正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

SuperGrok 4.2 is now available Basic features are free, while advanced agent modes and Heavy variants require SuperGrok or Premium+ subscriptions. If subscribed, test Agent Mode by starting prompts with specific task instructions.

Mario Nawfal

3,149,378 subscribers

36,148 次观看 • 7 个月前 •via X (Twitter)

新闻政治科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

✨ Advanced Visual Intelligence Agent! Nano Banana PRO is an AI-powered visual generation agent available on Agent Forge. Using supported third-party AI models and image-processing tools, it enables users to generate images from text-based prompts for creative exploration, drafts, prototypes, and visual experimentation. Whether you’re working on early design concepts, artistic ideas, or automated content workflows, Nano Banana PRO helps streamline the process by converting written prompts into visual outputs within the Agent Forge environment. 🔗

✨ Advanced Visual Intelligence Agent! Nano Banana PRO is an AI-powered visual generation agent available on Agent Forge. Using supported third-party AI models and image-processing tools, it enables users to generate images from text-based prompts for creative exploration, drafts, prototypes, and visual experimentation. Whether you’re working on early design concepts, artistic ideas, or automated content workflows, Nano Banana PRO helps streamline the process by converting written prompts into visual outputs within the Agent Forge environment. 🔗

AITECH CLOUD NETWORK

62,330 次观看 • 9 个月前

Using this new agent in ClickUp you can totally leapfrog the IDE, Cursor, Claude Code... Codegen is now available in ClickUp. "Hey Codegen, fix this bug" - me "PR submitted & ready for review!" - Codegen "Sweet, ship it" - me We've always believed that the future of AI value will be realized in horizontal software - today is a huge realization of this vision. Real example: This week our customer support reps started fixing features in real time. Product managers are now prototyping features themselves. You can mention Codegen or assign a task, and all of the optimized context is passed to the Agent to solve bugs and ship improvements with one shot. Available for everyone today.

Using this new agent in ClickUp you can totally leapfrog the IDE, Cursor, Claude Code... Codegen is now available in ClickUp. "Hey Codegen, fix this bug" - me "PR submitted & ready for review!" - Codegen "Sweet, ship it" - me We've always believed that the future of AI value will be realized in horizontal software - today is a huge realization of this vision. Real example: This week our customer support reps started fixing features in real time. Product managers are now prototyping features themselves. You can mention Codegen or assign a task, and all of the optimized context is passed to the Agent to solve bugs and ship improvements with one shot. Available for everyone today.

Zeb Evans

11,706 次观看 • 11 个月前

Alright, now that we know *what* an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.

Alright, now that we know what an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.

Google AI

22,487 次观看 • 10 个月前

My C++ 3DGS implementation has transitioned to the gsplat backend and is now licensed under Apache 2.0. - Supports MCMC densification by default. - Includes a fused bilateral grid implementation. - A basic viewer, contributed by the community, is available with more features in development. - Runs in headless mode. Exciting plans are underway for the project's evolution over the sumner. Check it out!

My C++ 3DGS implementation has transitioned to the gsplat backend and is now licensed under Apache 2.0. - Supports MCMC densification by default. - Includes a fused bilateral grid implementation. - A basic viewer, contributed by the community, is available with more features in development. - Runs in headless mode. Exciting plans are underway for the project's evolution over the sumner. Check it out!

MrNeRF

59,972 次观看 • 1 年前

Vibe coding apps that require you to store and manage large files just got easier, with Replit ⠕ App Storage. ✨ My favorite example in this category are any PDF analysis apps: create a fully customized AI synthesizer in just a few prompts. App Storage is Replit's Object Storage solution (like Amazon S3 or Google CS). But don't worry if those words sound foreign to you, Agent will set this up for you automatically if your app needs it. On that note, this Agent capability is just the beginning of our efforts to make building apps with databases and storage easier: 👇

Vibe coding apps that require you to store and manage large files just got easier, with Replit ⠕ App Storage. ✨ My favorite example in this category are any PDF analysis apps: create a fully customized AI synthesizer in just a few prompts. App Storage is Replit's Object Storage solution (like Amazon S3 or Google CS). But don't worry if those words sound foreign to you, Agent will set this up for you automatically if your app needs it. On that note, this Agent capability is just the beginning of our efforts to make building apps with databases and storage easier: 👇

vic

27,313 次观看 • 1 年前

THIS DEVELOPER USED OPENCLAW AGENTS TO RUN HIS B2B BUSINESS VIA TELEGRAM AND MADE $15,000/MONTH he doesn't write prompts from scratch or use generic browser interfaces. he runs a multi-agent framework through a mobile chat. the agents write code, test deployments, and update sites in real-time while he just hits approve the setup is straightforward: - spin up Coolify on a free cloud instance to host your own self-hosted agent panels - link the agent loop to a Telegram gateway to approve code edits from your phone - deploy specialized skill files directly to limit token waste and context decay - containerize the terminal execution using Docker to prevent security breaches if you are still running local agents without container safety, you are leaving money on the table. read the 30-day battle between OpenClaw and Hermes Agent to see who actually wins in production Full breakdown and migration playbook ↓

THIS DEVELOPER USED OPENCLAW AGENTS TO RUN HIS B2B BUSINESS VIA TELEGRAM AND MADE $15,000/MONTH he doesn't write prompts from scratch or use generic browser interfaces. he runs a multi-agent framework through a mobile chat. the agents write code, test deployments, and update sites in real-time while he just hits approve the setup is straightforward: - spin up Coolify on a free cloud instance to host your own self-hosted agent panels - link the agent loop to a Telegram gateway to approve code edits from your phone - deploy specialized skill files directly to limit token waste and context decay - containerize the terminal execution using Docker to prevent security breaches if you are still running local agents without container safety, you are leaving money on the table. read the 30-day battle between OpenClaw and Hermes Agent to see who actually wins in production Full breakdown and migration playbook ↓

marfin

26,654 次观看 • 3 个月前

Anthropic has introduced an update to Claude Managed Agents, releasing several powerful new features designed to improve agentic workflows and autonomy. 🔹Dreaming (Research Preview): Agents can now "dream" by reviewing past sessions during idle time. This process extracts patterns, spots recurring mistakes, and curates memories so the agent continually learns and improves over time without human intervention. 🔹Outcomes (Public Beta): This feature allows developers to set a specific quality bar by writing a rubric. A separate grader agent then evaluates the output, forcing the primary agent to iterate on the work until it meets the defined success criteria. 🔹Multiagent Orchestration (Public Beta): A lead agent can now break down complex jobs and delegate specific tasks to specialized sub-agents, which work in parallel to execute the broader objective. 🔹Webhooks (Public Beta): Users can subscribe to webhooks to receive automatic notifications the moment an agentic task is completed.

Anthropic has introduced an update to Claude Managed Agents, releasing several powerful new features designed to improve agentic workflows and autonomy. 🔹Dreaming (Research Preview): Agents can now "dream" by reviewing past sessions during idle time. This process extracts patterns, spots recurring mistakes, and curates memories so the agent continually learns and improves over time without human intervention. 🔹Outcomes (Public Beta): This feature allows developers to set a specific quality bar by writing a rubric. A separate grader agent then evaluates the output, forcing the primary agent to iterate on the work until it meets the defined success criteria. 🔹Multiagent Orchestration (Public Beta): A lead agent can now break down complex jobs and delegate specific tasks to specialized sub-agents, which work in parallel to execute the broader objective. 🔹Webhooks (Public Beta): Users can subscribe to webhooks to receive automatic notifications the moment an agentic task is completed.

Wes Roth

53,266 次观看 • 4 个月前

🆕 Need for Speed: The Run - Fusion Fix is now available! 3,000 miles. San Francisco to New York. Now with a new camera mode! 🔗 Download: • 🔧 Features: • Skip intro - bypass startup FMVs and login prompts for faster loading • Improved windowed mode - borderless, resized to match your selected resolution ✨ Optional: • Unlock all cars in the garage • Unlock all challenge content • Unlock everything in the game 🎥 Free-look camera with mouse & right stick support - adjustable sensitivity, reset timeout, return speed, axis inversion. Press LS + RS to toggle between the original free look and the new camera.

🆕 Need for Speed: The Run - Fusion Fix is now available! 3,000 miles. San Francisco to New York. Now with a new camera mode! 🔗 Download: • 🔧 Features: • Skip intro - bypass startup FMVs and login prompts for faster loading • Improved windowed mode - borderless, resized to match your selected resolution ✨ Optional: • Unlock all cars in the garage • Unlock all challenge content • Unlock everything in the game 🎥 Free-look camera with mouse & right stick support - adjustable sensitivity, reset timeout, return speed, axis inversion. Press LS + RS to toggle between the original free look and the new camera.

Fusion Fix

103,060 次观看 • 5 个月前

Now Live - Get almost 10% on staked Sol with our Stake Agent Looks at 5 staking protocols and gives you the best return! We plan on bringing more features and agents to Solana in the near term! Let us know what you want us to integrate next! We are thinking Kamino or Drift - Official but let us know if you'd like to have something else

Now Live - Get almost 10% on staked Sol with our Stake Agent Looks at 5 staking protocols and gives you the best return! We plan on bringing more features and agents to Solana in the near term! Let us know what you want us to integrate next! We are thinking Kamino or Drift - Official but let us know if you'd like to have something else

Orbit

18,738 次观看 • 1 年前

Introducing the BIOS API: Turn Your Agent Into a Research Scientist Built to: 🦞 Add biomedical workflows to your OpenClaw🦞 agent 🧠 Create research or health agents w/ on-demand scientific intelligence 🧪 Pay per query via x402 on Base Any agent or app can now tap into the BIOS AI Scientist, plugging BIOS into the broader agent economy. What is BIOS? BIOS is an AI Scientist designed to handle complex biomedical research by orchestrating specialized scientific subagents. Ranked #1 on the leading bioinformatics benchmark, BIOS is already being used by 1,000+ researchers and labs to build new drugs and medicines. An Agentic Economy for Science AI agents have proven they can form multi-billion dollar ecosystems. BIOS applies the same primitives to drug discovery pipelines and health. Instead of coding bots and personal AI assistants, think research agent swarms running on a modern scientific stack. Imagine an OpenClaw agent built for longevity: It scans new literature daily, generates novel compound hypotheses through BIOS, designs validation workflows, and routes the best candidates to wet-lab funding - all programmatically. Connect it with an agent for microbiome health, enabling agent “backrooms” that autonomously surface cross-disciplinary insights. Micropayments for Scientific Work via x402 Each query triggers payment routing to BIOS and whichever subagents contribute to a response. The best agents earn. Usage settles instantly across contributing sources. The goal is pay-per-task science: paying for a CRISPR assay result, licensing a genomic dataset, or triggering a clinical data query - all settled in seconds via USDC. No purchase orders. No grant bureaucracy. No middlemen. x402 is the payment rail that makes agent-to-lab commerce possible - letting capital and cognition route themselves to the highest-signal science. What Will You Build? Drug discovery copilots? Longevity scouts? Automated literature monitors? Scientific due diligence agents? We’ll soon share the first implementations of the BIOS API. Stay tuned and see below for instructions on generating an API key for your agent or use-case.

Introducing the BIOS API: Turn Your Agent Into a Research Scientist Built to: 🦞 Add biomedical workflows to your OpenClaw🦞 agent 🧠 Create research or health agents w/ on-demand scientific intelligence 🧪 Pay per query via x402 on Base Any agent or app can now tap into the BIOS AI Scientist, plugging BIOS into the broader agent economy. What is BIOS? BIOS is an AI Scientist designed to handle complex biomedical research by orchestrating specialized scientific subagents. Ranked #1 on the leading bioinformatics benchmark, BIOS is already being used by 1,000+ researchers and labs to build new drugs and medicines. An Agentic Economy for Science AI agents have proven they can form multi-billion dollar ecosystems. BIOS applies the same primitives to drug discovery pipelines and health. Instead of coding bots and personal AI assistants, think research agent swarms running on a modern scientific stack. Imagine an OpenClaw agent built for longevity: It scans new literature daily, generates novel compound hypotheses through BIOS, designs validation workflows, and routes the best candidates to wet-lab funding - all programmatically. Connect it with an agent for microbiome health, enabling agent “backrooms” that autonomously surface cross-disciplinary insights. Micropayments for Scientific Work via x402 Each query triggers payment routing to BIOS and whichever subagents contribute to a response. The best agents earn. Usage settles instantly across contributing sources. The goal is pay-per-task science: paying for a CRISPR assay result, licensing a genomic dataset, or triggering a clinical data query - all settled in seconds via USDC. No purchase orders. No grant bureaucracy. No middlemen. x402 is the payment rail that makes agent-to-lab commerce possible - letting capital and cognition route themselves to the highest-signal science. What Will You Build? Drug discovery copilots? Longevity scouts? Automated literature monitors? Scientific due diligence agents? We’ll soon share the first implementations of the BIOS API. Stay tuned and see below for instructions on generating an API key for your agent or use-case.

Bio Protocol

25,957 次观看 • 7 个月前

We had a driver this week in a litigation case lose their load because they didn't know straps werent the same WLL as graded chain. Not all drivers are created equal. A CDL is not a CDL is not a CDL. We’ve got plenty of dock-bumper drivers for basic freight. The real shortage is trained, mechanically inclined, mode-specific operators. Dry van is not open deck. Open deck is not tank. Tank is not hazmat. Hazmat is not heavy haul. When fleets add specialized modes and start sliding basic freight drivers into them without real training, securement knowledge, mechanical sense, or understanding of the exposure, that is where failure starts. The truck may look similar. The work is not.

We had a driver this week in a litigation case lose their load because they didn't know straps werent the same WLL as graded chain. Not all drivers are created equal. A CDL is not a CDL is not a CDL. We’ve got plenty of dock-bumper drivers for basic freight. The real shortage is trained, mechanically inclined, mode-specific operators. Dry van is not open deck. Open deck is not tank. Tank is not hazmat. Hazmat is not heavy haul. When fleets add specialized modes and start sliding basic freight drivers into them without real training, securement knowledge, mechanical sense, or understanding of the exposure, that is where failure starts. The truck may look similar. The work is not.

Rob Carpenter

663,689 次观看 • 5 个月前

Genesis Update: VVAP Now Includes ‘Vote Against’ Option veVIRTUAL holders (i.e. $VIRTUAL stakers) can now vote for or against agents to determine how 10% of the total daily point supply is distributed. This allocation is part of the veVIRTUAL Voted Agent Points (VVAP) system. How it works: • You can now cast vote on "Support" or "Against" on any active agent • Daily VVAP points are distributed based on net veVIRTUAL support (i.e., total Support - total Against) • Example: If an agent receives 100 veVIRTUAL worth of votes and 60 veVIRTUAL worth of ‘Vote Against’, its net support is 40 veVIRTUAL, and its VVAP share is calculated accordingly. This update enables the community to show support for agents they resonate with, as well as to share feedback when they feel less aligned.

Genesis Update: VVAP Now Includes ‘Vote Against’ Option veVIRTUAL holders (i.e. $VIRTUAL stakers) can now vote for or against agents to determine how 10% of the total daily point supply is distributed. This allocation is part of the veVIRTUAL Voted Agent Points (VVAP) system. How it works: • You can now cast vote on "Support" or "Against" on any active agent • Daily VVAP points are distributed based on net veVIRTUAL support (i.e., total Support - total Against) • Example: If an agent receives 100 veVIRTUAL worth of votes and 60 veVIRTUAL worth of ‘Vote Against’, its net support is 40 veVIRTUAL, and its VVAP share is calculated accordingly. This update enables the community to show support for agents they resonate with, as well as to share feedback when they feel less aligned.

Virtuals Protocol

62,327 次观看 • 1 年前

Most Web3 campaigns still pay for attention. This one pays for usage. NeoSoul is live on Action Model with a $5K pool running until September 10. The task is simple and specific: Create your first AI agent on NeoSoul. Meet the success criteria. Get verified through the Action Model browser extension. No vanity metrics. No empty follows. Just a real product action that actually matters. This is the point of ActionFi. Partners don’t buy fake engagement. They pay people to experience the product. If you already have the extension installed, you can start now. If not, you’re leaving a live campaign on the table. 👉 Have you created your first NeoSoul agent yet? #ActionModel #ActionFi #NeoSoul

Most Web3 campaigns still pay for attention. This one pays for usage. NeoSoul is live on Action Model with a $5K pool running until September 10. The task is simple and specific: Create your first AI agent on NeoSoul. Meet the success criteria. Get verified through the Action Model browser extension. No vanity metrics. No empty follows. Just a real product action that actually matters. This is the point of ActionFi. Partners don’t buy fake engagement. They pay people to experience the product. If you already have the extension installed, you can start now. If not, you’re leaving a live campaign on the table. 👉 Have you created your first NeoSoul agent yet? #ActionModel #ActionFi #NeoSoul

Trathoa

21,461 次观看 • 27 天前

this is f*cking beyond comprehension. Google engineers just shipped the entire agent lifecycle in one release: build, scale, govern. and every piece answers a specific way agents die in production > context layers (Static, Turn, User, Cache): you decide what the model carries between turns, so token spend stops being a mystery > a self heal plugin: the agent notices a tool call failed and retries it a different way instead of dying mid run > adk deploy: one command from your laptop to the managed runtime, no packaging, no infra ticket > Go joins Python and Java, with its own A2A SDK then the part nobody builds for themselves: > a dashboard on token consumption, latency, error rates and tool calls: the four things that actually kill an agent > a traces tab that opens the real sequence of actions the agent took, step by step > a playground wired to the deployed agent, past sessions included, so debugging is not a redeploy loop > an Evaluation Layer with a User Simulator, because you cannot unit test a non deterministic system and the part that decides whether it ever ships: > agents get native identities as first class IAM principals: least privilege applies to them like it does to people > Model Armor screens prompt injection, tool calls and responses, inline for Gemini or over REST > Security Command Center inventories every agentic asset and flags data exfiltration by an agent ADK is already at 7 million downloads. the runtime has a free tier, and express mode runs off a Gmail address. the prototype was never the hard part.

this is f*cking beyond comprehension. Google engineers just shipped the entire agent lifecycle in one release: build, scale, govern. and every piece answers a specific way agents die in production > context layers (Static, Turn, User, Cache): you decide what the model carries between turns, so token spend stops being a mystery > a self heal plugin: the agent notices a tool call failed and retries it a different way instead of dying mid run > adk deploy: one command from your laptop to the managed runtime, no packaging, no infra ticket > Go joins Python and Java, with its own A2A SDK then the part nobody builds for themselves: > a dashboard on token consumption, latency, error rates and tool calls: the four things that actually kill an agent > a traces tab that opens the real sequence of actions the agent took, step by step > a playground wired to the deployed agent, past sessions included, so debugging is not a redeploy loop > an Evaluation Layer with a User Simulator, because you cannot unit test a non deterministic system and the part that decides whether it ever ships: > agents get native identities as first class IAM principals: least privilege applies to them like it does to people > Model Armor screens prompt injection, tool calls and responses, inline for Gemini or over REST > Security Command Center inventories every agentic asset and flags data exfiltration by an agent ADK is already at 7 million downloads. the runtime has a free tier, and express mode runs off a Gmail address. the prototype was never the hard part.

NO1ennn

24,666 次观看 • 13 天前

Most AI video tools are stuck in a loop, you generate, change the prompt, and wait again. Vidu S2 is pushing things forward by making generation interactive. You can edit the video while it is being created. Change the style, swap the background, or switch outfits in real time. If you drop in a new image, the video adjusts instantly without awkward cuts. Under the hood, it combines real time 720P output with an AI agent that actively watches the video to plan what happens next. It allows you to change reference images on the fly, powered by a model optimized specifically for live streaming. This opens up massive possibilities. Imagine viewers controlling visual changes during a livestream, people transforming into game characters, or shoppers trying on different looks live. The entire S Series is available for a free trial right now so you can test it yourself. Use my code PANDAS2 with the link below to grab 300 bonus credits to explore the other features. Vidu Stream: 300 Bonus Credits: Vidu AI #ViduAI #ViduS #ViduS2

Most AI video tools are stuck in a loop, you generate, change the prompt, and wait again. Vidu S2 is pushing things forward by making generation interactive. You can edit the video while it is being created. Change the style, swap the background, or switch outfits in real time. If you drop in a new image, the video adjusts instantly without awkward cuts. Under the hood, it combines real time 720P output with an AI agent that actively watches the video to plan what happens next. It allows you to change reference images on the fly, powered by a model optimized specifically for live streaming. This opens up massive possibilities. Imagine viewers controlling visual changes during a livestream, people transforming into game characters, or shoppers trying on different looks live. The entire S Series is available for a free trial right now so you can test it yourself. Use my code PANDAS2 with the link below to grab 300 bonus credits to explore the other features. Vidu Stream: 300 Bonus Credits: Vidu AI #ViduAI #ViduS #ViduS2

AI Panda

98,066 次观看 • 13 天前

whoever leaked this has bigger balls than sense Google Research and MIT ran the same agent jobs 260 different ways for Nature last month: they held the prompts, the tools and the compute budget identical and moved nothing but the wiring between the agents, and the same work swung from 70% worse than a single agent to 80.8% better, averaging out at 0.0% i ran my own single agent against the task list first and it cleared 6 of 10 alone, already past the line where a crew starts subtracting this is Graph Engineering, the layer that decides whether a crew is worth 80% more or 70% less, and it installs into the agent you already pay for: - score your solo agent on the real task first: above roughly 45% success that study predicts zero to negative returns from any crew you put around it - under that line, put one supervisor over the fan out: crews with no correction step amplified their own errors to 17.2x the single agent rate, supervised aggregation held it to 4.4x - give every worker one output and let none of them read a peer's draft, so a wrong step reaches the supervisor instead of four other agents - run the comparison again after every model upgrade, because a better model raises your baseline and a higher baseline is what makes a crew stop paying - keep the single agent alive as the control, the only number that says the wiring is earning its calls turns out the shape does not travel: the biggest win came off a finance task under one supervisor and the worst collapse off a planning task with independent agents my position, and it is the arguable one: a crew is a bet on your own diagram, and the model you pick moves that bet less than one arrow does bookmark this, the three moves that draw those arrows before you pay for one extra call are in the post below ↓

whoever leaked this has bigger balls than sense Google Research and MIT ran the same agent jobs 260 different ways for Nature last month: they held the prompts, the tools and the compute budget identical and moved nothing but the wiring between the agents, and the same work swung from 70% worse than a single agent to 80.8% better, averaging out at 0.0% i ran my own single agent against the task list first and it cleared 6 of 10 alone, already past the line where a crew starts subtracting this is Graph Engineering, the layer that decides whether a crew is worth 80% more or 70% less, and it installs into the agent you already pay for: - score your solo agent on the real task first: above roughly 45% success that study predicts zero to negative returns from any crew you put around it - under that line, put one supervisor over the fan out: crews with no correction step amplified their own errors to 17.2x the single agent rate, supervised aggregation held it to 4.4x - give every worker one output and let none of them read a peer's draft, so a wrong step reaches the supervisor instead of four other agents - run the comparison again after every model upgrade, because a better model raises your baseline and a higher baseline is what makes a crew stop paying - keep the single agent alive as the control, the only number that says the wiring is earning its calls turns out the shape does not travel: the biggest win came off a finance task under one supervisor and the worst collapse off a planning task with independent agents my position, and it is the arguable one: a crew is a bet on your own diagram, and the model you pick moves that bet less than one arrow does bookmark this, the three moves that draw those arrows before you pay for one extra call are in the post below ↓

Argona

891,965 次观看 • 1 个月前

Dynamic workflows are a generalization of harnesses, automations, loops, routing, and graphs. It's the most powerful feature I have built into my agent orchestrator. Supports all kinds of patterns that leverage different agent backends (claude, codex, pi, hermes,...). It's a meta-harness approach that unlocks new forms of test-time compute. Example of use cases it supports: > LLM councils to get different perspectives from LLMs or plan more intensively > Dynamically routing tasks to different agents based on needs (e.g., cost efficiency and optimal intelligence) > Advisor/Judge + executor workflows and pretty much any complex graph-based pattern required by the task. I find it especially useful for long-running work and code reviewing. > Agent teams that talk to each other if needed for the task. I like to use this for AI editing, artifact creation, and other creative tasks. And I am sure it supports so many things that I haven't discovered yet. I got inspired by the dynamic workflow feature released by the Claude Code team. I had actually built it earlier this year but wanted to generalize it across different agent backends. I think this is going to become more popular in the coming days. I will share more of my findings soon.

Dynamic workflows are a generalization of harnesses, automations, loops, routing, and graphs. It's the most powerful feature I have built into my agent orchestrator. Supports all kinds of patterns that leverage different agent backends (claude, codex, pi, hermes,...). It's a meta-harness approach that unlocks new forms of test-time compute. Example of use cases it supports: > LLM councils to get different perspectives from LLMs or plan more intensively > Dynamically routing tasks to different agents based on needs (e.g., cost efficiency and optimal intelligence) > Advisor/Judge + executor workflows and pretty much any complex graph-based pattern required by the task. I find it especially useful for long-running work and code reviewing. > Agent teams that talk to each other if needed for the task. I like to use this for AI editing, artifact creation, and other creative tasks. And I am sure it supports so many things that I haven't discovered yet. I got inspired by the dynamic workflow feature released by the Claude Code team. I had actually built it earlier this year but wanted to generalize it across different agent backends. I think this is going to become more popular in the coming days. I will share more of my findings soon.

elvis

32,897 次观看 • 2 个月前

I tried Hedra Agent by Hedra to see if one conversation could replace the usual mess of switching models, rewriting prompts, and juggling tools. So I started with a simple idea, Hedra Agent: - Selected the right models on its own - Generated refined visuals - Suggested multiple stylistic directions - Then turned the chosen frames into a cohesive video All within the same conversation while remembering every detail we discussed. I was able to shift the mood, adjust the lighting, refine the composition, explore different angles, and even adapt the format simply by giving natural feedback. I did not have to restart or rebuild anything from scratch. The Agent handled the workflow from idea to finished, platform-ready content. What stood out was not just the output quality, but also the continuity. Instead of operating tools, it felt like collaborating with a system that understands context and builds with you step by step. Check how it works 👇🏻

I tried Hedra Agent by Hedra to see if one conversation could replace the usual mess of switching models, rewriting prompts, and juggling tools. So I started with a simple idea, Hedra Agent: - Selected the right models on its own - Generated refined visuals - Suggested multiple stylistic directions - Then turned the chosen frames into a cohesive video All within the same conversation while remembering every detail we discussed. I was able to shift the mood, adjust the lighting, refine the composition, explore different angles, and even adapt the format simply by giving natural feedback. I did not have to restart or rebuild anything from scratch. The Agent handled the workflow from idea to finished, platform-ready content. What stood out was not just the output quality, but also the continuity. Instead of operating tools, it felt like collaborating with a system that understands context and builds with you step by step. Check how it works 👇🏻

Amira Zairi

31,593 次观看 • 6 个月前