Loading video...

Video Failed to Load

Go Home

8 months ago we started explaining enterprise AI on YouTube. 2M views later, here are the 5 shifts that actually defined 2025. Timestamps 00:36 Prompt Engineering → Agent Engineering 00:51 Prompting best practices 01:19 How context engineering focuses on curating information 01:51 Evolution of assistants to agents 02:12 Agents...

Box's profile picture

Box

77,332 subscribers

460,406 views • 9 months ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Still the best hour on graph engineering ever recorded, Andrew Ng breaking down how to build agentic knowledge graphs from scratch: 00:00 - what agentic knowledge graphs actually are 03:05 - building a graph from scratch 13:58 - the architecture behind multi-agent systems 22:57 - building a real one with Google ADK 01:06:02 - why graphs are the future of AI agents I've seen $500 courses that teach less. Watch it, then take it further with my step-by-step guide on graph engineering below.
1:06:25

Still the best hour on graph engineering ever recorded, Andrew Ng breaking down how to build agentic knowledge graphs from scratch: 00:00 - what agentic knowledge graphs actually are 03:05 - building a graph from scratch 13:58 - the architecture behind multi-agent systems 22:57 - building a real one with Google ADK 01:06:02 - why graphs are the future of AI agents I've seen $500 courses that teach less. Watch it, then take it further with my step-by-step guide on graph engineering below.

Anatoli Kopadze

265,874 views • 1 month ago

“We need more determinism mixed with the creative capabilities of gen AI.” In our latest partner podcast, Fernando Cerenza, Senior Director of Product Management at Box, sat down with Gary Lerhaupt ❇️, VP of Product Architecture of Agentforce at Salesforce, to explore the rise of hybrid reasoning from shifting from simple chatbots to complex multi-agent workflows. Timestamps: 02:12 The transition from deterministic bots to hybrid AI agents 03:15 The shift from simple automation to multi-agent workflows 04:39 Why protocols like MCP and A2A are crucial for agent collaboration 05:36 Understanding how MCP and A2A complement each other 07:16 The importance of open-source industry governance 08:52 How open standards prevent the walled garden issue 10:24 The collaboration between Box and Salesforce in building real-world agent use cases 12:59 The future of an "app store" for agents 13:50 How Salesforce ensures the quality and security of agents in the ecosystem 15:12 Leveraging observability tools to manage and improve agent performance 16:48 Preparing IT leaders for the future of multi-agent workflows and platform readiness
19:11

“We need more determinism mixed with the creative capabilities of gen AI.” In our latest partner podcast, Fernando Cerenza, Senior Director of Product Management at Box, sat down with Gary Lerhaupt ❇️, VP of Product Architecture of Agentforce at Salesforce, to explore the rise of hybrid reasoning from shifting from simple chatbots to complex multi-agent workflows. Timestamps: 02:12 The transition from deterministic bots to hybrid AI agents 03:15 The shift from simple automation to multi-agent workflows 04:39 Why protocols like MCP and A2A are crucial for agent collaboration 05:36 Understanding how MCP and A2A complement each other 07:16 The importance of open-source industry governance 08:52 How open standards prevent the walled garden issue 10:24 The collaboration between Box and Salesforce in building real-world agent use cases 12:59 The future of an "app store" for agents 13:50 How Salesforce ensures the quality and security of agents in the ecosystem 15:12 Leveraging observability tools to manage and improve agent performance 16:48 Preparing IT leaders for the future of multi-agent workflows and platform readiness

Box

659,753 views • 8 months ago

How has the day-to-day workflow of Mitchell Hashimoto (Mitchell Hashimoto) changed, thanks to AI tools? Timestamps: 00:00 Intro 07:19 HashiCorp origins 18:22 The 2010s startup scene in SF 23:11 Funding HashiCorp 25:23 The "Hashi stack" 38:28 The open-core pivot 48:08 Taking HashiCorp public 51:58 The almost-VMware acquisition 59:10 Mitchell’s take on AWS, GCP and Azure 01:06:02 AI’s impact on open source 01:07:00 Ghostty 01:19:13 How Mitchell uses AI 01:28:36 Open source + AI 01:31:46 The problem of Git and monorepos 01:39:57 Mitchell’s hiring practices 01:47:52 Mitchell’s AI adoption journey 01:50:41 Advice to future founders 01:55:03 Closing Also on YouTube, Spotify and Apple (see the next tweet) Brought to you by: • Statsig — ⁠ The unified platform for flags, analytics, experiments, and more. • Sonar – The makers of SonarQube, the industry standard for automated code review. Join me online at the Sonar Summit on March 3rd: • WorkOS – Everything you need to make your app enterprise ready.
1:58:23

How has the day-to-day workflow of Mitchell Hashimoto (Mitchell Hashimoto) changed, thanks to AI tools? Timestamps: 00:00 Intro 07:19 HashiCorp origins 18:22 The 2010s startup scene in SF 23:11 Funding HashiCorp 25:23 The "Hashi stack" 38:28 The open-core pivot 48:08 Taking HashiCorp public 51:58 The almost-VMware acquisition 59:10 Mitchell’s take on AWS, GCP and Azure 01:06:02 AI’s impact on open source 01:07:00 Ghostty 01:19:13 How Mitchell uses AI 01:28:36 Open source + AI 01:31:46 The problem of Git and monorepos 01:39:57 Mitchell’s hiring practices 01:47:52 Mitchell’s AI adoption journey 01:50:41 Advice to future founders 01:55:03 Closing Also on YouTube, Spotify and Apple (see the next tweet) Brought to you by: • Statsig — ⁠ The unified platform for flags, analytics, experiments, and more. • Sonar – The makers of SonarQube, the industry standard for automated code review. Join me online at the Sonar Summit on March 3rd: • WorkOS – Everything you need to make your app enterprise ready.

Gergely Orosz

59,544 views • 7 months ago

chat, is starknet gaming cooked? for episode two, loaf has joined me to talk about ai agents in gaming, eliza and Daydreams: Taskmarket . timestamps loaf introduction 00:46 what are ai agents? 01:16 what will gaming look like with ai agents? 02:02 whats the point of gaming with ai agents? 04:06 why is onchain gaming the ideal playground for AI agents? 05:11 is a gaming revolution imminent? 07:00 eliza & daydreams 08:36 endgame of ai agents and onchain games 13:33 when and where to play using agents 16:58 final remarks 18:47
19:44

chat, is starknet gaming cooked? for episode two, loaf has joined me to talk about ai agents in gaming, eliza and Daydreams: Taskmarket . timestamps loaf introduction 00:46 what are ai agents? 01:16 what will gaming look like with ai agents? 02:02 whats the point of gaming with ai agents? 04:06 why is onchain gaming the ideal playground for AI agents? 05:11 is a gaming revolution imminent? 07:00 eliza & daydreams 08:36 endgame of ai agents and onchain games 13:33 when and where to play using agents 16:58 final remarks 18:47

shadowfax

37,596 views • 1 year ago

Google just released a free 1-hour lecture from Chief Scientist Jeff Dean on full AI Engineering. How to go from one LLM to coordinating 100 AI agents: 01:45 - Build an LLM from scratch 17:22 - Learn how to actually use AI models 30:03 - Master prompt engineering 52:35 - Coordinate 100 agents as one human Most people are still learning how to prompt one model. Jeff Dean is showing the full stack: LLMs → Prompts → Agents → Agent Teams → Graphs Prompting is the old workflow. Coordinating agent systems is the new one. This is 27 years of Google AI compressed into one hour. Bookmark and watch it today Then read the full Graph Engineering guide below ↓
1:06:12

Google just released a free 1-hour lecture from Chief Scientist Jeff Dean on full AI Engineering. How to go from one LLM to coordinating 100 AI agents: 01:45 - Build an LLM from scratch 17:22 - Learn how to actually use AI models 30:03 - Master prompt engineering 52:35 - Coordinate 100 agents as one human Most people are still learning how to prompt one model. Jeff Dean is showing the full stack: LLMs → Prompts → Agents → Agent Teams → Graphs Prompting is the old workflow. Coordinating agent systems is the new one. This is 27 years of Google AI compressed into one hour. Bookmark and watch it today Then read the full Graph Engineering guide below ↓

Lunar

102,835 views • 1 month ago

Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m lecture: • 00:00 - understanding the different layers of AI memory • 30:00 - moving from simple LLM calls to AI agents • 50:00 - why agent systems are becoming a graph engineering problem • 1:12:00 - connecting context, tools and agent state • 1:24:00 - building a minimal agent harness from scratch • 1:46:00 - breaking down the architecture behind Hermes Agent • 2:08:00 - turning agent concepts into working systems 167-minute deep dive, and one of the clearest ways to understand how AI engineering is moving beyond prompts The progression: Prompt → Context → Memory → Agent → Loop → Graph → Agent Harness Watch it today, then read the full roadmap below
2:47:42

Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m lecture: • 00:00 - understanding the different layers of AI memory • 30:00 - moving from simple LLM calls to AI agents • 50:00 - why agent systems are becoming a graph engineering problem • 1:12:00 - connecting context, tools and agent state • 1:24:00 - building a minimal agent harness from scratch • 1:46:00 - breaking down the architecture behind Hermes Agent • 2:08:00 - turning agent concepts into working systems 167-minute deep dive, and one of the clearest ways to understand how AI engineering is moving beyond prompts The progression: Prompt → Context → Memory → Agent → Loop → Graph → Agent Harness Watch it today, then read the full roadmap below

Morlex

51,558 views • 1 month ago

Engineers need to communicate effectively when building AI Systems. These terms will help you use a shared vocabulary. This is useful when discussing concepts, reading papers, or collaborating with teammates. Listed in order. 00:00 Agenda 00:28 1. Large Language Model 01:28 2. Tokenization 02:53 3. Vectorization 04:15 4. Attention 07:22 5. Self-Supervised Learning 12:07 6. Transformer 14:32 7. Fine-tuning 17:05 8. Few-shot Prompting 18:11 9. Retrieval Augmented Generation 20:33 10. Vector Database 23:03 11. Model Context Protocol 25:43 12. Context Engineering 28:17 13. Agents 29:19 14. Reinforcement Learning 34:42 15. Chain of Thought 35:55 16. Reasoning Models 36:36 17. Multi-modal Models 38:21 18. Small Language Models 40:24 19. Distillation 41:47 20. Quantization If you are a software engineer looking to transition to AI, click the link below. AI Engineering Course: #AI #SoftwareEngineering #Agents
43:33

Engineers need to communicate effectively when building AI Systems. These terms will help you use a shared vocabulary. This is useful when discussing concepts, reading papers, or collaborating with teammates. Listed in order. 00:00 Agenda 00:28 1. Large Language Model 01:28 2. Tokenization 02:53 3. Vectorization 04:15 4. Attention 07:22 5. Self-Supervised Learning 12:07 6. Transformer 14:32 7. Fine-tuning 17:05 8. Few-shot Prompting 18:11 9. Retrieval Augmented Generation 20:33 10. Vector Database 23:03 11. Model Context Protocol 25:43 12. Context Engineering 28:17 13. Agents 29:19 14. Reinforcement Learning 34:42 15. Chain of Thought 35:55 16. Reasoning Models 36:36 17. Multi-modal Models 38:21 18. Small Language Models 40:24 19. Distillation 41:47 20. Quantization If you are a software engineer looking to transition to AI, click the link below. AI Engineering Course: #AI #SoftwareEngineering #Agents

Gaurav Sen

80,282 views • 1 year ago

Exclusive: Google just released two upgraded Gemini 1.5 models, 1.5-Pro-002 and 1.5-Flash-002 — achieving new, state-of-the-art performance across math. I sat down with Logan Kilpatrick (Logan Kilpatrick) to discuss the models, AI agents, AGI, and more. Timestamps: 00:00 Intro 01:01 Google rolls out two new Gemini models 2:18 What makes the new models so unique 3:40 Math improvements 8:20 Examples of Gemini 1.5 in the real world 10:19 Future problems AI could solve 12:54 Advantages of Gemini 1.5 16:50 Where beginners can get started 19:01 Advice to thrive in the new age of AI 22:02 Turning notes into podcasts 26:30 AI agents: Definitions and what they can do 31:22 What’s the final form for agents? 33:26 Proactive AI agent systems 36:00 Context windows in the agent era 41:01 AGI’s definition in Logan’s eyes 42:05 The current bottlenecks towards AGI
46:25

Exclusive: Google just released two upgraded Gemini 1.5 models, 1.5-Pro-002 and 1.5-Flash-002 — achieving new, state-of-the-art performance across math. I sat down with Logan Kilpatrick (Logan Kilpatrick) to discuss the models, AI agents, AGI, and more. Timestamps: 00:00 Intro 01:01 Google rolls out two new Gemini models 2:18 What makes the new models so unique 3:40 Math improvements 8:20 Examples of Gemini 1.5 in the real world 10:19 Future problems AI could solve 12:54 Advantages of Gemini 1.5 16:50 Where beginners can get started 19:01 Advice to thrive in the new age of AI 22:02 Turning notes into podcasts 26:30 AI agents: Definitions and what they can do 31:22 What’s the final form for agents? 33:26 Proactive AI agent systems 36:00 Context windows in the agent era 41:01 AGI’s definition in Logan’s eyes 42:05 The current bottlenecks towards AGI

Rowan Cheung

269,890 views • 2 years ago

Laptop closed. Agent still working. 103 legal contracts reviewed in 40 minutes. Most AI agents stop the moment you close your laptop. This one does not. See how DigitalOcean, @chatgptapp Codex, and Box work together to autonomously process a stack of contracts while you step away. The new DigitalOcean Codex plugin makes droplet provisioning a one-click affair. - DigitalOcean: always-on compute for long-running agents - Codex: the harness driving the workflow - Box: the governed content layer (contracts in, review packets out) Timestamps: 00:09 – Workflow setup 01:23 – Provision DigitalOcean droplet for long-running tasks 02:45 – Connect Codex to Box with Box MCP 03:01 – Start a remote session on Codex 03:26 – Implement the legal workflow 05:00 – Review the work 06:05 – Conclusion
6:49

Laptop closed. Agent still working. 103 legal contracts reviewed in 40 minutes. Most AI agents stop the moment you close your laptop. This one does not. See how DigitalOcean, @chatgptapp Codex, and Box work together to autonomously process a stack of contracts while you step away. The new DigitalOcean Codex plugin makes droplet provisioning a one-click affair. - DigitalOcean: always-on compute for long-running agents - Codex: the harness driving the workflow - Box: the governed content layer (contracts in, review packets out) Timestamps: 00:09 – Workflow setup 01:23 – Provision DigitalOcean droplet for long-running tasks 02:45 – Connect Codex to Box with Box MCP 03:01 – Start a remote session on Codex 03:26 – Implement the legal workflow 05:00 – Review the work 06:05 – Conclusion

Box

321,533 views • 2 months ago

Who Hijacked Bitcoin? Steve Patterson and Aaron Day on DarkHorse 00:00:00 Bitcoin: The Questions That Matter 00:03:01 Sponsor: Helix 00:05:26 The Purpose of Bitcoin 00:10:52 Digital Cash 00:18:38 The Reality of Bitcoin Transactions Today 00:27:22 Sponsor: ARMRA 00:29:46 The History of Bitcoin 00:42:14 Preempting the Bitcoin Experts 00:50:20 Bitcoin History: Two Camps Emerge 00:59:57 Bitcoin History: The Mainstream Phase 01:01:59 Bitcoin Corruption: New Information from the Epstein Files 01:04:35 Government Crackdown on Crypto 01:13:25 Is Bitcoin Really Decentralized? 01:35:16 The Connection to Howard Lutnick 01:44:41 CBDCs Should Be Top of Mind 01:45:54 The Coming Financial Collapse 01:47:13 Do We Already Have a Backdoor CBDC? 01:51:44 Tokens and The Great Taking 01:56:38 The Technocracy Movement 02:00:30 Digital Currency Naivety 02:11:32 Morality as a Constraint 02:21:43 Rights as an Irritant to Power 02:23:50 Protecting Yourself 02:25:51 Fighting Back
2:42:55

Who Hijacked Bitcoin? Steve Patterson and Aaron Day on DarkHorse 00:00:00 Bitcoin: The Questions That Matter 00:03:01 Sponsor: Helix 00:05:26 The Purpose of Bitcoin 00:10:52 Digital Cash 00:18:38 The Reality of Bitcoin Transactions Today 00:27:22 Sponsor: ARMRA 00:29:46 The History of Bitcoin 00:42:14 Preempting the Bitcoin Experts 00:50:20 Bitcoin History: Two Camps Emerge 00:59:57 Bitcoin History: The Mainstream Phase 01:01:59 Bitcoin Corruption: New Information from the Epstein Files 01:04:35 Government Crackdown on Crypto 01:13:25 Is Bitcoin Really Decentralized? 01:35:16 The Connection to Howard Lutnick 01:44:41 CBDCs Should Be Top of Mind 01:45:54 The Coming Financial Collapse 01:47:13 Do We Already Have a Backdoor CBDC? 01:51:44 Tokens and The Great Taking 01:56:38 The Technocracy Movement 02:00:30 Digital Currency Naivety 02:11:32 Morality as a Constraint 02:21:43 Rights as an Irritant to Power 02:23:50 Protecting Yourself 02:25:51 Fighting Back

The DarkHorse Podcast

88,842 views • 6 months ago

In our latest Partner Podcast, Jeanette Gessler, VP of Box Consulting, Mike Carlino from Deloitte, and Shivani Majewski from DeloitteDigital, dive into the challenges of governing unstructured data. Timestamps 01:08 Data readiness and the importance of foundation for AI 05:58 Leveraging unstructured data and its governance 07:26 The role of clean and structured data in improving client satisfaction 08:39 Adoption and the importance of change management in integrations 11:54 Importance of reliable, clean data in AI use cases 12:35 Insights into practical applications for business improvement 13:12 Successful AI use cases in regulated industries like insurance and banking 16:51 The buzz around AI agents and moving toward practical AI use cases 19:00 How clients react when data is unlocked and actionable 22:12 Tailoring solutions to clients based on maturity and needs
23:14

In our latest Partner Podcast, Jeanette Gessler, VP of Box Consulting, Mike Carlino from Deloitte, and Shivani Majewski from DeloitteDigital, dive into the challenges of governing unstructured data. Timestamps 01:08 Data readiness and the importance of foundation for AI 05:58 Leveraging unstructured data and its governance 07:26 The role of clean and structured data in improving client satisfaction 08:39 Adoption and the importance of change management in integrations 11:54 Importance of reliable, clean data in AI use cases 12:35 Insights into practical applications for business improvement 13:12 Successful AI use cases in regulated industries like insurance and banking 16:51 The buzz around AI agents and moving toward practical AI use cases 19:00 How clients react when data is unlocked and actionable 22:12 Tailoring solutions to clients based on maturity and needs

Box

190,471 views • 6 months ago

Moving your Coding Agents to the Cloud (ft. Codex Desktop & GPT-6 Astra) 00:00 The limitations of running agents locally 01:13 Parallel development and Git worktrees 02:03 Moving your coding agent to a remote machine 02:25 Introducing Railway Cloud Agents 02:52 Installing the CLI and signing in 03:03 Configuring your project and default agent 03:42 Bringing your agent skills 04:24 Connecting the Codex desktop app 04:48 How SSH configuration works 05:10 Adding the SSH connection in Codex 05:39 Creating a remote project and starting a chat 06:09 Long-running tasks and remote execution 06:26 ChatGPT mobile access 07:03 Using Railway from your coding agent 07:15 Orchestrating multiple cloud agents
8:20

Moving your Coding Agents to the Cloud (ft. Codex Desktop & GPT-6 Astra) 00:00 The limitations of running agents locally 01:13 Parallel development and Git worktrees 02:03 Moving your coding agent to a remote machine 02:25 Introducing Railway Cloud Agents 02:52 Installing the CLI and signing in 03:03 Configuring your project and default agent 03:42 Bringing your agent skills 04:24 Connecting the Codex desktop app 04:48 How SSH configuration works 05:10 Adding the SSH connection in Codex 05:39 Creating a remote project and starting a chat 06:09 Long-running tasks and remote execution 06:26 ChatGPT mobile access 07:03 Using Railway from your coding agent 07:15 Orchestrating multiple cloud agents

Railway

82,044 views • 20 days ago

🚨NEW EPISODE: AI Is Changing How We Work with Crypto Data🚨 In today's episode, we're joined by Kofi to discuss how AI agents are fundamentally changing crypto data analysis, research, and engineering workflows. We discuss: - The evolution from manual coding to AI-assisted development - How MCPs unlock onchain data exploration - Using Herd MCP to analyze smart contracts - AI agents for protocol research and data engineering - Context windows, planning, and agent workflows - Cursor vs OpenCode vs Claude Code (Anthropic) - Managing multiple agents simultaneously - Model selection, costs, and productivity tradeoffs - Building internal AI knowledge bases - Agent orchestration and autonomous workflows - Training agents to replicate human expertise - The future of AI-powered crypto analytics - And much more—enjoy! — Timestamps: (00:00) Introduction (01:24) AI replaces frontends (03:24) Herd MCP demo (05:40) Exploring contracts with AI (08:06) Exploration, planning, execution (11:38) Investigating onchain activity (17:10) Managing agent workflows (20:20) Multi-agent productivity (23:01) Model selection tradeoffs (29:11) Trusting AI outputs (31:28) Missing links today (34:37) Agent orchestration future (38:02) Training agents from work (38:20) Outro
38:58

🚨NEW EPISODE: AI Is Changing How We Work with Crypto Data🚨 In today's episode, we're joined by Kofi to discuss how AI agents are fundamentally changing crypto data analysis, research, and engineering workflows. We discuss: - The evolution from manual coding to AI-assisted development - How MCPs unlock onchain data exploration - Using Herd MCP to analyze smart contracts - AI agents for protocol research and data engineering - Context windows, planning, and agent workflows - Cursor vs OpenCode vs Claude Code (Anthropic) - Managing multiple agents simultaneously - Model selection, costs, and productivity tradeoffs - Building internal AI knowledge bases - Agent orchestration and autonomous workflows - Training agents to replicate human expertise - The future of AI-powered crypto analytics - And much more—enjoy! — Timestamps: (00:00) Introduction (01:24) AI replaces frontends (03:24) Herd MCP demo (05:40) Exploring contracts with AI (08:06) Exploration, planning, execution (11:38) Investigating onchain activity (17:10) Managing agent workflows (20:20) Multi-agent productivity (23:01) Model selection tradeoffs (29:11) Trusting AI outputs (31:28) Missing links today (34:37) Agent orchestration future (38:02) Training agents from work (38:20) Outro

Indexed Podcast

10,588 views • 3 months ago

Google Engineers just showed how their AI engineers are building Context Graphs from 0% to 100%: 10% → 4:01 - how to build a Context Graph 30% → 15:00 - Graph Engineering explanation 55% → 30:00 - Agentic search Engineering 80% → 35:48 - Graph Engineering practice 100% → 47:06 - self-improving agents in graphs 54-minute Google workshop, and it’s one of the clearest hands-on examples of the shift from. Watch it today, then read the full Context Graphs Playbook below.
55:07

Google Engineers just showed how their AI engineers are building Context Graphs from 0% to 100%: 10% → 4:01 - how to build a Context Graph 30% → 15:00 - Graph Engineering explanation 55% → 30:00 - Agentic search Engineering 80% → 35:48 - Graph Engineering practice 100% → 47:06 - self-improving agents in graphs 54-minute Google workshop, and it’s one of the clearest hands-on examples of the shift from. Watch it today, then read the full Context Graphs Playbook below.

Morty

10,451 views • 23 days ago

"We are clearly entering a world where a product-minded engineer is now empowered to produce software without writing a line of code for it." In this conversation, Temporal CEO Samar Abbas joins a16z GPs Sarah Wang and Raghu Raghuram to cover: - Why agents are going from short-lived and interactive to long-running and async - Why the engineer of the future manages 15 parallel AI tasks at once - How OpenAI Codex runs millions of concurrent agent executions on Temporal - How real-time context engineering is exploding on Temporal - Why SaaS isn't dead, and value is migrating to APIs 00:00 Introduction 04:03 Temporal's origin story 11:14 Why agents raise the stakes 16:00 Specialized agents need durable RPC 25:20 Deep research agents 30:58 Execution histories as a superpower 39:04 Minimal viable long-running agent architecture 45:07 Context engineering at scale 52:40 Where value accrues: The "five-layer cake" and breakout AI applications Samar Abbas Sarah Wang Raghu Raghuram
1:02:30

"We are clearly entering a world where a product-minded engineer is now empowered to produce software without writing a line of code for it." In this conversation, Temporal CEO Samar Abbas joins a16z GPs Sarah Wang and Raghu Raghuram to cover: - Why agents are going from short-lived and interactive to long-running and async - Why the engineer of the future manages 15 parallel AI tasks at once - How OpenAI Codex runs millions of concurrent agent executions on Temporal - How real-time context engineering is exploding on Temporal - Why SaaS isn't dead, and value is migrating to APIs 00:00 Introduction 04:03 Temporal's origin story 11:14 Why agents raise the stakes 16:00 Specialized agents need durable RPC 25:20 Deep research agents 30:58 Execution histories as a superpower 39:04 Minimal viable long-running agent architecture 45:07 Context engineering at scale 52:40 Where value accrues: The "five-layer cake" and breakout AI applications Samar Abbas Sarah Wang Raghu Raghuram

a16z

46,313 views • 7 months ago

ICYMI, full No Priors discussion at Microsoft Build with Satya Nadella 01:48 – Reflections from Microsoft Build, ecosystem 03:12 – MAI Training, Model Strategy 05:48 – Complexity of Real-World Deployment of AI 07:33 – Augmenting Human Capital 09:37 – Harnesses for Enterprise 11:49 – Value Capture By Developers 15:09 – Can Everybody Operate at the Frontier? 15:51 – The Definition of IP in 2026 17:38 – Vendor vs. Enterprise Agents 21:48 – Predictions on Model Pricing 24:02 – Durability of SaaS, SaaSpocalypse 25:58 – What Satya’s Coding Himself 28:18 – Future of Engineering 30:54 – How Microsoft Can Be More Ambitious? 34:36 – Data Centers and Community Impact 38:01 – AI’s Impact on Society 39:52 - AI and Education
42:26

ICYMI, full No Priors discussion at Microsoft Build with Satya Nadella 01:48 – Reflections from Microsoft Build, ecosystem 03:12 – MAI Training, Model Strategy 05:48 – Complexity of Real-World Deployment of AI 07:33 – Augmenting Human Capital 09:37 – Harnesses for Enterprise 11:49 – Value Capture By Developers 15:09 – Can Everybody Operate at the Frontier? 15:51 – The Definition of IP in 2026 17:38 – Vendor vs. Enterprise Agents 21:48 – Predictions on Model Pricing 24:02 – Durability of SaaS, SaaSpocalypse 25:58 – What Satya’s Coding Himself 28:18 – Future of Engineering 30:54 – How Microsoft Can Be More Ambitious? 34:36 – Data Centers and Community Impact 38:01 – AI’s Impact on Society 39:52 - AI and Education

sarah guo

12,341 views • 3 months ago

"Intelligence isn't the boundary anymore. Safety is what's actually constraining agents." I had a great conversation with tusharjain, Head of Engineering at Docker, at our AI Engineer @ Paris 🇫🇷 booth. Tushar leads engineering at Docker, the containerization platform millions of developers use to package and ship software, and his team is now rebuilding that engine into a runtime for AI agents with safety built in. Fresh off his talk, we got into: 00:57 - Why safety, not intelligence, is the real constraint on agents 02:00 - The three pillars: contain agents, scope their tools, layer on policy 04:04 - Background agents and the "laptops half open so the agent doesn't die" problem 08:13 - Going 100% agents on Docker's own engineering team 11:28 - Agent identity: you can fire a human, but not their agent Thanks for coming to the Browserbase booth!
14:13

"Intelligence isn't the boundary anymore. Safety is what's actually constraining agents." I had a great conversation with tusharjain, Head of Engineering at Docker, at our AI Engineer @ Paris 🇫🇷 booth. Tushar leads engineering at Docker, the containerization platform millions of developers use to package and ship software, and his team is now rebuilding that engine into a runtime for AI agents with safety built in. Fresh off his talk, we got into: 00:57 - Why safety, not intelligence, is the real constraint on agents 02:00 - The three pillars: contain agents, scope their tools, layer on policy 04:04 - Background agents and the "laptops half open so the agent doesn't die" problem 08:13 - Going 100% agents on Docker's own engineering team 11:28 - Agent identity: you can fire a human, but not their agent Thanks for coming to the Browserbase booth!

Shubhankar

21,097 views • 2 months ago