正在加载视频...

视频加载失败

返回首页

📚 Build Deep Research Agent: From Question to Insight Complex research rarely fits in one search box. The Deep Research workflow built with Dify Iterates, reasons, and sources until the answer is complete. 💡 Key workflow nodes include: 1) Start: capture the research topic and the loop budget 2)...

dify_ai's profile picture

Dify

22,407 subscribers

22,470 次观看 • 1 年前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

3 条评论

jem 的头像
jem1 年前

Is there a template for it? since the blog post doesn’t cover the prompts and all of the structured outputs

Dify 的头像
Dify1 年前

The template is now live on our Explore page:

ksminnovation 的头像
ksminnovation1 年前

Can AI redefine scientific discovery? Dr. Tal Patalon explores OpenAI’s Deep Research in her latest Forbes article. 🎨 Future by Eduardo Kobra, provided by Eden Gallery. @TalPatalon @forbes @edengallery_

相关视频

You can now connect GitHub repos to deep research in ChatGPT. 🐙 Ask a question and the deep research agent will read and search the repo’s source code and PRs, returning a detailed report with citations. Hit deep research → GitHub to get started.
0:46

You can now connect GitHub repos to deep research in ChatGPT. 🐙 Ask a question and the deep research agent will read and search the repo’s source code and PRs, returning a detailed report with citations. Hit deep research → GitHub to get started.

OpenAI Developers

1,507,446 次观看 • 1 年前

Launch Week Day 2: the Consensus Research Agent. Consensus can now complete complex research tasks through multi-step tool calls. One prompt in. A full research workflow out.
6:41

Launch Week Day 2: the Consensus Research Agent. Consensus can now complete complex research tasks through multi-step tool calls. One prompt in. A full research workflow out.

Consensus

16,851 次观看 • 5 个月前

Built a small research playground with Nimble API. You enter a prompt: → Research OpenAI competitors → Find AI startups in (Any country of your choice) → Analyze the AI coding agent market The app turns it into a structured research report with summaries, findings, and source cards. Here's the workflow 👇
0:23

Built a small research playground with Nimble API. You enter a prompt: → Research OpenAI competitors → Find AI startups in (Any country of your choice) → Analyze the AI coding agent market The app turns it into a structured research report with summaries, findings, and source cards. Here's the workflow 👇

Kaitee

35,418 次观看 • 4 个月前

1. The first AI Research Agent, deep research on any topic in one click. visit and sign up, input any topic you want to research for. Then you can get: → Write high-quality articles instantly → Back them with credible sources
0:29

1. The first AI Research Agent, deep research on any topic in one click. visit and sign up, input any topic you want to research for. Then you can get: → Write high-quality articles instantly → Back them with credible sources

Allen Lattimer

45,288 次观看 • 1 年前

Deep Research Combined With Powerpoint Our PowerPoint agent - gathers requirements - does deep research and gathers content - creates an outline for each slide - lets you make edits and upload a template and presents the final result in the form of a finished product!!
0:46

Deep Research Combined With Powerpoint Our PowerPoint agent - gathers requirements - does deep research and gathers content - creates an outline for each slide - lets you make edits and upload a template and presents the final result in the form of a finished product!!

Bindu Reddy

23,783 次观看 • 1 年前

Deep Research 🤝 Gemini Live. Use your voice to explore a topic — in depth — with Gemini Live's Deep Research integration. 1. Just ask the Google Gemini to run a Deep Research report on a topic, then feel free to close the chat, lock your screen, or keep chatting about other things. 2. Gemini will work asynchronously in the background and send you a notification when your full research report is ready. 3. Once it is, you can chat through the results, ask follow-up questions, or refine the details.
0:51

Deep Research 🤝 Gemini Live. Use your voice to explore a topic — in depth — with Gemini Live's Deep Research integration. 1. Just ask the Google Gemini to run a Deep Research report on a topic, then feel free to close the chat, lock your screen, or keep chatting about other things. 2. Gemini will work asynchronously in the background and send you a notification when your full research report is ready. 3. Once it is, you can chat through the results, ask follow-up questions, or refine the details.

Google

394,378 次观看 • 1 个月前

ChatGPT gives you wrong answers and fake citations (many don't know this). Here's a quick free solution (watch the video): 1. Go to consensus(dot)app 2. Type in your research question 3. Turn on "synthesize" for the summary 4. Dive into accurate research papers that tell you the truth Let me know if this is helpful to find reliable research and cite better.
0:24

ChatGPT gives you wrong answers and fake citations (many don't know this). Here's a quick free solution (watch the video): 1. Go to consensus(dot)app 2. Type in your research question 3. Turn on "synthesize" for the summary 4. Dive into accurate research papers that tell you the truth Let me know if this is helpful to find reliable research and cite better.

Aadit Sheth

380,069 次观看 • 3 年前

AI research is getting f...cking illegal 15 GitHub projects for turning a question into sources, evidence, citations, and a finished report 01 GPT Researcher ▸ → recursive deep research 02 STORM ▸ SEARCH DEEPER 03 Perplexica ▸ 04 Open Deep Research ▸ 05 DeerFlow ▸ READ THE WEB 06 Firecrawl ▸ 07 Crawl4AI ▸ 08 Jina Reader ▸ TURN PAPERS INTO EVIDENCE 09 PaperQA2 ▸ → agentic RAG + citations 10 OpenScholar ▸ 11 PaperMage ▸ CONNECT THE SOURCES 12 GraphRAG ▸ 13 LightRAG ▸ 14 Kotaemon ▸ 15 Docling ▸ the loop: ask → split the problem → search multiple paths → read the sources → extract evidence → connect the findings → challenge the answer → cite → write 3 stacks I'd actually try: deep research: GPT Researcher → Firecrawl → GraphRAG → Docling scientific: OpenScholar → PaperQA2 → PaperMage → LightRAG private research: Perplexica → Crawl4AI → Kotaemon → GraphRAG the interesting part isn't generating a 20-page report it's being able to trace where every important claim came from AI already learned how to write this stack teaches it how to research ⭣
0:34

AI research is getting f...cking illegal 15 GitHub projects for turning a question into sources, evidence, citations, and a finished report 01 GPT Researcher ▸ → recursive deep research 02 STORM ▸ SEARCH DEEPER 03 Perplexica ▸ 04 Open Deep Research ▸ 05 DeerFlow ▸ READ THE WEB 06 Firecrawl ▸ 07 Crawl4AI ▸ 08 Jina Reader ▸ TURN PAPERS INTO EVIDENCE 09 PaperQA2 ▸ → agentic RAG + citations 10 OpenScholar ▸ 11 PaperMage ▸ CONNECT THE SOURCES 12 GraphRAG ▸ 13 LightRAG ▸ 14 Kotaemon ▸ 15 Docling ▸ the loop: ask → split the problem → search multiple paths → read the sources → extract evidence → connect the findings → challenge the answer → cite → write 3 stacks I'd actually try: deep research: GPT Researcher → Firecrawl → GraphRAG → Docling scientific: OpenScholar → PaperQA2 → PaperMage → LightRAG private research: Perplexica → Crawl4AI → Kotaemon → GraphRAG the interesting part isn't generating a 20-page report it's being able to trace where every important claim came from AI already learned how to write this stack teaches it how to research ⭣

Lummox

38,585 次观看 • 1 个月前

Introducing Qwen 3 + Deep Research! We built a deep research agent with Qwen 3 and it performed better than most open source models that we've tried. the code is completely open source and free! built with 's Langgraph Together AI and uses Perplexity Tavily for search here's the code link:
0:57

Introducing Qwen 3 + Deep Research! We built a deep research agent with Qwen 3 and it performed better than most open source models that we've tried. the code is completely open source and free! built with 's Langgraph Together AI and uses Perplexity Tavily for search here's the code link:

Soham

34,604 次观看 • 1 年前

Your research agent can search the web in English. But the evidence that should shape your answer is in French film institute reports, Japanese trade publications, Brazilian creator communities, and Polish cinema data. That is not a model problem. It is a retrieval and orchestration problem. Neither gets solved by a bigger model. Here's a deep dive of the Temporal, OpenAI, and Box AI research agent we built. The agent plans multilingual queries, searches concurrently across four markets, synthesizes a cited master report, publishes localized briefs to Box with retry-safe versioning, and asks Box AI to compare the external findings against your internal governed content. End-to-end durable research.
1:13

Your research agent can search the web in English. But the evidence that should shape your answer is in French film institute reports, Japanese trade publications, Brazilian creator communities, and Polish cinema data. That is not a model problem. It is a retrieval and orchestration problem. Neither gets solved by a bigger model. Here's a deep dive of the Temporal, OpenAI, and Box AI research agent we built. The agent plans multilingual queries, searches concurrently across four markets, synthesizes a cited master report, publishes localized briefs to Box with retry-safe versioning, and asks Box AI to compare the external findings against your internal governed content. End-to-end durable research.

Box

34,452 次观看 • 3 个月前

First upgrade of PhoenixONE is here - featuring agent thought log. As the research agent is thinking, get a glimpse into the data, insight extraction, and underlying processes. On an average query, Phoenix Crypto Research & Deep Research performs rapid AI contextual search & analysis on 40-50 data sources. On the user growth side - Vietnam Wave 2 coming right up. Meanwhile, Turkey Wave 1 is about to start! $PHB #PhoenixAI #DeepResearch
1:18

First upgrade of PhoenixONE is here - featuring agent thought log. As the research agent is thinking, get a glimpse into the data, insight extraction, and underlying processes. On an average query, Phoenix Crypto Research & Deep Research performs rapid AI contextual search & analysis on 40-50 data sources. On the user growth side - Vietnam Wave 2 coming right up. Meanwhile, Turkey Wave 1 is about to start! $PHB #PhoenixAI #DeepResearch

Phoenix AI Labs

21,907 次观看 • 1 年前

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.
7:37

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.

Santiago

21,079 次观看 • 2 个月前

5⃣ Deep Research is even smarter, rolling out for everyone to try. Today, we're giving Gemini users the ability to try Deep Research, your personal AI research assistant, at no cost. 🧠✨ Gemini Deep Research has been upgraded to 2.0 Flash Thinking Experimental. With this model’s advanced reasoning, Gemini is even better at all stages of research, from planning to delivering even more insightful and detailed reports. Gemini Advanced and qualifying enterprise users have expanded access to Deep Research to save even more time on their most complex projects. Try Deep Research:
0:37

5⃣ Deep Research is even smarter, rolling out for everyone to try. Today, we're giving Gemini users the ability to try Deep Research, your personal AI research assistant, at no cost. 🧠✨ Gemini Deep Research has been upgraded to 2.0 Flash Thinking Experimental. With this model’s advanced reasoning, Gemini is even better at all stages of research, from planning to delivering even more insightful and detailed reports. Gemini Advanced and qualifying enterprise users have expanded access to Deep Research to save even more time on their most complex projects. Try Deep Research:

Google Gemini

258,607 次观看 • 1 年前

Introducing Deep Research for legal in Harvey. Built on OpenAI's Deep Research API and Harvey's legal reasoning systems, Deep Research will enable a new class of legal agents for the world's top law firms and enterprise teams.
5:10

Introducing Deep Research for legal in Harvey. Built on OpenAI's Deep Research API and Harvey's legal reasoning systems, Deep Research will enable a new class of legal agents for the world's top law firms and enterprise teams.

Harvey

58,852 次观看 • 1 年前

I built an entire AI Marketing Campaign Studio with Teamily AI 2.0 But the real game changer? I turned the entire workflow into a reusable Loop Here's how it worked: → Market Research Agent analyzed the target audience → Ad Creative Strategist developed the campaign direction → Social Media Strategist created the content strategy → Review Agent identified issues before human approval Then I changed the target audience from startup founders to small business owners Instead of starting over, I ran the same Loop again The agents updated the research, messaging, and campaign strategy using shared context One workflow, multiple specialized agents, and far less manual coordination This is what AI-native collaboration looks like with Teamily AI 2.0 Try it and save your own workflow as a Loop 🔗 Teamily AI
1:20

I built an entire AI Marketing Campaign Studio with Teamily AI 2.0 But the real game changer? I turned the entire workflow into a reusable Loop Here's how it worked: → Market Research Agent analyzed the target audience → Ad Creative Strategist developed the campaign direction → Social Media Strategist created the content strategy → Review Agent identified issues before human approval Then I changed the target audience from startup founders to small business owners Instead of starting over, I ran the same Loop again The agents updated the research, messaging, and campaign strategy using shared context One workflow, multiple specialized agents, and far less manual coordination This is what AI-native collaboration looks like with Teamily AI 2.0 Try it and save your own workflow as a Loop 🔗 Teamily AI

Sheral Tech

28,536 次观看 • 4 天前