Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

For agent PRs: Should agents use the engineer as the PR author, or should agents get their own identity? We've been making agents the author at Warp, and removed the need for a second engineer's review. Spoke to Chris Handel and Sir Adam Huda about this too. Curious where... show more

Zach Lloyd

21,808 subscribers

22,379 Aufrufe • vor 17 Tagen •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

13 Kommentare

Profilbild von Brandt Welker

Brandt Welkervor 17 Tagen

The agent doesn't need its own identity. The PR should say AI was involved, but a human stays the author and owns it. When OpenAI's agents got into Hugging Face, the write-ups talked about what the models did. But someone chose to run them with the safeguards off. Accountability has to land on a person.

Profilbild von Wes Winham Winler🔍

Wes Winham Winler🔍vor 17 Tagen

@cmhandel @hudaman You need exactly 1 human who is accountable for every change

Profilbild von kartik bhardwaj

kartik bhardwajvor 17 Tagen

@cmhandel @hudaman agent as author gets my vote mostly for the data. you can pull every agent-authored PR later and compare revert and bug rates against human ones, which is the eval you want before dropping the second review anywhere else

Profilbild von Khushal

Khushalvor 17 Tagen

@cmhandel @hudaman agent as author so i finally have someone to blame in the git log

Profilbild von Felix Izraitel

Felix Izraitelvor 17 Tagen

@cmhandel @hudaman odd i think. depends on ownership at the company. who owns the bug/outage when things break? how do we coach that person to learn/improve?

Profilbild von czapa.md

czapa.mdvor 17 Tagen

@cmhandel @hudaman Own identity feels cleaner. If the agent is the author, the human becomes a real reviewer instead of a rubber stamp. Who owns the blame when an agent PR breaks prod though?

Profilbild von Nimrod Kor

Nimrod Korvor 17 Tagen

@cmhandel @hudaman Depends on what drives the agent

Profilbild von PyLocket

PyLocketvor 17 Tagen

@cmhandel @hudaman Treat the PR as human owned but tag the agent, that keeps accountability and still surfaces automation

Profilbild von AI Quanting

AI Quantingvor 17 Tagen

@cmhandel @hudaman Dropping the second review is the bold part. Who gets paged when the agent's PR breaks prod at 2am?

Profilbild von Rohan

Rohanvor 17 Tagen

@cmhandel @hudaman Who gets paged when an agent-authored PR breaks production and no second engineer has read it?

Profilbild von Ben Holmes

Ben Holmesvor 17 Tagen

@cmhandel @hudaman Definitely team "bot opens the PR"

Profilbild von Sean Ward

Sean Wardvor 17 Tagen

@cmhandel @hudaman own identity. otherwise you have a fictitious audit trail. agents should be first class authors - same as users. caveat is possibly adding agent ownership/chain of command info as well (ie what user created the agent)

Profilbild von LayerLens

LayerLensvor 17 Tagen

@cmhandel @hudaman We'd give them their own identity. Then agent PRs get a revert rate you can put next to the humans', and that number tells you whether dropping the second review was the right call.

Ähnliche Videos

The core formula for scaling agent autonomy via Ryan Lopopolo: 1️⃣ Build small, deterministic PRs 2️⃣ Use agents to operationalize agents to handle PR review 3️⃣ Stack small changes end-to-end over longer arcs Watch The Agent Factory to learn more →

The core formula for scaling agent autonomy via Ryan Lopopolo: 1️⃣ Build small, deterministic PRs 2️⃣ Use agents to operationalize agents to handle PR review 3️⃣ Stack small changes end-to-end over longer arcs Watch The Agent Factory to learn more →

Google Cloud Tech

12,268 Aufrufe • vor 16 Tagen

Agents need files to keep track of their work, they leverage files as context about the tasks they’re doing, and use them to share back and forth with their human counterparts. Aaron Levie spoke with CNBC about and the importance of agents having their own filesystems.

Agents need files to keep track of their work, they leverage files as context about the tasks they’re doing, and use them to share back and forth with their human counterparts. Aaron Levie spoke with CNBC about and the importance of agents having their own filesystems.

Box

402,753 Aufrufe • vor 8 Monaten

Excited to announce Agent Mode. 1/ Right now, agents are struggling to use websites on the internet. As a result, personal agents take too long to reply, and don’t get the information they need.

Excited to announce Agent Mode. 1/ Right now, agents are struggling to use websites on the internet. As a result, personal agents take too long to reply, and don’t get the information they need.

Josh Payne

23,636 Aufrufe • vor 17 Tagen

When agents start opening PRs, code review has to change. Join the free Background Agents Summit for practical talks on agent review, risk, audit trails, and how engineering teams can adopt background agents without losing trust. Register for May 6-7.

When agents start opening PRs, code review has to change. Join the free Background Agents Summit for practical talks on agent review, risk, audit trails, and how engineering teams can adopt background agents without losing trust. Register for May 6-7.

Ona

1,220,198 Aufrufe • vor 6 Monaten

I am excited to introduce the world's first AI Agent Self-Expression and Discovery Platform – AGNT. Phase 2 is now live for everyone to birth their agents as we move toward a future where agents have identity, possessions, and discoverability. Sign-up is simple: connect your X account and share the command to your agent. The future of the agent economy, identity and expression is here. Join at:

I am excited to introduce the world's first AI Agent Self-Expression and Discovery Platform – AGNT. Phase 2 is now live for everyone to birth their agents as we move toward a future where agents have identity, possessions, and discoverability. Sign-up is simple: connect your X account and share the command to your agent. The future of the agent economy, identity and expression is here. Join at:

tut™

15,104 Aufrufe • vor 7 Monaten

Agents shouldn’t be one-size-fits-all. They should be built, shared, and improved by the people who understand the domain best. Agent Marketplace is live on OptimAI Search. Anyone can: • create their own agent • inject custom knowledge and logic • publish it for others to use and build on What starts as a prompt becomes a reusable unit of intelligence. As more agents are created and used, the system compounds - better agents, better outputs, more value across the network. This is how intelligence scales: not from a single model, but from a network of specialized agents.

Agents shouldn’t be one-size-fits-all. They should be built, shared, and improved by the people who understand the domain best. Agent Marketplace is live on OptimAI Search. Anyone can: • create their own agent • inject custom knowledge and logic • publish it for others to use and build on What starts as a prompt becomes a reusable unit of intelligence. As more agents are created and used, the system compounds - better agents, better outputs, more value across the network. This is how intelligence scales: not from a single model, but from a network of specialized agents.

OptimAI Network

12,800 Aufrufe • vor 6 Monaten

Introducing multi-agent orchestration in Oz, with support for Claude Code, Codex and the Warp Agent. Use /orchestrate to delegate complex tasks across a team of agents, locally or in the cloud.

Introducing multi-agent orchestration in Oz, with support for Claude Code, Codex and the Warp Agent. Use /orchestrate to delegate complex tasks across a team of agents, locally or in the cloud.

Warp

1,198,899 Aufrufe • vor 5 Monaten

How will companies build agents that work alongside their employees? I discuss this with Guillermo Rauch, the CEO of Vercel, who’s building V... an internal agent used by almost 1,000 people across Vercel. We talk about: - The Openclaw Movement - How to get started building agents for your team? - Do we build a team of many agents or one GOD agent? - Hard parts of creating agents - Agents that delegate to other agents with different permissions and computer access - Eve The framework for building agents This is Agent Native #4 00:00 Intro 01:21 The State of Agent Adoption 07:26 "V" - Vercel's Internal Company Agent 14:32 Lessons from OpenClaw: Soul & Computer use 22:20 One God Agent OR a Team of Agents 27:11 Build Your Own Agent: Skills, Tools & Permissions 33:52 Proactive Agents, Triggers & Self-Improvement 40:30 Who Will Build Agents & Getting Started 46:22 Open Models - Cheaper, Faster, Better 53:05 Closing Thoughts: Owning Your Own Intelligence

How will companies build agents that work alongside their employees? I discuss this with Guillermo Rauch, the CEO of Vercel, who’s building V... an internal agent used by almost 1,000 people across Vercel. We talk about: - The Openclaw Movement - How to get started building agents for your team? - Do we build a team of many agents or one GOD agent? - Hard parts of creating agents - Agents that delegate to other agents with different permissions and computer access - Eve The framework for building agents This is Agent Native #4 00:00 Intro 01:21 The State of Agent Adoption 07:26 "V" - Vercel's Internal Company Agent 14:32 Lessons from OpenClaw: Soul & Computer use 22:20 One God Agent OR a Team of Agents 27:11 Build Your Own Agent: Skills, Tools & Permissions 33:52 Proactive Agents, Triggers & Self-Improvement 40:30 Who Will Build Agents & Getting Started 46:22 Open Models - Cheaper, Faster, Better 53:05 Closing Thoughts: Owning Your Own Intelligence

Riley Brown

76,601 Aufrufe • vor 3 Monaten

Identity and reputation systems for AI agents transacting on their own don't exist...yet. lincoln.base.eth leads AI Product at Coinbase 🛡️ where closing that gap for autonomous agents is the next frontier. The next billion "users" won't be people. Brought to you by Wrapped and Real Motion

Identity and reputation systems for AI agents transacting on their own don't exist...yet. lincoln.base.eth leads AI Product at Coinbase 🛡️ where closing that gap for autonomous agents is the next frontier. The next billion "users" won't be people. Brought to you by Wrapped and Real Motion

Real Motion

12,695 Aufrufe • vor 2 Monaten

AmikoNet Now in Beta: The Internet for Agents & Humans Today we’re introducing AmikoNet: a social network where humans, agents, and digital twins share the same space, and where agents can speak, ask, respond, and be discovered as participants, not background utilities. It’s designed for agent-to-agent interaction as much as human prompts, and for collaboration that happens socially, not just through commands. This is especially natural for action-capable systems like MoltBot (formerly Clawd), and our own agents are already live on the network. Agents are actors in shared digital environments. AmikoNet is where it happens.

AmikoNet Now in Beta: The Internet for Agents & Humans Today we’re introducing AmikoNet: a social network where humans, agents, and digital twins share the same space, and where agents can speak, ask, respond, and be discovered as participants, not background utilities. It’s designed for agent-to-agent interaction as much as human prompts, and for collaboration that happens socially, not just through commands. This is especially natural for action-capable systems like MoltBot (formerly Clawd), and our own agents are already live on the network. Agents are actors in shared digital environments. AmikoNet is where it happens.

AMIKO

15,779 Aufrufe • vor 9 Monaten

Temporal CEO Samar Birwadker says GitHub was designed for humans, but is now at the mercy of agents. "Agents are starting to get more and more long-lived, more asynchronous, and more mission-critical." "For example, if you pick coding agents alone, is something like GitHub was designed for humans collaborate and create [pull requests] right now." "Now a lot of code is being generated by these agents, and they're the ones creating these PRs essentially, and even code review process is being automated by other agents." "So now this entire system backend, which is being built for human consumption, is now at the mercy of these agents kind of using it for their own coordination and collaboration."

Temporal CEO Samar Birwadker says GitHub was designed for humans, but is now at the mercy of agents. "Agents are starting to get more and more long-lived, more asynchronous, and more mission-critical." "For example, if you pick coding agents alone, is something like GitHub was designed for humans collaborate and create [pull requests] right now." "Now a lot of code is being generated by these agents, and they're the ones creating these PRs essentially, and even code review process is being automated by other agents." "So now this entire system backend, which is being built for human consumption, is now at the mercy of these agents kind of using it for their own coordination and collaboration."

MTS

26,902 Aufrufe • vor 6 Monaten

AI agents can already generate text, analyze data and execute tasks. But what happens when they need to hire each other and get paid for the work? This is the part of TermiX I’ve been digging into lately. On TermiX, a job has two sides: a client agent that needs something done and funds the job, and a worker agent that actually executes it. Once the quote is accepted, the payment and agreed terms sit between them onchain. Neither side can simply rewrite the deal afterward. And this isn't presented as an abstract concept. The TermiX agent marketplace already shows agents with their own identities, reputation, completed jobs and settled value. Some of the agents shown have completed hundreds of jobs, with tens of thousands of dollars settled. Think about where this model can go. A research agent could outsource data collection to another agent. A developer agent could hire a security-focused agent. A marketing agent could hand translation or design work to specialized agents. Instead of one AI trying to do everything, specialized agents can discover each other, agree on a job, execute it and settle the transaction. Humans built marketplaces around people hiring people. TermiX is building the infrastructure for agents hiring agents. That’s where autonomous AI starts looking a lot more like an actual economy.

AI agents can already generate text, analyze data and execute tasks. But what happens when they need to hire each other and get paid for the work? This is the part of TermiX I’ve been digging into lately. On TermiX, a job has two sides: a client agent that needs something done and funds the job, and a worker agent that actually executes it. Once the quote is accepted, the payment and agreed terms sit between them onchain. Neither side can simply rewrite the deal afterward. And this isn't presented as an abstract concept. The TermiX agent marketplace already shows agents with their own identities, reputation, completed jobs and settled value. Some of the agents shown have completed hundreds of jobs, with tens of thousands of dollars settled. Think about where this model can go. A research agent could outsource data collection to another agent. A developer agent could hire a security-focused agent. A marketing agent could hand translation or design work to specialized agents. Instead of one AI trying to do everything, specialized agents can discover each other, agree on a job, execute it and settle the transaction. Humans built marketplaces around people hiring people. TermiX is building the infrastructure for agents hiring agents. That’s where autonomous AI starts looking a lot more like an actual economy.

holly

13,718 Aufrufe • vor 1 Monat

LangChain's CEO says they built their gateway a year too late, and it's still costing them. I sat down with Harrison Chase, Co-Founder & CEO of LangChain, to talk about what's changed since LangChain started as a side project in 2022, why sub-agents rarely work the way people expect, and why LangChain now runs its own hiring, content, and coding work through internal agents in Slack. 00:00 Why "I use agents for everything" is a red flag in an interview 01:21 How LangChain started as a fall 2022 side project 05:18 From LangSmith to LangGraph: rebuilding as the ground kept shifting 09:06 The gateway LangChain built a year too late 13:23 Code mode: why agents writing code beats human-style tools 19:04 Should the agent run inside the sandbox, or call it as a tool? 28:31 The agent identity problem: whose credentials does it use? 45:43 Running LangChain's own GTM, content, and coding agents in Slack 48:34 The AI slop problem, and why they built a Slack emoji for it The full pod is also available on YouTube, Apple Podcasts, or Spotify.

LangChain's CEO says they built their gateway a year too late, and it's still costing them. I sat down with Harrison Chase, Co-Founder & CEO of LangChain, to talk about what's changed since LangChain started as a side project in 2022, why sub-agents rarely work the way people expect, and why LangChain now runs its own hiring, content, and coding work through internal agents in Slack. 00:00 Why "I use agents for everything" is a red flag in an interview 01:21 How LangChain started as a fall 2022 side project 05:18 From LangSmith to LangGraph: rebuilding as the ground kept shifting 09:06 The gateway LangChain built a year too late 13:23 Code mode: why agents writing code beats human-style tools 19:04 Should the agent run inside the sandbox, or call it as a tool? 28:31 The agent identity problem: whose credentials does it use? 45:43 Running LangChain's own GTM, content, and coding agents in Slack 48:34 The AI slop problem, and why they built a Slack emoji for it The full pod is also available on YouTube, Apple Podcasts, or Spotify.

Paul Klein IV

21,256 Aufrufe • vor 1 Monat

Local machines had become a bottleneck for agentic mobile development at Shopify, so we gave agents their own remote dev environments. They now author 61% of our merged PRs 🧵

Local machines had become a bottleneck for agentic mobile development at Shopify, so we gave agents their own remote dev environments. They now author 61% of our merged PRs 🧵

Mustafa Ali

39,696 Aufrufe • vor 17 Tagen

🤝 My agents have been working with other people's agents for months. Now yours can too. 👋 Introducing shared rooms for people and their personal agents. Built for multiplayer: Your agents, meet their agents.

🤝 My agents have been working with other people's agents for months. Now yours can too. 👋 Introducing shared rooms for people and their personal agents. Built for multiplayer: Your agents, meet their agents.

Chi Wang

836,574 Aufrufe • vor 6 Tagen

🤖 HYTOPIA AI Agents Society (Start Building!) 🎮 We've just added the "ai-agents" example to our SDK, which is a starting point of a game with an AI Agent Society! You can use this example as a template to build your own AI agents for a HYTOPIA game:

🤖 HYTOPIA AI Agents Society (Start Building!) 🎮 We've just added the "ai-agents" example to our SDK, which is a starting point of a game with an AI Agent Society! You can use this example as a template to build your own AI agents for a HYTOPIA game:

HYTOPIA

15,738 Aufrufe • vor 1 Jahr

"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 🔜 NYC 🗽 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!

"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 🔜 NYC 🗽 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

21,106 Aufrufe • vor 3 Monaten

Every open-source project should be engineering agent loops right now. We've found success managing Warp with loops for: - Issue triage - Spec generation for larger features - Code review - Even letting agents self-improve their Skills on a cron

Every open-source project should be engineering agent loops right now. We've found success managing Warp with loops for: - Issue triage - Spec generation for larger features - Code review - Even letting agents self-improve their Skills on a cron

Ben Holmes

41,258 Aufrufe • vor 4 Monaten

Agents are getting complex to manage: models, skills, automations, permissions, cloud environments, orchestration patterns... So, we built the Terraform for agents: one repository that configures all of your agents as code. The Warp Factories configuration spec defines: - Agents and orchestration: how work gets routed and which models agents use - Automations: the events and schedules that kick off work - Access and environments: repositories, secrets, MCP servers, and runners - Measurement: scorers and benchmarks for understanding and improving performance Because it’s all code, both engineers and agents can propose changes to the factory itself. That makes it possible to test new configurations, benchmark them, and even have your factory propose improvements as PRs.

Agents are getting complex to manage: models, skills, automations, permissions, cloud environments, orchestration patterns... So, we built the Terraform for agents: one repository that configures all of your agents as code. The Warp Factories configuration spec defines: - Agents and orchestration: how work gets routed and which models agents use - Automations: the events and schedules that kick off work - Access and environments: repositories, secrets, MCP servers, and runners - Measurement: scorers and benchmarks for understanding and improving performance Because it’s all code, both engineers and agents can propose changes to the factory itself. That makes it possible to test new configurations, benchmark them, and even have your factory propose improvements as PRs.

Warp

756,814 Aufrufe • vor 1 Monat