’s now possible 🧵 ↓ ✦ Hybrid retrieval → combine keyword filtering and vector similarity in a single query ✦ Forkable databases → retrieval and safe experimentation without external systems ✦ Native Postgres semantics → everything stays queryable, inspectable, and debuggable in SQL Why this matters: → Fewer moving parts in RAG pipelines → No extra infrastructure to stitch together → Agents can iterate and learn safely → Production data stays isolated and protected This is an awesome shift! Stop bolting workflows onto your database. Let your database be the workflow 🔥

🚨 Tiger Data - Creators of TimescaleDB (Yes! the team behind TimescaleDB) is quietly revolutionizing how we build agents. The Old Way: Glueing together Postgres + Vector DBs + Search tools = complexity. The New Way: Tiger Data’s Agentic Postgres handles it all natively 🔥 What’s now possible 🧵 ↓ ✦ Hybrid retrieval → combine keyword filtering and vector similarity in a single query ✦ Forkable databases → retrieval and safe experimentation without external systems ✦ Native Postgres semantics → everything stays queryable, inspectable, and debuggable in SQL Why this matters: → Fewer moving parts in RAG pipelines → No extra infrastructure to stitch together → Agents can iterate and learn safely → Production data stays isolated and protected This is an awesome shift! Stop bolting workflows onto your database. Let your database be the workflow 🔥

Charly Wargnier

20,181 views • 5 months ago

HERMES AGENT + OBSIDIAN IS A COMBINATION NOBODY IS TALKING ABOUT. Hermes ships with a bundled Obsidian skill. read, search, and create notes in your vault out of the box. why this combination is powerful: Hermes built-in memory is capped. MEMORY.md: 2,200 chars (~800 tokens). USER.md: 1,375 chars (~500 tokens). Obsidian vault has no cap. your agent writes research, session summaries, project context, and learned patterns as linked markdown notes. unlimited depth. the agent creates indexed notes by design. timestamps, backlinks, tags. every note connects to the knowledge graph. three ways to integrate: 1. BUNDLED OBSIDIAN SKILL (simplest) ships with Hermes. reads, searches, creates notes in your vault directly. hermes skills list | grep obsidian 2. OBSIDIAN MCP SERVER (deepest) 30+ tools: full-text search, tag lookup, note management, vault analysis, link analysis, orphan detection. add it via: hermes mcp 3. TELEGRAM + CRON → VAULT (always-on) set a cron job that writes daily summaries, research findings, or task reports directly into your Obsidian vault. your agent feeds the vault while you sleep. you review in Obsidian when you're ready. the unlock: Hermes memory handles what the agent needs to know per session (capped, injected). Obsidian handles everything the agent has ever learned (uncapped, searchable). short-term in Hermes. long-term in Obsidian. both accessible. both persistent. keep the vault scope narrow at first. start with one /Hermes folder. expand once you trust the workflow. 8 Loops Indise Hermes Agent👇

HERMES AGENT + OBSIDIAN IS A COMBINATION NOBODY IS TALKING ABOUT. Hermes ships with a bundled Obsidian skill. read, search, and create notes in your vault out of the box. why this combination is powerful: Hermes built-in memory is capped. MEMORY.md: 2,200 chars (~800 tokens). USER.md: 1,375 chars (~500 tokens). Obsidian vault has no cap. your agent writes research, session summaries, project context, and learned patterns as linked markdown notes. unlimited depth. the agent creates indexed notes by design. timestamps, backlinks, tags. every note connects to the knowledge graph. three ways to integrate: 1. BUNDLED OBSIDIAN SKILL (simplest) ships with Hermes. reads, searches, creates notes in your vault directly. hermes skills list | grep obsidian 2. OBSIDIAN MCP SERVER (deepest) 30+ tools: full-text search, tag lookup, note management, vault analysis, link analysis, orphan detection. add it via: hermes mcp 3. TELEGRAM + CRON → VAULT (always-on) set a cron job that writes daily summaries, research findings, or task reports directly into your Obsidian vault. your agent feeds the vault while you sleep. you review in Obsidian when you're ready. the unlock: Hermes memory handles what the agent needs to know per session (capped, injected). Obsidian handles everything the agent has ever learned (uncapped, searchable). short-term in Hermes. long-term in Obsidian. both accessible. both persistent. keep the vault scope narrow at first. start with one /Hermes folder. expand once you trust the workflow. 8 Loops Indise Hermes Agent👇

YanXbt

20,617 views • 1 month ago

Hermes is powerful. But Open WebUI makes it way easier to actually use. Here’s the setup: → Run Hermes locally → Add the API server → Set up the environment file → Install Open WebUI with Docker → Connect Hermes as the chat agent → Log in and start chatting through a clean UI Now you can use Hermes without living inside the terminal. You get a ChatGPT-style interface, file uploads, model switching, web search, image tools, previews, and cleaner conversation management. Save this video, you’ll make Hermes 10x easier to use. Want the SOP? DM me. 💬

Hermes is powerful. But Open WebUI makes it way easier to actually use. Here’s the setup: → Run Hermes locally → Add the API server → Set up the environment file → Install Open WebUI with Docker → Connect Hermes as the chat agent → Log in and start chatting through a clean UI Now you can use Hermes without living inside the terminal. You get a ChatGPT-style interface, file uploads, model switching, web search, image tools, previews, and cleaner conversation management. Save this video, you’ll make Hermes 10x easier to use. Want the SOP? DM me. 💬

Julian Goldie SEO

61,195 views • 2 months ago

RLM is the most import foundation of my Pi Harness (other than Pi of course). It's seeded with late interaction retrieval results (thanks to @lightonai for pylate). The Agent initiates it with query then.. 𝐒𝐞𝐭𝐮𝐩 A python REPL is created and seeded with: 1. Late interaction search to pre-filter. Instead of doing top 3/5/10, it's top hundreds of documents. This is set into a `context` variable. 2. Python functions are loaded in to do more searches if `context` variable isn't enough. And to make llm calls with cheaper models in parallel batches. 𝐈𝐭𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐋𝐨𝐨𝐩 From there, an LLM iterates in the REPL based on the query. It's just like exploring in a jupyter notebook. The LLM writes prose (like a markdown cell) and code to be run in the REPL each turn. This allows the LLM to sort, filter, and synthesize information. It can fan out and ask smaller models to summarize, combine, contrast, or do anything else to documents to help it understand the data. After several turns the LLM reponds with the final answer. Either because it found the answer, or hit the budget limit. Context as a Python variable, LLM as the programmer, REPL as the runtime. 𝐖𝐡𝐲 𝐃𝐨𝐞𝐬 𝐓𝐡𝐢𝐬 𝐖𝐨𝐫𝐤 1. Richer Shell. Agents (and subagents) work by intermixing code and prose/thinking. But they use static scripts or bash that run and exit and start over each tool call. That's not ideal for exploration and synthesis of data. For that, state is useful to continue building and exploring the data as you learn more. There's a reason jupyter notebooks have been popular with data scientists. 2. Keeps main agent context clean. The better context you have the better the agent will perform (duh!). This means three thing: better human input, less missing search results, and less incorrect search results. Letting the agent iterate allows it to synthesize just what is needed and nothing else. All bad paths or peeks at something that turns out to be irrelevant stays out of main agent context. 3. Stack the good ideas! People often compare late interaction search vs RLM. Or static vs dynamic languages. Or agentic search vs semantic search. But...You can just use them all together for what they're each good at. Use them all for the area they're really great for. Read the full post which has more detail about how and why.

RLM is the most import foundation of my Pi Harness (other than Pi of course). It's seeded with late interaction retrieval results (thanks to @lightonai for pylate). The Agent initiates it with query then.. 𝐒𝐞𝐭𝐮𝐩 A python REPL is created and seeded with: 1. Late interaction search to pre-filter. Instead of doing top 3/5/10, it's top hundreds of documents. This is set into a `context` variable. 2. Python functions are loaded in to do more searches if `context` variable isn't enough. And to make llm calls with cheaper models in parallel batches. 𝐈𝐭𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐋𝐨𝐨𝐩 From there, an LLM iterates in the REPL based on the query. It's just like exploring in a jupyter notebook. The LLM writes prose (like a markdown cell) and code to be run in the REPL each turn. This allows the LLM to sort, filter, and synthesize information. It can fan out and ask smaller models to summarize, combine, contrast, or do anything else to documents to help it understand the data. After several turns the LLM reponds with the final answer. Either because it found the answer, or hit the budget limit. Context as a Python variable, LLM as the programmer, REPL as the runtime. 𝐖𝐡𝐲 𝐃𝐨𝐞𝐬 𝐓𝐡𝐢𝐬 𝐖𝐨𝐫𝐤 1. Richer Shell. Agents (and subagents) work by intermixing code and prose/thinking. But they use static scripts or bash that run and exit and start over each tool call. That's not ideal for exploration and synthesis of data. For that, state is useful to continue building and exploring the data as you learn more. There's a reason jupyter notebooks have been popular with data scientists. 2. Keeps main agent context clean. The better context you have the better the agent will perform (duh!). This means three thing: better human input, less missing search results, and less incorrect search results. Letting the agent iterate allows it to synthesize just what is needed and nothing else. All bad paths or peeks at something that turns out to be irrelevant stays out of main agent context. 3. Stack the good ideas! People often compare late interaction search vs RLM. Or static vs dynamic languages. Or agentic search vs semantic search. But...You can just use them all together for what they're each good at. Use them all for the area they're really great for. Read the full post which has more detail about how and why.

Isaac Flath

40,212 views • 2 months ago

Today we announced the new Einstein Copilot Search and Salesforce Vector Database in Data Cloud to power semantic search and retrieval augmented generation. This will enhance Einstein Copilot's ability to understand, generate outputs, and automate actions across a wide variety of use cases, contexts, and data/content types. LLMs can't be relied on to recall specific data they were trained on, so the way to make them work in the enterprise, where accuracy is paramount, is to feed them with the right data using hybrid keyword and vector search-powered RAG. By bringing all this seamlessly into our apps and Einstein Copilot UX as well as Hyperforce cloud infrastructure, we can offer high performance, low latency, addressing data privacy, security, and residency requirements🌟

Today we announced the new Einstein Copilot Search and Salesforce Vector Database in Data Cloud to power semantic search and retrieval augmented generation. This will enhance Einstein Copilot's ability to understand, generate outputs, and automate actions across a wide variety of use cases, contexts, and data/content types. LLMs can't be relied on to recall specific data they were trained on, so the way to make them work in the enterprise, where accuracy is paramount, is to feed them with the right data using hybrid keyword and vector search-powered RAG. By bringing all this seamlessly into our apps and Einstein Copilot UX as well as Hyperforce cloud infrastructure, we can offer high performance, low latency, addressing data privacy, security, and residency requirements🌟

Clara Shih

49,620 views • 2 years ago

🔥 Your X Agent just got eyes. Watch it think. Built for strict X API compliance. No automated bulk actions. Every engagement is a suggestion you act on manually. Your account stays safe. 💥 New: Live Reasoning Terminal — see every search, thread read, memory recall, and engagement decision across 21 tools as your autonomous agent works. No black box. Here's the full loop in 60 seconds: ↓🎥 1️⃣ Configure Topics, accounts, model tier, run interval, action toggles — full control over what your agent does and how often. 2️⃣ Run Trigger manually or set it on autopilot. Every 30 min to once a day. 3️⃣ Watch it think Live terminal streams every tool call, search, thread read, and decision in real-time. You see exactly what the agent sees. 4️⃣ Review suggestions Replies, likes, follows land in your inbox. Nothing goes live without you. Human-in-the-loop — built for strict X API compliance. 5️⃣ Restyle Don't like the tone? Rewrite any reply — concise, insightful, casual, or your own custom style. One click. 6️⃣ Feedback Hit "Replied" after you post. The agent learns what you approve and adapts next run. The more you use it, the sharper it gets. 🆓 X API costs on us for early users. No extra keys needed. 10 latest models. 7 providers. (OpenAI, Anthropic, Kimi.ai, and more) Try now →

🔥 Your X Agent just got eyes. Watch it think. Built for strict X API compliance. No automated bulk actions. Every engagement is a suggestion you act on manually. Your account stays safe. 💥 New: Live Reasoning Terminal — see every search, thread read, memory recall, and engagement decision across 21 tools as your autonomous agent works. No black box. Here's the full loop in 60 seconds: ↓🎥 1️⃣ Configure Topics, accounts, model tier, run interval, action toggles — full control over what your agent does and how often. 2️⃣ Run Trigger manually or set it on autopilot. Every 30 min to once a day. 3️⃣ Watch it think Live terminal streams every tool call, search, thread read, and decision in real-time. You see exactly what the agent sees. 4️⃣ Review suggestions Replies, likes, follows land in your inbox. Nothing goes live without you. Human-in-the-loop — built for strict X API compliance. 5️⃣ Restyle Don't like the tone? Rewrite any reply — concise, insightful, casual, or your own custom style. One click. 6️⃣ Feedback Hit "Replied" after you post. The agent learns what you approve and adapts next run. The more you use it, the sharper it gets. 🆓 X API costs on us for early users. No extra keys needed. 10 latest models. 7 providers. (OpenAI, Anthropic, Kimi.ai, and more) Try now →

Solaris AI

16,671 views • 4 months ago

The founder of LangChain says both models and harnesses have gotten really good between December and now. According to Harrison Chase, the core idea of an agent before Christmas was a model running in a loop and calling tools. This had been the north star for 3 years. - langchain had this when it launched - autogpt was the same idea - openclaw is kind of a future version of it Then about a year ago, they started getting really good. Claude Code, Manus, and Deep Research were all launched around the same time. All of them use the same pattern: running in a loop with harnesses (planning tools, file systems, code execution, etc) Harness engineering became a thing. Then Opus came out in November and really unlocked it. - the harness let the model do more and more - less hardcoded logic - way more control Then everyone went on vacation, played around, and realized that the model and the harness finally worked reliably.

The founder of LangChain says both models and harnesses have gotten really good between December and now. According to Harrison Chase, the core idea of an agent before Christmas was a model running in a loop and calling tools. This had been the north star for 3 years. - langchain had this when it launched - autogpt was the same idea - openclaw is kind of a future version of it Then about a year ago, they started getting really good. Claude Code, Manus, and Deep Research were all launched around the same time. All of them use the same pattern: running in a loop with harnesses (planning tools, file systems, code execution, etc) Harness engineering became a thing. Then Opus came out in November and really unlocked it. - the harness let the model do more and more - less hardcoded logic - way more control Then everyone went on vacation, played around, and realized that the model and the harness finally worked reliably.

Ivan Burazin

33,948 views • 3 months ago

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Malte Ubl

124,713 views • 6 months ago

𝗚𝗿𝗲𝗽 𝗶𝘀 𝗲𝘅𝗽𝗮𝗻𝗱𝗶𝗻𝗴 𝗯𝗲𝘆𝗼𝗻𝗱 𝗯𝘂𝘀𝗶𝗻𝗲𝘀𝘀 𝗱𝘂𝗲 𝗱𝗶𝗹𝗶𝗴𝗲𝗻𝗰𝗲 𝘁𝗼 𝗵𝗲𝗹𝗽 𝘆𝗼𝘂 𝗴𝗲𝘁 𝘀𝗲𝗿𝗶𝗼𝘂𝘀 𝘄𝗼𝗿𝗸 𝗱𝗼𝗻𝗲 𝘄𝗶𝘁𝗵 𝟮𝟬 𝗔𝗜 𝗘𝘅𝗽𝗲𝗿𝘁𝘀 𝗮𝗰𝗿𝗼𝘀𝘀 𝟭𝟲 𝗶𝗻𝗱𝘂𝘀𝘁𝗿𝗶𝗲𝘀 In December, we launched Grep, an AI agent for business due diligence, as a research preview. Within two weeks, hundreds of people were using it in underwriting, maritime law, logistics, oil and gas, crypto, sales and marketing and much more. Today, we're launching the next version with 20 AI experts across 16 industries to help you carry out deep research and get serious work done. 𝗪𝗵𝘆 𝘄𝗲'𝗿𝗲 𝗯𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗚𝗿𝗲𝗽 Most people are still stuck with AI that doesn't help them get work done. Chatbots that aren't specialized in their domain or vertical agents built for 2024's models—rigid workflows that break easily. Meanwhile, software engineers using Claude Code or Cursor are shipping 10x faster because those tools figured out what actually works. Modern coding agents load up the right context. Then get to work on your objective. That's what Grep does too. You give it an objective—"research this company to verify it is legitimate," "analyze this market and identify potential leads," "tell me who previously owned this vessel," "evaluate this vendor's compliance risk," "carry out a background check on this employee." Grep picks the right Expert and starts investigating across 50+ specialized sources, including corporate registries, court records, financial filings, sanctions databases, shipping data, academic journals and much more. This deep research provides the context to help you complete your task. Then you dig deeper. Ask follow-ups. Probe specific angles. The expert already has all the skills and integrations to help you get work done. But work doesn't end with research. Grep helps you turn that research into docs, decks, slides, reports, and even code. The context carries through, so the AI Expert can help you execute, not just inform. We're pretty excited about Grep and would love your feedback, especially if you are an early adopter of AI in your domain but aren't satisfied with your existing workflows. If you want to try Grep, join the waitlist at - we'll be starting with a small group of beta users and expanding as we make our AI Experts even better with user feedback. P.S. Huge thanks to Awesomic for the launch video 🎬

𝗚𝗿𝗲𝗽 𝗶𝘀 𝗲𝘅𝗽𝗮𝗻𝗱𝗶𝗻𝗴 𝗯𝗲𝘆𝗼𝗻𝗱 𝗯𝘂𝘀𝗶𝗻𝗲𝘀𝘀 𝗱𝘂𝗲 𝗱𝗶𝗹𝗶𝗴𝗲𝗻𝗰𝗲 𝘁𝗼 𝗵𝗲𝗹𝗽 𝘆𝗼𝘂 𝗴𝗲𝘁 𝘀𝗲𝗿𝗶𝗼𝘂𝘀 𝘄𝗼𝗿𝗸 𝗱𝗼𝗻𝗲 𝘄𝗶𝘁𝗵 𝟮𝟬 𝗔𝗜 𝗘𝘅𝗽𝗲𝗿𝘁𝘀 𝗮𝗰𝗿𝗼𝘀𝘀 𝟭𝟲 𝗶𝗻𝗱𝘂𝘀𝘁𝗿𝗶𝗲𝘀 In December, we launched Grep, an AI agent for business due diligence, as a research preview. Within two weeks, hundreds of people were using it in underwriting, maritime law, logistics, oil and gas, crypto, sales and marketing and much more. Today, we're launching the next version with 20 AI experts across 16 industries to help you carry out deep research and get serious work done. 𝗪𝗵𝘆 𝘄𝗲'𝗿𝗲 𝗯𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗚𝗿𝗲𝗽 Most people are still stuck with AI that doesn't help them get work done. Chatbots that aren't specialized in their domain or vertical agents built for 2024's models—rigid workflows that break easily. Meanwhile, software engineers using Claude Code or Cursor are shipping 10x faster because those tools figured out what actually works. Modern coding agents load up the right context. Then get to work on your objective. That's what Grep does too. You give it an objective—"research this company to verify it is legitimate," "analyze this market and identify potential leads," "tell me who previously owned this vessel," "evaluate this vendor's compliance risk," "carry out a background check on this employee." Grep picks the right Expert and starts investigating across 50+ specialized sources, including corporate registries, court records, financial filings, sanctions databases, shipping data, academic journals and much more. This deep research provides the context to help you complete your task. Then you dig deeper. Ask follow-ups. Probe specific angles. The expert already has all the skills and integrations to help you get work done. But work doesn't end with research. Grep helps you turn that research into docs, decks, slides, reports, and even code. The context carries through, so the AI Expert can help you execute, not just inform. We're pretty excited about Grep and would love your feedback, especially if you are an early adopter of AI in your domain but aren't satisfied with your existing workflows. If you want to try Grep, join the waitlist at - we'll be starting with a small group of beta users and expanding as we make our AI Experts even better with user feedback. P.S. Huge thanks to Awesomic for the launch video 🎬

AJ Asver

28,077 views • 5 months ago