Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Jev Engineering is what turns a messy agent graph into a controlled decision loop. and up to 193x faster and 444x cheaper in tests. the video looks complex, but the idea is simple: Jev Engineering makes that decision explicit. state enters → routes get scored → confidence updates →... weak branches die → strong branches keep moving → execution unlocks so instead of every agent improvising independently, the system keeps narrowing the graph. 0.00 → 0.41 → 0.68 → 0.80 → 0.93 and that score can decide: which model runs → which tool gets called → which branch retries → which result gets rejected that’s the point of Jev Engineering: don’t just give agents more intelligence. engineer how they make decisions. full breakdown guide belowshow more

Ricker

10,629 subscribers

19,376 views • 1 month ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

12 Comments

Smarty1 month ago

wow mate

rewind1 month ago

Clean visual, bro

Dain1 month ago

knowing when to stop a branch is just as important as knowing which one to run.

Apex1 month ago

Banger mate, really enjoy your article

Ricker1 month ago

glad that you find it useful

Selfy1 month ago

start reading full article

Jurly1 month ago

explicit confidence gates are much easier to debug than a swarm of implicit agent choices.

Sophia l1 month ago

how do you handle confidence decay over time

Brjan | AI Builder1 month ago

turning a messy agent graph into a decision loop could save teams tons of time

magsimich1 month ago

Making decisions explicit helps a lot

Morty1 month ago

What a visual mate, perfectly

Lee_19091 month ago

This is a really interesting take on agent decision-making.

Related Videos

Jev Engineering is what lets one decision layer control hundreds of agent paths without turning the system into chaos. and up to 193x faster and 444x cheaper in tests. it’s deciding: → which model gets called → which tool gets access → which result survives that’s what the video is showing. one state enters. Jev turns it into structured decisions. those decisions fan out across dozens of routes, agents and tools. then everything collapses back into one verified state. so instead of: LLM → agent → tool → another LLM → another guess you get: state → Jev decision layer → parallel routes → execution → verification → next state that’s the point of Jev Engineering: more parallelism without giving every branch permission to improvise. full breakdown in the article below ↓

Jev Engineering is what lets one decision layer control hundreds of agent paths without turning the system into chaos. and up to 193x faster and 444x cheaper in tests. it’s deciding: → which model gets called → which tool gets access → which result survives that’s what the video is showing. one state enters. Jev turns it into structured decisions. those decisions fan out across dozens of routes, agents and tools. then everything collapses back into one verified state. so instead of: LLM → agent → tool → another LLM → another guess you get: state → Jev decision layer → parallel routes → execution → verification → next state that’s the point of Jev Engineering: more parallelism without giving every branch permission to improvise. full breakdown in the article below ↓

Ricker

57,821 views • 1 month ago

Jev Engineering is what turns an agent stack into an actual control system and moves the expensive model out of every decision loop. and up to 193x faster and 444x cheaper in tests. the model shouldn’t decide everything. in this setup: request → structured state → Jev router → cheapest capable model → worker → relevance / approval checks → execution gate → tool the important part is that the decision layers don’t generate prose. they route → score → block → approve. so expensive models only get called when the task actually needs them. that’s the point of Jev Engineering: separate reasoning from decision-making, then make the decision layer measurable, cheap and fast. full breakdown in the article below ↓

Jev Engineering is what turns an agent stack into an actual control system and moves the expensive model out of every decision loop. and up to 193x faster and 444x cheaper in tests. the model shouldn’t decide everything. in this setup: request → structured state → Jev router → cheapest capable model → worker → relevance / approval checks → execution gate → tool the important part is that the decision layers don’t generate prose. they route → score → block → approve. so expensive models only get called when the task actually needs them. that’s the point of Jev Engineering: separate reasoning from decision-making, then make the decision layer measurable, cheap and fast. full breakdown in the article below ↓

Ricker

183,199 views • 1 month ago

Jev Engineering is the layer most agent stacks are still missing. state → decision → action → verification → next state up to 193x faster and 444x cheaper in our tests. everyone is optimizing the model. Jev Engineering optimizes what happens between model calls. every agent eventually hits the same fork: state → multiple possible actions → one route has to win instead of sending every decision back to an expensive LLM call, Jev turns that into a dedicated layer: so the loop becomes: LLM → reason Jev → decide tools / agents → execute state → update Jev → decide again once decisions become their own engineering layer, you can benchmark, batch and verify them separately. full blueprint in article ↓

Jev Engineering is the layer most agent stacks are still missing. state → decision → action → verification → next state up to 193x faster and 444x cheaper in our tests. everyone is optimizing the model. Jev Engineering optimizes what happens between model calls. every agent eventually hits the same fork: state → multiple possible actions → one route has to win instead of sending every decision back to an expensive LLM call, Jev turns that into a dedicated layer: so the loop becomes: LLM → reason Jev → decide tools / agents → execute state → update Jev → decide again once decisions become their own engineering layer, you can benchmark, batch and verify them separately. full blueprint in article ↓

Ricker

116,701 views • 1 month ago

Jev Engineering turns a static agent workflow into a graph that can rewrite itself while running. the video is basically the problem at scale: hundreds of routes → thousands of crossings → different agents → different tools → different confidence levels Jev Engineering doesn’t control every step. it controls the crossings. when two paths compete: → score both → kill the weak route → reroute the task so instead of one fixed chain, you get a live braid: state → decision → parallel paths → crossings → Jev → next state that’s the point of Jev Engineering: more parallel execution without letting the system lose the objective. the agents create the paths. Jev decides which paths survive. full breakdown below ↓

Jev Engineering turns a static agent workflow into a graph that can rewrite itself while running. the video is basically the problem at scale: hundreds of routes → thousands of crossings → different agents → different tools → different confidence levels Jev Engineering doesn’t control every step. it controls the crossings. when two paths compete: → score both → kill the weak route → reroute the task so instead of one fixed chain, you get a live braid: state → decision → parallel paths → crossings → Jev → next state that’s the point of Jev Engineering: more parallel execution without letting the system lose the objective. the agents create the paths. Jev decides which paths survive. full breakdown below ↓

Ricker

11,506 views • 1 month ago

Jev Engineering changes the unit of optimization from “agent” to “decision.” that sounds small, but it changes the architecture. and up to 193x faster and 444x cheaper in tests. normal multi-agent stack: agent → prompt → tool → output Jev-style stack: shared state → decision boundary → selected branch → execution → measurement → state update now you can optimize the actual control points: latency per decision cost per fork confidence threshold retry policy branch survival termination condition the agents underneath can change. the models can change. the tools can change. the decision layer stays measurable. that’s why Jev Engineering feels more like systems engineering than prompt engineering.

Jev Engineering changes the unit of optimization from “agent” to “decision.” that sounds small, but it changes the architecture. and up to 193x faster and 444x cheaper in tests. normal multi-agent stack: agent → prompt → tool → output Jev-style stack: shared state → decision boundary → selected branch → execution → measurement → state update now you can optimize the actual control points: latency per decision cost per fork confidence threshold retry policy branch survival termination condition the agents underneath can change. the models can change. the tools can change. the decision layer stays measurable. that’s why Jev Engineering feels more like systems engineering than prompt engineering.

Ricker

22,469 views • 1 month ago

Jev Engineering ran 5,400 agent executions and sent exactly 0 decisions back to me. that’s the number i care about here. and up to 193x faster and 444x cheaper in tests. 18 turns → 300 agents → 5,400 runs → 43 Jev calls → 16 outputs kept → 0 human escalations the loop handled three decisions around every turn: Choice → Score → Noul then it stopped itself when the goal crossed 0.93 vs 0.85 required. that’s what Jev Engineering looks like when it works: not “more autonomous agents.” fewer reasons for the human to come back into the loop.

Jev Engineering ran 5,400 agent executions and sent exactly 0 decisions back to me. that’s the number i care about here. and up to 193x faster and 444x cheaper in tests. 18 turns → 300 agents → 5,400 runs → 43 Jev calls → 16 outputs kept → 0 human escalations the loop handled three decisions around every turn: Choice → Score → Noul then it stopped itself when the goal crossed 0.93 vs 0.85 required. that’s what Jev Engineering looks like when it works: not “more autonomous agents.” fewer reasons for the human to come back into the loop.

Ricker

13,329 views • 1 month ago

your agent is not the loop the loop is only the smallest layer LOOP vs GRAPH vs HARNESS ENGINEERING most teams still treat all three like one prompt that is why agent failures feel impossible to diagnose LOOP ENGINEERING controls iteration turns retries budgets evaluators exits stalled progress when the run keeps going forever the loop is broken make long-running work survive crashes and restarts → GRAPH ENGINEERING controls structure nodes edges state branches cycles joins checkpoints when the agent takes the wrong path the graph is broken make state and routing explicit → inspect the topology without asking another model to explain it → HARNESS ENGINEERING controls access tools permissions memory sandboxes evals traces humans when the agent touches the wrong system the harness is broken isolate generated code and tool execution from the host → put an eval gate before every model or prompt update → keep one trace across every node model and tool call → without loop engineering it never stops without graph engineering you cannot see the path without harness engineering it can reach anything the prompt lives inside the loop the loop lives inside the graph the graph lives inside the harness the model is the smallest box in the system debug the layer that actually owns the failure save this before the next agent rewrite

your agent is not the loop the loop is only the smallest layer LOOP vs GRAPH vs HARNESS ENGINEERING most teams still treat all three like one prompt that is why agent failures feel impossible to diagnose LOOP ENGINEERING controls iteration turns retries budgets evaluators exits stalled progress when the run keeps going forever the loop is broken make long-running work survive crashes and restarts → GRAPH ENGINEERING controls structure nodes edges state branches cycles joins checkpoints when the agent takes the wrong path the graph is broken make state and routing explicit → inspect the topology without asking another model to explain it → HARNESS ENGINEERING controls access tools permissions memory sandboxes evals traces humans when the agent touches the wrong system the harness is broken isolate generated code and tool execution from the host → put an eval gate before every model or prompt update → keep one trace across every node model and tool call → without loop engineering it never stops without graph engineering you cannot see the path without harness engineering it can reach anything the prompt lives inside the loop the loop lives inside the graph the graph lives inside the harness the model is the smallest box in the system debug the layer that actually owns the failure save this before the next agent rewrite

elune

16,875 views • 3 months ago

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 views • 3 months ago

Jev + Claude Opus 5.5 is f*cking dangerous hand the decision forks to Jev and one agent's bill drops from about $110 a day to $4 i still haven't found a better way to run Opus 4 calls Opus never has to make again: -> which project notes to load before context fills -> which easy steps go to a faster worker -> how to recover when a tool breaks, without blind retries -> which quick checks run before the full test suite Opus keeps every hard reasoning step Jev just picks from options the harness already tested each pick comes back in about 100 ms, and Jev's output tokens are free Jev engineering in one line: Opus gets the essay questions, Jev gets the multiple choice that's about $3,180 a month off the same workload numbers like that get people promoted read the paper in the video first, then the full Jev guide:

Jev + Claude Opus 5.5 is f*cking dangerous hand the decision forks to Jev and one agent's bill drops from about $110 a day to $4 i still haven't found a better way to run Opus 4 calls Opus never has to make again: -> which project notes to load before context fills -> which easy steps go to a faster worker -> how to recover when a tool breaks, without blind retries -> which quick checks run before the full test suite Opus keeps every hard reasoning step Jev just picks from options the harness already tested each pick comes back in about 100 ms, and Jev's output tokens are free Jev engineering in one line: Opus gets the essay questions, Jev gets the multiple choice that's about $3,180 a month off the same workload numbers like that get people promoted read the paper in the video first, then the full Jev guide:

Annatar.md

10,221 views • 22 days ago

a Stanford professor used JEV to build a data science system that analyzes 40.000.000.000 data points every 15 min his system can process massive datasets and automatically decide which results deserve deeper analysis. the professor spent more than a year developing the system with his research team. the first version relied heavily on LLMs to interpret every result. it worked, but analyzing millions of records created unnecessary latency and huge inference costs. then they redesigned the decision layer around Jev. instead of generating explanations for every data point, Jev evaluates the results and decides what the system should investigate next. I found a breakdown of the pipeline they used and the way Jev filters the data is surprisingly clever. I’ll show you how it works next so stay tuned if you want to see what Jev Engineering looks like inside a real data science system. would you let an AI decide which patterns in your data are worth investigating?

a Stanford professor used JEV to build a data science system that analyzes 40.000.000.000 data points every 15 min his system can process massive datasets and automatically decide which results deserve deeper analysis. the professor spent more than a year developing the system with his research team. the first version relied heavily on LLMs to interpret every result. it worked, but analyzing millions of records created unnecessary latency and huge inference costs. then they redesigned the decision layer around Jev. instead of generating explanations for every data point, Jev evaluates the results and decides what the system should investigate next. I found a breakdown of the pipeline they used and the way Jev filters the data is surprisingly clever. I’ll show you how it works next so stay tuned if you want to see what Jev Engineering looks like inside a real data science system. would you let an AI decide which patterns in your data are worth investigating?

deezzex

175,697 views • 1 month ago

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 views • 3 months ago

Jev + Opus 5.5 is the most underrated setup in AI right now, and i don't get why nobody's talking about it. I stopped letting Opus make every small decision in my agents. Jev makes them now. My Opus bill dropped ~500% on the same tasks, same results. Here's what Jev handles: - which files and notes to load before Opus sees anything - which effort level each task actually needs - what to do when a tool fails - which tests to run, and when to stop Opus only gets called for the hard reasoning. Every decision is a typed result the host checks before it runs. The exact prompt to set this up in your workflow is below.

Jev + Opus 5.5 is the most underrated setup in AI right now, and i don't get why nobody's talking about it. I stopped letting Opus make every small decision in my agents. Jev makes them now. My Opus bill dropped ~500% on the same tasks, same results. Here's what Jev handles: - which files and notes to load before Opus sees anything - which effort level each task actually needs - what to do when a tool fails - which tests to run, and when to stop Opus only gets called for the hard reasoning. Every decision is a typed result the host checks before it runs. The exact prompt to set this up in your workflow is below.

Anatoli Kopadze

77,128 views • 1 month ago

This is f*cking insane. Anthropic Research Lead: "Prompting is basically over 99% of our engineers already run swarms of 300+ self-improving agents. Now everyone is shifting to graphs" In just 20 minutes, she breaks down how graph engineering turns scattered agents into a system that improves itself One Agent → Loops → Plan Mode → Graphs → Self-Improving System Prompting was the old way. The graph around the model is the new one Worth more than most $1,000 agent engineering courses Bookmark and watch it today Then read the full Graph Engineering guide below ↓

This is f*cking insane. Anthropic Research Lead: "Prompting is basically over 99% of our engineers already run swarms of 300+ self-improving agents. Now everyone is shifting to graphs" In just 20 minutes, she breaks down how graph engineering turns scattered agents into a system that improves itself One Agent → Loops → Plan Mode → Graphs → Self-Improving System Prompting was the old way. The graph around the model is the new one Worth more than most $1,000 agent engineering courses Bookmark and watch it today Then read the full Graph Engineering guide below ↓

Kyrox

72,376 views • 9 days ago

This is f*cking insane. Anthropic Research Lead: "Prompting is basically over 99% of our engineers already run swarms of 300+ self-improving agents. Now everyone is shifting to graphs" In only 20 minutes, she breaks down how graph engineering turns scattered agents into a system that upgrades itself One Agent → Loops → Plan Mode → Graphs → Self-Improving System Prompting was the old approach. The graph around the model is the new one Worth more than most $1,000 agent engineering courses Bookmark and watch it today Then read the full Graph Engineering guide below ↓

This is f*cking insane. Anthropic Research Lead: "Prompting is basically over 99% of our engineers already run swarms of 300+ self-improving agents. Now everyone is shifting to graphs" In only 20 minutes, she breaks down how graph engineering turns scattered agents into a system that upgrades itself One Agent → Loops → Plan Mode → Graphs → Self-Improving System Prompting was the old approach. The graph around the model is the new one Worth more than most $1,000 agent engineering courses Bookmark and watch it today Then read the full Graph Engineering guide below ↓

Callan

15,632 views • 8 days ago

$Holy crap, who the hell did this?!! Someone open-sourced a Jev-powered second brain for AI agents and lets you plug it straight into your own agent. GitHub's already at 925 stars, repo's called Hermes-Jev-Skills. You just run one install command, and Jev takes over every tiny decision your agent burns premium tokens on. Which model answers, which skill to load, which memories matter, what survives when context gets cut. Give it your computer or browser and it'll pick the next click, but only from actions you already marked safe. It'll sort your inbox into lanes, strip hidden prompt injections out of search results, and triage every message in ~0.4 seconds. Claude Code and Codex support - they threw that in too. No dependencies, no patching Hermes core, and your API key never touches the agent Link's right here: The catch? Jev itself is a paid cloud API. The skills run on your machine; the decisions don't. But hey, a decision costs a fraction of a cent, everything fails open if Jev goes down, and your expensive model finally gets to do only the thinking. Who needs a damn frontier model picking which file to open!$

Holy crap, who the hell did this?!! Someone open-sourced a Jev-powered second brain for AI agents and lets you plug it straight into your own agent. GitHub's already at 925 stars, repo's called Hermes-Jev-Skills. You just run one install command, and Jev takes over every tiny decision your agent burns premium tokens on. Which model answers, which skill to load, which memories matter, what survives when context gets cut. Give it your computer or browser and it'll pick the next click, but only from actions you already marked safe. It'll sort your inbox into lanes, strip hidden prompt injections out of search results, and triage every message in ~0.4 seconds. Claude Code and Codex support - they threw that in too. No dependencies, no patching Hermes core, and your API key never touches the agent Link's right here: The catch? Jev itself is a paid cloud API. The skills run on your machine; the decisions don't. But hey, a decision costs a fraction of a cent, everything fails open if Jev goes down, and your expensive model finally gets to do only the thinking. Who needs a damn frontier model picking which file to open!

Archive

17,492 views • 1 month ago

Graph engineering is everywhere right now—so here's a quick breakdown of harnesses, loops, and graphs, and how they connect in multi-agent workflows. Watch the full video to learn about graph engineering with ADK →

Graph engineering is everywhere right now—so here's a quick breakdown of harnesses, loops, and graphs, and how they connect in multi-agent workflows. Watch the full video to learn about graph engineering with ADK →

Google Cloud Tech

35,753 views • 2 months ago

Jev Engineering transforms a collection of AI agents into a full-fledged management system while eliminating heavy, expensive models from every decision-making loop Speed: +19,000% Costs: -99.7% How this architecture works: Gatekeeper Request Mini-Model Validation Tool Router State Worker Management layers avoid generating detailed text and instead focus on directing, evaluating, blocking, or permitting Route -> Score -> Block -> Approve As a result, resource-intensive models are invoked exclusively when the task truly requires it This is the essence of Jev Engineering: to decouple reasoning from decision-making, making the decision-making layer fast, cheap, and easily quantifiable Detailed instructions in the article below

Jev Engineering transforms a collection of AI agents into a full-fledged management system while eliminating heavy, expensive models from every decision-making loop Speed: +19,000% Costs: -99.7% How this architecture works: Gatekeeper Request Mini-Model Validation Tool Router State Worker Management layers avoid generating detailed text and instead focus on directing, evaluating, blocking, or permitting Route -> Score -> Block -> Approve As a result, resource-intensive models are invoked exclusively when the task truly requires it This is the essence of Jev Engineering: to decouple reasoning from decision-making, making the decision-making layer fast, cheap, and easily quantifiable Detailed instructions in the article below

Bober_smart

13,950 views • 1 month ago

He is 18 teaching AI at Stanford making $2.2M on agents - and in 60 minutes revealed how to repeat it from zero: 00:30 - 5% who build agents will replace the 95% who just use them 38:33 - Jev Engineering is the only thing you need to make $2.2M on an agent 52:47 - Claude + Jev 10x cheaper and faster right now after watching I built my first agent with Jev in 15 minutes and sold it to a million dollar company for $100k: save & watch - the article below shows how to use Jev Engineering to make Claude 10x cheaper and build a $2.2M agent.

He is 18 teaching AI at Stanford making $2.2M on agents - and in 60 minutes revealed how to repeat it from zero: 00:30 - 5% who build agents will replace the 95% who just use them 38:33 - Jev Engineering is the only thing you need to make $2.2M on an agent 52:47 - Claude + Jev 10x cheaper and faster right now after watching I built my first agent with Jev in 15 minutes and sold it to a million dollar company for $100k: save & watch - the article below shows how to use Jev Engineering to make Claude 10x cheaper and build a $2.2M agent.

Noisy

13,407 views • 1 month ago

Anthropic engineer: "At Anthropic, all of our engineers are running hundreds of agents The way you do it is graph engineering" In just 36 minutes, he shows how Anthropic runs hundreds of agents at once and what actually makes it possible Prompts → Agents → Loops → Graphs The part most people skip is the return path, where every accepted result becomes a constraint for the next run Same model, same tokens, completely different system Prompting is the old workflow Graph engineering is the next one Watch it today Then save the full graph engineering guide below before everyone starts catching up ↓

Anthropic engineer: "At Anthropic, all of our engineers are running hundreds of agents The way you do it is graph engineering" In just 36 minutes, he shows how Anthropic runs hundreds of agents at once and what actually makes it possible Prompts → Agents → Loops → Graphs The part most people skip is the return path, where every accepted result becomes a constraint for the next run Same model, same tokens, completely different system Prompting is the old workflow Graph engineering is the next one Watch it today Then save the full graph engineering guide below before everyone starts catching up ↓

Lunar

32,987 views • 2 months ago

Jev + Opus 5.5, side by side. same agent. same task. same 60 decisions. Opus-only: $2.24 - 3m 37s Jev + Opus: $0.43 - 1m 15s the difference is who makes the small calls: which tool runs next - Jev is this output good enough - Jev is the goal met - Jev rewrite the refund handler - Opus 57 of 60 decisions never touched Opus. what you're watching: left routes every decision through Opus 5.5. right asks Jev first, Opus only fires when the task needs real reasoning. per decision: $0.032 -> $0.00025. watch the cost counters, not the output. the output is identical. full setup in the post below ↓

Jev + Opus 5.5, side by side. same agent. same task. same 60 decisions. Opus-only: $2.24 - 3m 37s Jev + Opus: $0.43 - 1m 15s the difference is who makes the small calls: which tool runs next - Jev is this output good enough - Jev is the goal met - Jev rewrite the refund handler - Opus 57 of 60 decisions never touched Opus. what you're watching: left routes every decision through Opus 5.5. right asks Jev first, Opus only fires when the task needs real reasoning. per decision: $0.032 -> $0.00025. watch the cost counters, not the output. the output is identical. full setup in the post below ↓

Mahax

19,565 views • 1 month ago