正在加载视频...

视频加载失败

返回首页

It is becoming f*cking dangerous: AI agents mapped out a full codebase based on just one question Jev creator Diogo Almeida put together a playbook to sync up 80 agents over 540,000 lines of code, creating a visual flow of the system architecture Simply ask: "What takes place when...

Bober_smart's profile picture

Bober_smart

20,418 subscribers

14,890 次观看 • 10 天前 •via X (Twitter)

科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

53 条评论

Alter Ego 的头像
Alter Ego10 天前

It looks amazing, you can create entire apps in just a few minutes

Bober_smart 的头像
Bober_smart10 天前

Now that’s a real alpha

Sevenup 的头像
Sevenup10 天前

80 agents, 540K lines of code, one question. AI-powered codebase mapping is getting wild.

Bober_smart 的头像
Bober_smart10 天前

Ohhh yes

MAX 的头像
MAX10 天前

mapping user flows directly to code and tests is the real value here

Bober_smart 的头像
Bober_smart10 天前

Oh yes, this is my favorite part

Kinder 的头像
Kinder10 天前

Orchestrating 80 agents over half a million lines of code is a crazy benchmark for multi-agent coordination.

Bober_smart 的头像
Bober_smart10 天前

This really looks insane

ELG 的头像
ELG10 天前

A good approach is to run a trial on a single user path first before scaling it up to the full repository

Bober_smart 的头像
Bober_smart10 天前

Yes, that’s a tactically sound move

Moysha 的头像
Moysha10 天前

80 agents is serious scale

Bober_smart 的头像
Bober_smart10 天前

Well, yes, this is truly large-scale

Dimss | Crypto × AI 的头像
Dimss | Crypto × AI10 天前

It looks impressive, and, most importantly, it’s useful for engineers.

Bober_smart 的头像
Bober_smart10 天前

Yes, and this can also be applied in many areas

Dekos 的头像
Dekos10 天前

I wonder what level AI development will reach.

Bober_smart 的头像
Bober_smart10 天前

I think this will yet surprise us

emelu 的头像
emelu10 天前

this is more like spinning up a Quant company

Bober_smart 的头像
Bober_smart10 天前

Quite possible

Bruno Cordista 的头像
Bruno Cordista10 天前

cool until one of the 80 is confidently wrong about auth. with my 16 bots the trust part is way harder than the setup

Bober_smart 的头像
Bober_smart10 天前

Yes, this works unfailingly

Macro Bombastic 的头像
Macro Bombastic10 天前

yeah the "what happens when a user uploads a file" angle is honestly the smartest part

me_cool_off 的头像
me_cool_off10 天前

agents + Jev is a strong combo for optimizing processes

Bober_smart 的头像
Bober_smart10 天前

This is an excellent combination

Slonski 的头像
Slonski10 天前

trial one path before scaling, sound caution

Bober_smart 的头像
Bober_smart10 天前

You should approach everything with a sensible mindset

kiosa 的头像
kiosa10 天前

Render is sick

Bober_smart 的头像
Bober_smart10 天前

Thanks, friend

Korens 的头像
Korens10 天前

saved thanks

Bober_smart 的头像
Bober_smart10 天前

Always happy to help

EugBass 的头像
EugBass10 天前

you have always been very dangerous goat

Bober_smart 的头像
Bober_smart10 天前

Hahaha thanks bro

Knight 的头像
Knight10 天前

how long did the full run over 540k lines take?

Bober_smart 的头像
Bober_smart10 天前

Approximately 5 hours

shmidt 的头像
shmidt10 天前

bookmarked!

Bober_smart 的头像
Bober_smart10 天前

Bro 🤝

boan 的头像
boan10 天前

bro turned a massive codebase into map

Bober_smart 的头像
Bober_smart10 天前

That’s very nice to hear

Kostya | AI 的头像
Kostya | AI10 天前

Coordinating 80 agents over 540,000 lines is a lot, so the visual architecture flow is a smart touch.

Bober_smart 的头像
Bober_smart10 天前

Yes, that really is a smart solution

Gipp 🦅 的头像
Gipp 🦅10 天前

teams with massive repos should pay attention for smoother audits

Bober_smart 的头像
Bober_smart10 天前

I fully agree here

tenzo 的头像
tenzo10 天前

tracing every user flow is a huge win

Andrii 的头像
Andrii10 天前

Eighty agents and a map of 170 scenarios are powerful, and the marked open-ended questions add credibility

安叫兽|Bird🕊️ 🔶 BNB 的头像
安叫兽|Bird🕊️ 🔶 BNB10 天前

就想知道这张图里有多少连线是它脑补的

Vlad 的头像
Vlad10 天前

linking user journeys directly to files and tests makes complex systems far easier to investigate

Insomnia 的头像
Insomnia10 天前

we can improving it now

magsimich 的头像
magsimich10 天前

The physics is very good here

Bober_smart 的头像
Bober_smart10 天前

I really tried

FakerFill 的头像
FakerFill10 天前

80 is brave. I had five and they LGTM'd each other until prod was quietly burning:

Rohan 的头像
Rohan10 天前

How do the 80 agents avoid editing the same module at once?

111@@@555@@@888 的头像
111@@@555@@@88810 天前

视频是如何做的？

Nitesh 的头像
Nitesh10 天前

80 agents mapping 540K lines of code is absolutely wild

Ridark 的头像
Ridark10 天前

Everything is described so clearly in this terminal of yours, love the clarity

相关视频

i built a codebase classifier with Jev and this might be the solution to overengineered code that agents create what should I test Jev on next?
1:39

i built a codebase classifier with Jev and this might be the solution to overengineered code that agents create what should I test Jev on next?

vogel

99,160 次观看 • 1 个月前

Top 9 agentic use cases for Jev: (bookmark this) Jev handles semantic decisions that ordinary code cannot express reliably. It returns typed answers and probabilities, while code continues to cover the workflow. Here are 9 practical use cases for Jev: 1. Browser next action > Convert the current DOM state into a bounded action such as click, type, or stop. Code executes only valid operation-target pairs. There are already several open-source Jev web agents. 2. Context compaction > Decide which events from a long agent trace should remain. The selected text stays verbatim instead of being replaced with a generated summary. 3. Skill and context loading > Compare the current user turn against the available skills. Load only the instructions needed for that turn instead of filling the context window with every skill. 4. Typed tool-call compilation > Map a natural-language request to a function and fill its typed arguments. Each argument is evaluated separately before code allows execution. 5. Citation verification > Check whether a quoted passage exists and whether the surrounding evidence supports the claim. The output can be supported, unsupported, or contradicted. 6. Extraction verification > Run a cheap extractor first, then use Jev to verify questionable fields. Clean records stay on the fast path while uncertain ones reach a reasoning model. 7. Agent trace evaluation > Turn raw trajectories into queryable labels such as progress and repetition. This avoids asking another LLM to write a full review of every run. 8. Semantic regression tests > Replay a trace suite against a new agent build. Semantic checks can then pass or block prompt, model, tool, and policy changes in CI. 9. Jevgrep code search > Search a codebase by what the code does rather than its exact words. Jev scores candidate snippets and returns the most relevant code first. If you want to see the final pattern in practice, it is already implemented in the Beacon open-source project. It captures full sessions across Claude Code, Codex, Cursor, OpenCode, and 20+ agent harnesses, and then Jev identifies which workflows and corrections are worth learning from, so that a lesson discovered by one agent can become available to the others. GitHub repo: If you want to dive deeper, check out the full guide on Jev below ↓
0:24

Top 9 agentic use cases for Jev: (bookmark this) Jev handles semantic decisions that ordinary code cannot express reliably. It returns typed answers and probabilities, while code continues to cover the workflow. Here are 9 practical use cases for Jev: 1. Browser next action > Convert the current DOM state into a bounded action such as click, type, or stop. Code executes only valid operation-target pairs. There are already several open-source Jev web agents. 2. Context compaction > Decide which events from a long agent trace should remain. The selected text stays verbatim instead of being replaced with a generated summary. 3. Skill and context loading > Compare the current user turn against the available skills. Load only the instructions needed for that turn instead of filling the context window with every skill. 4. Typed tool-call compilation > Map a natural-language request to a function and fill its typed arguments. Each argument is evaluated separately before code allows execution. 5. Citation verification > Check whether a quoted passage exists and whether the surrounding evidence supports the claim. The output can be supported, unsupported, or contradicted. 6. Extraction verification > Run a cheap extractor first, then use Jev to verify questionable fields. Clean records stay on the fast path while uncertain ones reach a reasoning model. 7. Agent trace evaluation > Turn raw trajectories into queryable labels such as progress and repetition. This avoids asking another LLM to write a full review of every run. 8. Semantic regression tests > Replay a trace suite against a new agent build. Semantic checks can then pass or block prompt, model, tool, and policy changes in CI. 9. Jevgrep code search > Search a codebase by what the code does rather than its exact words. Jev scores candidate snippets and returns the most relevant code first. If you want to see the final pattern in practice, it is already implemented in the Beacon open-source project. It captures full sessions across Claude Code, Codex, Cursor, OpenCode, and 20+ agent harnesses, and then Jev identifies which workflows and corrections are worth learning from, so that a lesson discovered by one agent can become available to the others. GitHub repo: If you want to dive deeper, check out the full guide on Jev below ↓

rody

47,630 次观看 • 29 天前

this is pure f*cking gold for anyone running coding agents Jev founder Diogo Amogo wrote a PDF on building a Jev harness what their tests show: > up to 200x faster > up to 400x cheaper the model hasn't been the bottleneck for a while speed and cost both come from the harness you wrap around it • how to use it > give this PDF and the article below to Claude Code or Codex > ask it to rebuild its own setup around Jev • how it turns into a promotion > pick the agent workflow your team pays the most for > rebuild it in one evening > bring the before and after bill to your manager one evening of Jev engineering, and next week you're the one running a harness most teams haven't built yet
0:24

this is pure f*cking gold for anyone running coding agents Jev founder Diogo Amogo wrote a PDF on building a Jev harness what their tests show: > up to 200x faster > up to 400x cheaper the model hasn't been the bottleneck for a while speed and cost both come from the harness you wrap around it • how to use it > give this PDF and the article below to Claude Code or Codex > ask it to rebuild its own setup around Jev • how it turns into a promotion > pick the agent workflow your team pays the most for > rebuild it in one evening > bring the before and after bill to your manager one evening of Jev engineering, and next week you're the one running a harness most teams haven't built yet

Annatar.md

72,264 次观看 • 17 天前

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!
2:17

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

Andrew Ng

127,724 次观看 • 1 年前

This Chinese developer runs 9 agents on Claude Code under a GPT-5.5 orchestrator and they close 500 client tasks a month without a single assistant. His client work is closed without him, on a single laptop and only three subscriptions. The entire system lives on one MacBook Pro M4 with 128 GB of memory and subscriptions to Claude Code and GPT-5.5 cost him approximately $300 a month. There is no CRM, no team, no office only a terminal window with 9 parallel streams. The orchestrator works with a simple system prompt: «You are the orchestrator of a client inbox. Classify every incoming email into 4 categories: code, content, analysis, communication. Delegate to the corresponding worker agent. When the result is ready, check it for completeness, send it to the client on my behalf, and mark the task as closed. Do not ask clarifying questions.» And the orchestrator checks the inbox every 30 seconds, classifies fresh emails, and distributes them to 9 worker agents on Claude Code, each of whom is responsible for their own class of tasks. Here is an example of how one of them closes a request to refactor a client's auth module: Task: refactor user-auth module Broke the monolith into 3 files by responsibilities Added unit tests, coverage increased to 87% Renamed 4 functions to camelCase according to the style guide PR is ready for review, link below» And so about 50 cycles a day. By noon 25 tasks are closed, by dinner 50, and by the end of the month 500. On average, it takes about 7 minutes from the appearance of an email in the inbox to sending the result to the client. This is more than what a live team of 6 developers, copywriters and analysts working 8 hours a day closes. This is no longer an agency. This is a workstation where an orchestrator replaces a manager, and 9 worker agents replace the staff. The pipeline goes from inbox to closing 500 times a month without human participation at any step.
1:32

This Chinese developer runs 9 agents on Claude Code under a GPT-5.5 orchestrator and they close 500 client tasks a month without a single assistant. His client work is closed without him, on a single laptop and only three subscriptions. The entire system lives on one MacBook Pro M4 with 128 GB of memory and subscriptions to Claude Code and GPT-5.5 cost him approximately $300 a month. There is no CRM, no team, no office only a terminal window with 9 parallel streams. The orchestrator works with a simple system prompt: «You are the orchestrator of a client inbox. Classify every incoming email into 4 categories: code, content, analysis, communication. Delegate to the corresponding worker agent. When the result is ready, check it for completeness, send it to the client on my behalf, and mark the task as closed. Do not ask clarifying questions.» And the orchestrator checks the inbox every 30 seconds, classifies fresh emails, and distributes them to 9 worker agents on Claude Code, each of whom is responsible for their own class of tasks. Here is an example of how one of them closes a request to refactor a client's auth module: Task: refactor user-auth module Broke the monolith into 3 files by responsibilities Added unit tests, coverage increased to 87% Renamed 4 functions to camelCase according to the style guide PR is ready for review, link below» And so about 50 cycles a day. By noon 25 tasks are closed, by dinner 50, and by the end of the month 500. On average, it takes about 7 minutes from the appearance of an email in the inbox to sending the result to the client. This is more than what a live team of 6 developers, copywriters and analysts working 8 hours a day closes. This is no longer an agency. This is a workstation where an orchestrator replaces a manager, and 9 worker agents replace the staff. The pipeline goes from inbox to closing 500 times a month without human participation at any step.

Blaze

29,917 次观看 • 5 个月前

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this
13:23

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,568 次观看 • 4 个月前

THIS IS ACTUAL F*CKING GOLD Anthropic just shared one of the best tricks for Claude Code. The idea: stop configuring Claude Code by hand. One prompt, 44 seconds, and your whole .claude/ folder writes itself. 7 files, 162 lines, 2 cents. you typed one line and wrote zero of them. You just launch Claude Code like this: claude --model opus "set up this repo: ..." here's the split: → 3 Haiku 5.5 agents scan the repo before a single file gets written → one reads the stack, one reads the npm scripts, one hunts for risky paths → Opus 5.5 takes those three summaries and writes the actual config → 7 files land: CLAUDE.md, 3 agents, permissions, a format hook and a /ship skill the part everyone gets wrong: they write CLAUDE.md from memory. a config written without reading the repo is a guess, and you live with that guess for months. here the risk scan came back with 5 dangerous paths and those went straight into the permissions file, so the agent is blocked from them before it ever runs once. the scripts scan found 5 npm scripts, and the agents got wired to the ones that actually exist in this repo instead of generic placeholders. one prompt from you, 7 files from it, 0 lines written by hand. Haiku reads. Opus writes. You commit. JEV engineering is the same move one layer down: 1,867 forks this run - which file, which agent, allow or ask - resolved in code at 0.97 sharpness, and the split ones (0.59 on "allow or ask") come back to you instead of being guessed the full tree ▸ you paste one prompt describing the setup you want ▸ 3 Haiku 5.5 agents scan stack, scripts and risky paths in parallel ▸ every agent returns a summary, never raw files ▸ Opus 5.5 writes CLAUDE.md, the agents, permissions, the hook and the skill ▸ anything touching permissions comes back to you before it is written ▸ JEV resolves micro-forks in code and escalates only the split ones paste the tree and this prompt into Claude Code ↓ "Set up this repo for me: 1. First scan it with 3 Haiku 5.5 agents in parallel: one reads the stack and manifests, one reads the build and npm scripts, one finds paths that are dangerous to touch. 2. Each agent returns a summary only, never raw file contents. 3. Then write CLAUDE.md, 3 subagents, a permissions file, a format hook and a /ship skill, all based on what the scan actually found, not on defaults. 4. Every risky path from the scan goes into the deny list before anything runs. 5. Ask me before writing anything that grants permissions. Show me every file as a diff first. No writes until I say go." ↳ save it, this is the first thing you run in every new repo.
0:36

THIS IS ACTUAL F*CKING GOLD Anthropic just shared one of the best tricks for Claude Code. The idea: stop configuring Claude Code by hand. One prompt, 44 seconds, and your whole .claude/ folder writes itself. 7 files, 162 lines, 2 cents. you typed one line and wrote zero of them. You just launch Claude Code like this: claude --model opus "set up this repo: ..." here's the split: → 3 Haiku 5.5 agents scan the repo before a single file gets written → one reads the stack, one reads the npm scripts, one hunts for risky paths → Opus 5.5 takes those three summaries and writes the actual config → 7 files land: CLAUDE.md, 3 agents, permissions, a format hook and a /ship skill the part everyone gets wrong: they write CLAUDE.md from memory. a config written without reading the repo is a guess, and you live with that guess for months. here the risk scan came back with 5 dangerous paths and those went straight into the permissions file, so the agent is blocked from them before it ever runs once. the scripts scan found 5 npm scripts, and the agents got wired to the ones that actually exist in this repo instead of generic placeholders. one prompt from you, 7 files from it, 0 lines written by hand. Haiku reads. Opus writes. You commit. JEV engineering is the same move one layer down: 1,867 forks this run - which file, which agent, allow or ask - resolved in code at 0.97 sharpness, and the split ones (0.59 on "allow or ask") come back to you instead of being guessed the full tree ▸ you paste one prompt describing the setup you want ▸ 3 Haiku 5.5 agents scan stack, scripts and risky paths in parallel ▸ every agent returns a summary, never raw files ▸ Opus 5.5 writes CLAUDE.md, the agents, permissions, the hook and the skill ▸ anything touching permissions comes back to you before it is written ▸ JEV resolves micro-forks in code and escalates only the split ones paste the tree and this prompt into Claude Code ↓ "Set up this repo for me: 1. First scan it with 3 Haiku 5.5 agents in parallel: one reads the stack and manifests, one reads the build and npm scripts, one finds paths that are dangerous to touch. 2. Each agent returns a summary only, never raw file contents. 3. Then write CLAUDE.md, 3 subagents, a permissions file, a format hook and a /ship skill, all based on what the scan actually found, not on defaults. 4. Every risky path from the scan goes into the deny list before anything runs. 5. Ask me before writing anything that grants permissions. Show me every file as a diff first. No writes until I say go." ↳ save it, this is the first thing you run in every new repo.

Sprytix

24,378 次观看 • 4 天前

Jev has been blowing up lately. If you've got the Jev API but don't know how to play around with it yet, you can just copy this checklist. 1. jev-ultrafast A high-speed browser Agent built with Browser Use. Jev only judges "what to do, which element to click" at each step, and only calls the small model when typing is needed. Searching for a flight on Google Flights takes about 7 seconds. 2. fast-jev-compaction Context compression for Claude Code. Before each tool call, have Jev judge if there's anything still useful; delete the useless stuff, and keep the original text without rewriting it. 3. json-render Vercel Labs' generative UI framework. In experiments, Jev doesn't write JSON token by token; it just handles selecting components, properties, and layouts. 4. typesafe-mcp Best for people who just got the API. Plug Jev into Claude Code, Claude Desktop, Codex, and Pi, and do Choice / Score / Noul anytime. 5. jev-mcp Ready-made Agent judgment toolkit: fact-checking, content screening, semantic ranking, classification, and information extraction. 6. SemDecide Turn Jev into a command-line tool. Directly classify, score, and filter in the Shell—great for hooking up to crawlers, CI, and data pipelines. 7. jev-codex-router First have Jev judge how hard this round of programming tasks is, then decide the model tier, reasoning depth, and speed mode. 8. Winnow Context garbage collection for Claude Code. When Read / Bash / Grep spits out a ton of stuff, Jev first judges which parts are really relevant to the current task. 9. jev-review Before code review, run it through Jev first to pick out high-risk changes, then hand them off to a pricier big model or a human. Comes with a local dashboard. 10. Blink Use Jev as a code repository navigator. At each directory level, judge which files are most relevant to the current issue, then keep digging down. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓
0:24

Jev has been blowing up lately. If you've got the Jev API but don't know how to play around with it yet, you can just copy this checklist. 1. jev-ultrafast A high-speed browser Agent built with Browser Use. Jev only judges "what to do, which element to click" at each step, and only calls the small model when typing is needed. Searching for a flight on Google Flights takes about 7 seconds. 2. fast-jev-compaction Context compression for Claude Code. Before each tool call, have Jev judge if there's anything still useful; delete the useless stuff, and keep the original text without rewriting it. 3. json-render Vercel Labs' generative UI framework. In experiments, Jev doesn't write JSON token by token; it just handles selecting components, properties, and layouts. 4. typesafe-mcp Best for people who just got the API. Plug Jev into Claude Code, Claude Desktop, Codex, and Pi, and do Choice / Score / Noul anytime. 5. jev-mcp Ready-made Agent judgment toolkit: fact-checking, content screening, semantic ranking, classification, and information extraction. 6. SemDecide Turn Jev into a command-line tool. Directly classify, score, and filter in the Shell—great for hooking up to crawlers, CI, and data pipelines. 7. jev-codex-router First have Jev judge how hard this round of programming tasks is, then decide the model tier, reasoning depth, and speed mode. 8. Winnow Context garbage collection for Claude Code. When Read / Bash / Grep spits out a ton of stuff, Jev first judges which parts are really relevant to the current task. 9. jev-review Before code review, run it through Jev first to pick out high-risk changes, then hand them off to a pricier big model or a human. Comes with a local dashboard. 10. Blink Use Jev as a code repository navigator. At each directory level, judge which files are most relevant to the current issue, then keep digging down. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

rody

204,901 次观看 • 1 个月前

I created a skill for OpenClaw to use Claude Code It launches a CRON that checks background tasks every minute When done it wakes up the main thread Insane result: I can code on my project while working out and launch 10 Claude Code agents on the same project
7:26

I created a skill for OpenClaw to use Claude Code It launches a CRON that checks background tasks every minute When done it wakes up the main thread Insane result: I can code on my project while working out and launch 10 Claude Code agents on the same project

Melvyn • Builder

36,400 次观看 • 8 个月前

CLAUDE CODE + GROK + JEV - THE FILE WHERE THREE HEADS CLOSE A TICKET IN 9 MINUTES FOR $1.74 a month of this costs $208.80, the same 120 merges by hand are 300 hours and $28,500 ticket → plan → patch → tests → review → merge Claude Code on Opus 5.5 writes the patch, Grok reads it back and argues, Jev holds the gate and merges only on green tests three heads, and not one of them is allowed to push code to prod on its own 38 files read, 3 touched, +412 lines, 48 tests, and the first four failed, so the patch went back two minutes twenty later it was 48 of 48, and only then did Jev open the gate out of 120 patches Claude Code and Grok signed off on 78 straight away and had a fight about the other 22 those 22 arguments are the product, because a reviewer that never objects is just decoration the meter clocked $208.80 for the month, and to catch the human bill it would have to keep running for another 136 months and here is the brutal part of this file: 6 of the 94 merged tickets came back with bugs every one of them sat in the part of the code the test suite has never read, because coverage there is 61% two models in the same blind spot is not two opinions, it is one mistake signed twice save this and paste it into Claude Code - let it run your ticket through these three heads ↓
1:11

CLAUDE CODE + GROK + JEV - THE FILE WHERE THREE HEADS CLOSE A TICKET IN 9 MINUTES FOR $1.74 a month of this costs $208.80, the same 120 merges by hand are 300 hours and $28,500 ticket → plan → patch → tests → review → merge Claude Code on Opus 5.5 writes the patch, Grok reads it back and argues, Jev holds the gate and merges only on green tests three heads, and not one of them is allowed to push code to prod on its own 38 files read, 3 touched, +412 lines, 48 tests, and the first four failed, so the patch went back two minutes twenty later it was 48 of 48, and only then did Jev open the gate out of 120 patches Claude Code and Grok signed off on 78 straight away and had a fight about the other 22 those 22 arguments are the product, because a reviewer that never objects is just decoration the meter clocked $208.80 for the month, and to catch the human bill it would have to keep running for another 136 months and here is the brutal part of this file: 6 of the 94 merged tickets came back with bugs every one of them sat in the part of the code the test suite has never read, because coverage there is 61% two models in the same blind spot is not two opinions, it is one mistake signed twice save this and paste it into Claude Code - let it run your ticket through these three heads ↓

Sprytix

12,400 次观看 • 26 天前

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.
0:20

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 次观看 • 1 个月前

launched a swarm of 300 fly-agents and hooked them up to Jev Right before the main execution, the agents took full control of the prep work. In less than two minutes, this digital swarm swept through gigabytes of legacy clutter, aggressively indexing and sorting through forgotten docs, raw notes, and archived codebases across all my directories Then the main dashboard exploded with activity. Three hundred autonomous threads went to work in parallel writing code, hunting bugs, and running edge-case tests. Whenever an agent stumbled on complex logic, Jev instantly stepped in, validated the trace, and injected the exact pattern needed. Zero loops, pure high-speed execution Exactly four minutes in, the terminal dropped to dead silence All 300 tasks completed. Zero errors. 100% test coverage I opened the repo to find a rock-solid architecture, flawless code, and a clean deploy. Closed my laptop with a smile, while the agents, under Jev’s oversight, were already drafting the technical roadmap for the next sprint Bookmark this before you build your next multi-agent workflow
0:24

launched a swarm of 300 fly-agents and hooked them up to Jev Right before the main execution, the agents took full control of the prep work. In less than two minutes, this digital swarm swept through gigabytes of legacy clutter, aggressively indexing and sorting through forgotten docs, raw notes, and archived codebases across all my directories Then the main dashboard exploded with activity. Three hundred autonomous threads went to work in parallel writing code, hunting bugs, and running edge-case tests. Whenever an agent stumbled on complex logic, Jev instantly stepped in, validated the trace, and injected the exact pattern needed. Zero loops, pure high-speed execution Exactly four minutes in, the terminal dropped to dead silence All 300 tasks completed. Zero errors. 100% test coverage I opened the repo to find a rock-solid architecture, flawless code, and a clean deploy. Closed my laptop with a smile, while the agents, under Jev’s oversight, were already drafting the technical roadmap for the next sprint Bookmark this before you build your next multi-agent workflow

Bober_smart

17,409 次观看 • 1 个月前

how to use claude code mods like a top 1% user, step by step: give this to your agent before everyone catches on👇 1. set up Jev connect Jev to the model registry you want to use. check that the connection works and the listed models are available. 2. build your claude code mod open claude code 2.1.287 or later and paste this prompt: “build a mod called run-ledger. load plugin-authoring and use the API types for my installed version. create a dashboard that shows: - estimated cost per run, model, and source plugin where known - which model handles each task - each subagent’s status, latest action, and elapsed time include token counts, cache usage, and reported retries. count each request once. keep background tasks linked to their original run. use dated prices. label costs as API estimates, not subscription charges. show unknown when data is missing. connect the mod to my existing Jev setup. give Jev the task, available models, prices, budget, and relevant past results. ask it to recommend a model and explain why. start with recommendations. make automatic routing optional for eligible subagents. show the recommended model, actual model, result, and cost. include Jev’s own cost. keep state across hot reloads. add details and export. the dashboard itself must make no model calls. validate the plugin. test rendering, costs, attribution, and duplicate counting. give me steps for a live test.” 3. test the setup allow hot reload when prompted. run a simple task, a subagent task, and a mod-triggered model call. check that the dashboard updates, each request counts once, and Jev’s recommended model can actually run the task. 4. install the working mod ask claude to copy it out of the temporary folder and install it as a persistent plugin. see the cost. choose the model. check the result.
0:33

how to use claude code mods like a top 1% user, step by step: give this to your agent before everyone catches on👇 1. set up Jev connect Jev to the model registry you want to use. check that the connection works and the listed models are available. 2. build your claude code mod open claude code 2.1.287 or later and paste this prompt: “build a mod called run-ledger. load plugin-authoring and use the API types for my installed version. create a dashboard that shows: - estimated cost per run, model, and source plugin where known - which model handles each task - each subagent’s status, latest action, and elapsed time include token counts, cache usage, and reported retries. count each request once. keep background tasks linked to their original run. use dated prices. label costs as API estimates, not subscription charges. show unknown when data is missing. connect the mod to my existing Jev setup. give Jev the task, available models, prices, budget, and relevant past results. ask it to recommend a model and explain why. start with recommendations. make automatic routing optional for eligible subagents. show the recommended model, actual model, result, and cost. include Jev’s own cost. keep state across hot reloads. add details and export. the dashboard itself must make no model calls. validate the plugin. test rendering, costs, attribution, and duplicate counting. give me steps for a live test.” 3. test the setup allow hot reload when prompted. run a simple task, a subagent task, and a mod-triggered model call. check that the dashboard updates, each request counts once, and Jev’s recommended model can actually run the task. 4. install the working mod ask claude to copy it out of the temporary folder and install it as a persistent plugin. see the cost. choose the model. check the result.

Avid

47,276 次观看 • 25 天前

ANTHROPIC LEAKED A FILE WHERE 5 AGENTS WITH JEV BUILD A $1.2M A YEAR SYSTEM IN 30 MINUTES you pay $3.70 and walk away with an asset that can do $1.2M a year repo → data model → API → UI → evals no layer starts until the one under it is closed, and that edge is what turns five scripts into a system the operator on Haiku 4.5 brings up the repo and CI, the architect on Opus 5 lays down the data model and migrations two builders on Sonnet 5 run API and UI in parallel, and the reviewer on Opus 5.5 can keep finished code out of prod the evals were sitting in the file before the first line of code existed at minute zero there was not a single file, by the end it is a working product with payments and tests five agents cover in half an hour what a human team bills for a quarter JEV hands one line between layers instead of the whole history, so the next agent never re-reads the project and the run costs $3.70 instead of $370 the build takes 30 minutes, the first customers show up weeks later save this and paste it into Claude Code - let it assemble those 5 layers for you ↓
1:20

ANTHROPIC LEAKED A FILE WHERE 5 AGENTS WITH JEV BUILD A $1.2M A YEAR SYSTEM IN 30 MINUTES you pay $3.70 and walk away with an asset that can do $1.2M a year repo → data model → API → UI → evals no layer starts until the one under it is closed, and that edge is what turns five scripts into a system the operator on Haiku 4.5 brings up the repo and CI, the architect on Opus 5 lays down the data model and migrations two builders on Sonnet 5 run API and UI in parallel, and the reviewer on Opus 5.5 can keep finished code out of prod the evals were sitting in the file before the first line of code existed at minute zero there was not a single file, by the end it is a working product with payments and tests five agents cover in half an hour what a human team bills for a quarter JEV hands one line between layers instead of the whole history, so the next agent never re-reads the project and the run costs $3.70 instead of $370 the build takes 30 minutes, the first customers show up weeks later save this and paste it into Claude Code - let it assemble those 5 layers for you ↓

Sprytix

14,316 次观看 • 1 个月前

Coding agents waste a lot of tokens just figuring out how a site is structured before they can touch it. Map it once instead. Agentmap crawls any site and turns it into a structured map, pages, flows, and the data on each, that any agent loads in one shot. claude code, cursor, a browser agent, all of them skip the blind exploration and go straight to the task. Open source, powered by hyperbrowser ↓
0:27

Coding agents waste a lot of tokens just figuring out how a site is structured before they can touch it. Map it once instead. Agentmap crawls any site and turns it into a structured map, pages, flows, and the data on each, that any agent loads in one shot. claude code, cursor, a browser agent, all of them skip the blind exploration and go straight to the task. Open source, powered by hyperbrowser ↓

Hyperbrowser

15,640 次观看 • 3 个月前

This is f*cking insane. This Claude Code tip saved me thousands of dollars. once Opus 5.5 is your main model, stop burning it on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and ships the final code Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split anyone still running one model for everything is paying Opus prices to decide whether a file exists - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳
0:31

This is f*cking insane. This Claude Code tip saved me thousands of dollars. once Opus 5.5 is your main model, stop burning it on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and ships the final code Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split anyone still running one model for everything is paying Opus prices to decide whether a file exists - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

48,964 次观看 • 24 天前

Jev founder, Diogo Almeida, just put out a PDF on building a Jev harness for coding agents the claim: 200x faster, 400x cheaper the model stopped being the bottleneck a while ago. the harness around it is where the cost and the speed actually live five decisions sit on every loop, and only one of them writes code hand this PDF and the article below to your Claude Code or Codex instance and let it rebuild its own setup your agent gets a better harness tonight, and monday looks different than it would have 👇
0:23

Jev founder, Diogo Almeida, just put out a PDF on building a Jev harness for coding agents the claim: 200x faster, 400x cheaper the model stopped being the bottleneck a while ago. the harness around it is where the cost and the speed actually live five decisions sit on every loop, and only one of them writes code hand this PDF and the article below to your Claude Code or Codex instance and let it rebuild its own setup your agent gets a better harness tonight, and monday looks different than it would have 👇

Hanako

37,887 次观看 • 1 个月前

Claude Code tip, and it's absolute free f*cking gold: run Opus 5.5, Sonnet 5.5 and Fable 5.1 as one team and stop burning Opus tokens on routine work the setup in one line: plan on high, delegate on medium, keep Fable on call • who does what > Opus 5.5 on high - plans and ships the code > Sonnet 5.5 on medium - explorer reads code, worker edits and runs tests, researcher pulls docs > Fable 5.1 via /advisor fable - reads the whole session and speaks up only when it matters • when Fable 5.1 steps in -> before a plan: is this the right approach? -> when an error repeats: am I digging in the wrong place? -> before "done": what did I miss? Jev engineering takes it one layer lower: which file, which tool, retry or stop all go to Jev in under half a second, so the big models only see the real forks paste this into Claude Code ↓ "Rebuild my Claude Code setup: 1. Find subagents in ~/.claude/agents and .claude/agents that fit explorer, worker and researcher. Draft only the missing ones. Set each to model: sonnet, effort: medium. List any that pin a different model and leave them 2. In ~/.claude/settings.json set effortLevel to high and advisorModel to fable. 3. Report anything that disables the advisor (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, flag-fetching blockers) and CLAUDE_CODE_EFFORT_LEVEL. Change nothing. 4. Add to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done. Show every change as a diff. No edits until I say go." ↳
0:24

Claude Code tip, and it's absolute free f*cking gold: run Opus 5.5, Sonnet 5.5 and Fable 5.1 as one team and stop burning Opus tokens on routine work the setup in one line: plan on high, delegate on medium, keep Fable on call • who does what > Opus 5.5 on high - plans and ships the code > Sonnet 5.5 on medium - explorer reads code, worker edits and runs tests, researcher pulls docs > Fable 5.1 via /advisor fable - reads the whole session and speaks up only when it matters • when Fable 5.1 steps in -> before a plan: is this the right approach? -> when an error repeats: am I digging in the wrong place? -> before "done": what did I miss? Jev engineering takes it one layer lower: which file, which tool, retry or stop all go to Jev in under half a second, so the big models only see the real forks paste this into Claude Code ↓ "Rebuild my Claude Code setup: 1. Find subagents in ~/.claude/agents and .claude/agents that fit explorer, worker and researcher. Draft only the missing ones. Set each to model: sonnet, effort: medium. List any that pin a different model and leave them 2. In ~/.claude/settings.json set effortLevel to high and advisorModel to fable. 3. Report anything that disables the advisor (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, flag-fetching blockers) and CLAUDE_CODE_EFFORT_LEVEL. Change nothing. 4. Add to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done. Show every change as a diff. No edits until I say go." ↳

Mr. Buzzoni

144,764 次观看 • 26 天前

this is pure f*cking gold for anyone doing Jev engineering the skill that teaches Claude Code to build on Jev the right way, from TypeSafe themselves without it, coding agents send Jev one question at a time and guess the field names with it, the order is set before a single line gets written: docs -> behaviour -> judgments -> one request -> code decides the two-page breakdown of every rule: > the failure each of its 11 instructions is there to prevent > Choice, Noul or Score, picked at a glance > a prompt skeleton you paste straight into your agent 12.2x that's how far the bill fell in TypeSafe's cookbook when 13 questions went out in one call one short file, and your agent stops paying for decisions it should have batched
0:24

this is pure f*cking gold for anyone doing Jev engineering the skill that teaches Claude Code to build on Jev the right way, from TypeSafe themselves without it, coding agents send Jev one question at a time and guess the field names with it, the order is set before a single line gets written: docs -> behaviour -> judgments -> one request -> code decides the two-page breakdown of every rule: > the failure each of its 11 instructions is there to prevent > Choice, Noul or Score, picked at a glance > a prompt skeleton you paste straight into your agent 12.2x that's how far the bill fell in TypeSafe's cookbook when 13 questions went out in one call one short file, and your agent stops paying for decisions it should have batched

Mr. Buzzoni

28,212 次观看 • 28 天前

this is f*cking dangerous. i'm using it. agencies quote $25,000+ and 8 weeks for an app like this i sent one message to a group chat in Teamily AI (Teamily AI). 45 minutes later 3 AI agents had built it, tested it and handed it back my take: a few people and a few agents in one group, all working from the same context, beat one person juggling a stack of agents alone in a normal chatbot you're the middleman, pasting one answer into the next prompt. here the agents read the same thread and hand work to each other my whole brief was one line: "like Splitwise but simpler". then i mostly watched: → the Software Architect agent mapped every screen, then tagged the Content Creator on its own → the Content Creator named it Evenly ("split bills, keep friends") and wrote the copy for every screen → the Frontend Developer built it in Website Builder: sign up and login, groups, invite links, who owes whom, settle up, a read-only admin view and its own database with 12 tables → then it checked its own work: ran 129 tests, signed up as a brand new user and went through 34 screens → one more message from me and it added receipt scanning: snap a photo of the receipt, it pulls out the items and splits them zero code from me. the build itself took 26 minutes honestly the part that got me: during its own test one save looked stuck. it went through the server logs and the database before it trusted the result i ran this one solo, so more people in the chat is still my bet. 3 agents alone already worked like a small team that's the whole point of Teamily AI: a workspace where humans and agents collaborate. if you run a small business or a small team, this is the one to try want to copy it: make a group, add a Software Architect, a Content Creator and a Frontend Developer, describe your app in one line my invite link to try Teamily AI is in the first reply bookmark this and send it to the friend who's been "about to build an app" for years
0:43

this is f*cking dangerous. i'm using it. agencies quote $25,000+ and 8 weeks for an app like this i sent one message to a group chat in Teamily AI (Teamily AI). 45 minutes later 3 AI agents had built it, tested it and handed it back my take: a few people and a few agents in one group, all working from the same context, beat one person juggling a stack of agents alone in a normal chatbot you're the middleman, pasting one answer into the next prompt. here the agents read the same thread and hand work to each other my whole brief was one line: "like Splitwise but simpler". then i mostly watched: → the Software Architect agent mapped every screen, then tagged the Content Creator on its own → the Content Creator named it Evenly ("split bills, keep friends") and wrote the copy for every screen → the Frontend Developer built it in Website Builder: sign up and login, groups, invite links, who owes whom, settle up, a read-only admin view and its own database with 12 tables → then it checked its own work: ran 129 tests, signed up as a brand new user and went through 34 screens → one more message from me and it added receipt scanning: snap a photo of the receipt, it pulls out the items and splits them zero code from me. the build itself took 26 minutes honestly the part that got me: during its own test one save looked stuck. it went through the server logs and the database before it trusted the result i ran this one solo, so more people in the chat is still my bet. 3 agents alone already worked like a small team that's the whole point of Teamily AI: a workspace where humans and agents collaborate. if you run a small business or a small team, this is the one to try want to copy it: make a group, add a Software Architect, a Content Creator and a Frontend Developer, describe your app in one line my invite link to try Teamily AI is in the first reply bookmark this and send it to the friend who's been "about to build an app" for years

Argona

14,935 次观看 • 19 天前