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.

It's all about the loop. Agents accumulate state with every step of the loop. This state needs a new data primitive. That's Durable Streams 🧵👇

Electric

7,024 subscribers

10,835 Aufrufe • vor 6 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

7 Kommentare

Profilbild von Electric

Electricvor 6 Monaten

The data primitive for the agent loop:

Profilbild von Electric

Electricvor 6 Monaten

The agent loop accumulates state: messages, token streams, tool calls and results. A new kind of data that needs a new data primitive.

Profilbild von Electric

Electricvor 6 Monaten

.@DurableStreams are persistent, addressable, real-time streams. Reactive, resumable and extensible, they are the data primitive for the agent loop.

Profilbild von Electric

Electricvor 6 Monaten

Docs: Transports: Extensions: Examples:

Profilbild von Electric

Electricvor 6 Monaten

Deploy now on Electric Cloud:

Profilbild von Jeremy Osih

Jeremy Osihvor 6 Monaten

@DurableStreams I've been pretty excited for this !

Profilbild von Robert Balicki (👀 @IsographLabs)

Robert Balicki (👀 @IsographLabs)vor 6 Monaten

@DurableStreams Folks on this thread may be interested in trying out Barnum, which is a programming language that makes it easy to orchestrate your agents. Looping, branching, etc all already exist (in programming languages)! We don't need to reinvent them.

Ähnliche Videos

callbacks with durable objects are weird (but it's also convenient to solve human-in-the-loop for ai agents) tl;dr - by defining callbacks as data, we can let durable objects "sleep" while it's waiting for a timer/email/webhook/phone call/whatever. demo borked a little bit, I blame openai, but it all stilkl worked. that's video 2. gnight!

callbacks with durable objects are weird (but it's also convenient to solve human-in-the-loop for ai agents) tl;dr - by defining callbacks as data, we can let durable objects "sleep" while it's waiting for a timer/email/webhook/phone call/whatever. demo borked a little bit, I blame openai, but it all stilkl worked. that's video 2. gnight!

sunil pai

22,331 Aufrufe • vor 1 Jahr

If the state of Rivals right now was Overwatch you would see DOZENS of videos talking about the state of play with a negative connotation How more people are not talking about regardless of the "meta" the gameplay loop of rivals has been THE SAME for 2 years 40s ults 24/7

If the state of Rivals right now was Overwatch you would see DOZENS of videos talking about the state of play with a negative connotation How more people are not talking about regardless of the "meta" the gameplay loop of rivals has been THE SAME for 2 years 40s ults 24/7

Samito

317,050 Aufrufe • vor 8 Monaten

Step into the magic and enjoy every beat with the Tomorrowland x Loop Earplugs. Available at

Step into the magic and enjoy every beat with the Tomorrowland x Loop Earplugs. Available at

Tomorrowland

15,631 Aufrufe • vor 1 Jahr

the loop is not the whole agent it is only one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls iteration turns retries budgets stop conditions success checks stalled progress use durable execution when the run must survive crashes → GRAPH ENGINEERING controls structure nodes edges state branches checkpoints routing handoffs build stateful agents as explicit graphs → inspect the topology without putting a model in the loop → HARNESS ENGINEERING controls exposure tools permissions memory sandboxes evals traces humans isolate generated code from the host machine → test behavior before users ever see it → preserve one trace across every model step and tool call → without loop control it keeps running without graph structure the path stays invisible without harness control it can reach anything the loop runs inside the graph the graph runs inside the harness the model is only one component debug the layer that actually owns the failure save this then read the article below

the loop is not the whole agent it is only one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls iteration turns retries budgets stop conditions success checks stalled progress use durable execution when the run must survive crashes → GRAPH ENGINEERING controls structure nodes edges state branches checkpoints routing handoffs build stateful agents as explicit graphs → inspect the topology without putting a model in the loop → HARNESS ENGINEERING controls exposure tools permissions memory sandboxes evals traces humans isolate generated code from the host machine → test behavior before users ever see it → preserve one trace across every model step and tool call → without loop control it keeps running without graph structure the path stays invisible without harness control it can reach anything the loop runs inside the graph the graph runs inside the harness the model is only one component debug the layer that actually owns the failure save this then read the article below

rari

20,934 Aufrufe • vor 2 Monaten

"By stitching these three primitives together, you get an agent loop that's actually a distributed state machine under the hood." At DevCon 6, Palantir Group Lead Natasha Armbrust launches Agent Engine and Agent SDK, giving developers the core primitives to build agents that form a distributed state machine and are multiplayer by design. ▪️Context items for defining agent sessions through strongly typed data ▪️ Events for expressively acting on changes in state ▪️Effects for connecting agents to the outside world

"By stitching these three primitives together, you get an agent loop that's actually a distributed state machine under the hood." At DevCon 6, Palantir Group Lead Natasha Armbrust launches Agent Engine and Agent SDK, giving developers the core primitives to build agents that form a distributed state machine and are multiplayer by design. ▪️Context items for defining agent sessions through strongly typed data ▪️ Events for expressively acting on changes in state ▪️Effects for connecting agents to the outside world

Palantir

72,323 Aufrufe • vor 3 Monaten

Andrew Ng at Stanford: “Stop waiting for the perfect model. Build the iteration "loop" and "graphs" around it.” move from prompt → loop → graph → self-improving system • 00:05 - why every AI project needs an iteration loop • 04:08 - the full cycle: data → model → deploy → monitor • 16:02 - why faster iteration can decide who wins • 26:09 - using error analysis to improve the right data • 39:39 - why shipping a simple system beats waiting for perfection • 54:26 - monitoring drift and improving models after deployment 67-minute Stanford lecture, and it’s one of the clearest playbooks on why experienced AI engineers optimize the loop around the model, not just the model itself. It's watch today, then read the full step by step roadmap in the article below

Andrew Ng at Stanford: “Stop waiting for the perfect model. Build the iteration "loop" and "graphs" around it.” move from prompt → loop → graph → self-improving system • 00:05 - why every AI project needs an iteration loop • 04:08 - the full cycle: data → model → deploy → monitor • 16:02 - why faster iteration can decide who wins • 26:09 - using error analysis to improve the right data • 39:39 - why shipping a simple system beats waiting for perfection • 54:26 - monitoring drift and improving models after deployment 67-minute Stanford lecture, and it’s one of the clearest playbooks on why experienced AI engineers optimize the loop around the model, not just the model itself. It's watch today, then read the full step by step roadmap in the article below

Morlex

22,861 Aufrufe • vor 2 Monaten

the loop is not the agent it is one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls repetition turns retries budgets exits success checks no progress use durable execution when the run must survive failure → GRAPH ENGINEERING controls topology nodes edges state branches checkpoints handoffs build stateful agents as explicit graphs → analyze the topology without putting a model in the loop → HARNESS ENGINEERING controls the blast radius tools permissions memory sandboxes evals traces humans isolate generated code from the host → test behavior before it reaches users → keep one trace across every model node and tool call → without loop control it never stops without graph structure you cannot see the path without harness control it can touch anything the loop lives inside the graph the graph lives inside the harness the model is not the system debug the layer that owns the failure save this

the loop is not the agent it is one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls repetition turns retries budgets exits success checks no progress use durable execution when the run must survive failure → GRAPH ENGINEERING controls topology nodes edges state branches checkpoints handoffs build stateful agents as explicit graphs → analyze the topology without putting a model in the loop → HARNESS ENGINEERING controls the blast radius tools permissions memory sandboxes evals traces humans isolate generated code from the host → test behavior before it reaches users → keep one trace across every model node and tool call → without loop control it never stops without graph structure you cannot see the path without harness control it can touch anything the loop lives inside the graph the graph lives inside the harness the model is not the system debug the layer that owns the failure save this

elune

50,193 Aufrufe • vor 2 Monaten

Korra has a loop in the corner while in avatar state so be careful

Chakotay

32,915 Aufrufe • vor 10 Monaten

While AI timeline argues about loop engineering, a 20-year-old student in Shenzhen built the biggest loop anyone's aimed at money: 300 agents, one brain, $1,200 -> 395,000. Not a prompt. Not a bot. A loop that runs the whole job on its own - and never asks him a thing. No fund. No backers. Just a laptop, a dorm room, and a bet that a swarm beats a genius. His wallet: The smartest single model still works one step at a time. His loop moves in 300 directions at once - and never checks in with him. Claude Opus 4.8 runs the floor as the brain. 300 agents are the hands. One loop ties them together: > Decompose - Opus breaks the market into targets > Dispatch - 300 agents scatter across them at once > Execute - thousands of reads in a single pass, not one by one > Review - Opus grades every edge before a cent moves The hands find. The brain judges. The loop learns what failed and runs again, tighter each time. One daily loss cap, and it shuts itself down. It's not a bot you babysit. It's a loop that runs the whole desk. Everyone's just learning to run one loop. He runs 300 in one. The edge was never the genius model - it's the size of the loop, and the brain in charge of it. Save this - the full 300-agent loop is laid out above, start to finish. You'll want it when you build your own. 300 agents are looping right now, hunting the markets everyone skips. Two clicks and their trades land in your wallet too:

While AI timeline argues about loop engineering, a 20-year-old student in Shenzhen built the biggest loop anyone's aimed at money: 300 agents, one brain, $1,200 -> 395,000. Not a prompt. Not a bot. A loop that runs the whole job on its own - and never asks him a thing. No fund. No backers. Just a laptop, a dorm room, and a bet that a swarm beats a genius. His wallet: The smartest single model still works one step at a time. His loop moves in 300 directions at once - and never checks in with him. Claude Opus 4.8 runs the floor as the brain. 300 agents are the hands. One loop ties them together: > Decompose - Opus breaks the market into targets > Dispatch - 300 agents scatter across them at once > Execute - thousands of reads in a single pass, not one by one > Review - Opus grades every edge before a cent moves The hands find. The brain judges. The loop learns what failed and runs again, tighter each time. One daily loss cap, and it shuts itself down. It's not a bot you babysit. It's a loop that runs the whole desk. Everyone's just learning to run one loop. He runs 300 in one. The edge was never the genius model - it's the size of the loop, and the brain in charge of it. Save this - the full 300-agent loop is laid out above, start to finish. You'll want it when you build your own. 300 agents are looping right now, hunting the markets everyone skips. Two clicks and their trades land in your wallet too:

cvxv666

53,282 Aufrufe • vor 3 Monaten

Meet Data Scout. It's a $500k data scientist for every employee. One of those agents every business needs. > Has Snowflake access (+ Notion, Slack, Github) > Runs deep analysis on all user and account data > Can be called by other agents for recurring reports Data Scout is one of the most used agents at Notion. And you can build one.

Meet Data Scout. It's a $500k data scientist for every employee. One of those agents every business needs. > Has Snowflake access (+ Notion, Slack, Github) > Runs deep analysis on all user and account data > Can be called by other agents for recurring reports Data Scout is one of the most used agents at Notion. And you can build one.

Hurley

33,300 Aufrufe • vor 6 Monaten

Isaiah Rashad breaks down the meaning behind naming his album “It’s Been Awful” with Ebro: "It's just life, it's reflection with a lot of things. The state of the Government, the state of the world, the state of national parks, the state of women's rights, the state of the rights taking away from special needs kids in the south a lot of it is awful"

Isaiah Rashad breaks down the meaning behind naming his album “It’s Been Awful” with Ebro: "It's just life, it's reflection with a lot of things. The state of the Government, the state of the world, the state of national parks, the state of women's rights, the state of the rights taking away from special needs kids in the south a lot of it is awful"

Ahmed/The Ears/IG: BigBizTheGod 🇸🇴

74,164 Aufrufe • vor 4 Monaten

NEW 🚨: The Nation State Race to Accumulate 1M #Bitcoin Began 17 Days Ago! 👇

NEW 🚨: The Nation State Race to Accumulate 1M #Bitcoin Began 17 Days Ago! 👇

Simply Bitcoin

56,146 Aufrufe • vor 1 Jahr

built `jev-review` TypeSafe AI it's an experimental, local-first MCP plugin that gives coding agents a score quality feedback loop across different metrics. agents call jev while they work, get scored, make improvements, and repeat the loop try below 👇

built `jev-review` TypeSafe AI it's an experimental, local-first MCP plugin that gives coding agents a score quality feedback loop across different metrics. agents call jev while they work, get scored, make improvements, and repeat the loop try below 👇

Niaz Morshed

47,370 Aufrufe • vor 27 Tagen

$this harness stack is f*cking gold TypeSafe AI + LangChain finally dropped the layer that makes agents affordable at company scale: jev running inside the langchain agent loop as middleware the problem every big team hits: each fork in the loop is another full LLM call. at 10 agents that's a bill. at 10,000 it's the budget > routing before: every task goes to the frontier model now: jev picks the least costly model that can finish it. lookups go fast, architecture goes powerful > guardrails before: the "is this command dangerous?" check sat in the closed parts of claude code, codex, cursor now: AutoModeMiddleware(tools=["bash"]). one line, any agent, blocked before the tool runs > decisions before: one LLM call per question now: every question about the same state in one request, answered in parallel > audit before: "the model decided" now: the answer, the probability and the confidence stay in agent state > adoption no rewrite. pip install langchain-typesafe and drop it into the agent you already run TypeSafe reports up to 200x faster inference and 400x lower cost than comparable LLMs on classification. the LLM still reasons and writes. jev takes the thousands of small calls in between already live: browserbase agents for fractions of a cent, a live trading agent, email triage at scale full loop mapped below: 7 agents, 4 jev gates per step count the forks in your agent loop tonigh$

this harness stack is f*cking gold TypeSafe AI + LangChain finally dropped the layer that makes agents affordable at company scale: jev running inside the langchain agent loop as middleware the problem every big team hits: each fork in the loop is another full LLM call. at 10 agents that's a bill. at 10,000 it's the budget > routing before: every task goes to the frontier model now: jev picks the least costly model that can finish it. lookups go fast, architecture goes powerful > guardrails before: the "is this command dangerous?" check sat in the closed parts of claude code, codex, cursor now: AutoModeMiddleware(tools=["bash"]). one line, any agent, blocked before the tool runs > decisions before: one LLM call per question now: every question about the same state in one request, answered in parallel > audit before: "the model decided" now: the answer, the probability and the confidence stay in agent state > adoption no rewrite. pip install langchain-typesafe and drop it into the agent you already run TypeSafe reports up to 200x faster inference and 400x lower cost than comparable LLMs on classification. the LLM still reasons and writes. jev takes the thousands of small calls in between already live: browserbase agents for fractions of a cent, a live trading agent, email triage at scale full loop mapped below: 7 agents, 4 jev gates per step count the forks in your agent loop tonigh

NO1ennn

31,666 Aufrufe • vor 15 Tagen

Watch this deep-dive with Head of API Sabrina on the next stage of loop engineering and self-improving agents.

Watch this deep-dive with Head of API Sabrina on the next stage of loop engineering and self-improving agents.

Venice

26,326 Aufrufe • vor 2 Monaten

Anthropic just reliesed the best 1-hour workshop on Loop engineering: from one prompt to a Loop that improves itself 5:31 - loop memory 11:02 - check, build, commit 13:06 - one feature per loop 33:03 - MVP in 1 hour Free, the best thing on Loop engineering I've come across. Watch it, then try your first loop with the step-by-step guide below

Anthropic just reliesed the best 1-hour workshop on Loop engineering: from one prompt to a Loop that improves itself 5:31 - loop memory 11:02 - check, build, commit 13:06 - one feature per loop 33:03 - MVP in 1 hour Free, the best thing on Loop engineering I've come across. Watch it, then try your first loop with the step-by-step guide below

Mahax

97,431 Aufrufe • vor 1 Monat

This indie dev is making a horror game based on Acrophobia - the fear of heights, & Liminal Space - Trapped in a corridor above the clouds - Every loop, the environment changes - Find anomalies, trigger the alarm, break the loop Would you play this? It's called Cloudrooms.

This indie dev is making a horror game based on Acrophobia - the fear of heights, & Liminal Space - Trapped in a corridor above the clouds - Every loop, the environment changes - Find anomalies, trigger the alarm, break the loop Would you play this? It's called Cloudrooms.

Indie Game Joe

47,902 Aufrufe • vor 5 Monaten

Great example of what Foundry enables: durable, stateful agents that run across time boundaries, orchestrate tools and models, and close the loop with evaluation and improvement over long-running workflows. Jeff Hollan

Great example of what Foundry enables: durable, stateful agents that run across time boundaries, orchestrate tools and models, and close the loop with evaluation and improvement over long-running workflows. Jeff Hollan

Satya Nadella

147,606 Aufrufe • vor 5 Monaten