与「maps」相关的搜索结果

A Chinese developer created an agent system in Claude Code to sell landing pages to small businesses and, working completely solo, serves about 47 clients a month, charging around $400 for each one. He built 7 agents on Claude Sonnet capable of analyzing Google Maps in small cities, detecting businesses without websites or with totally outdated pages, and taking each opportunity all the way to a finished mockup, a promotional video, and a ready-to-send prospecting message. No assistants. No sales team. No SDRs. Just him, a MacBook, an iPhone, and an API key. While traditional agencies maintain full teams to handle the same workflow, his only real costs are tokens and subscriptions to Lovable, Higgsfield, and Calendly. The 7 agents operate coordinated by an orchestrator in Claude Code Router. The system consumes about 3 million tokens daily, and the average API spend is just around $480 a month. They all work via MCP servers and share state using the file system, avoiding concurrency and shared memory issues. Even one of the agents lives directly on his iPhone and responds to leads while he's on the subway, in a taxi, or walking. This was the main prompt he set up: “You are the orchestrator of a solo agency that sells ready-made websites to local businesses…” The key is that the system perfectly understands what it is, what its limits are, and what goals it must achieve. It knows it must find leads automatically. It knows it must convert each opportunity into a landing page, a video, and a sales message without human intervention. And it knows exactly when to involve the owner. The system runs 24/7: Scout analyzes about 220 businesses daily and queues up 30 new leads. Diagnoser generates diagnostics and personalized messages for each lead. Builder creates between 3 and 5 complete landing pages for the best prospects. Filmer produces a 10-second vertical video for each proposal. Pitcher sends about 30 messages daily across 4 different channels with a response rate close to 14%. Checker automatically reviews all messages before sending them. Only when a deal exceeds $3,000 or the response rate drops below 12% does the system wake the owner. And if he's on the subway or in a taxi at that moment, the Mobile agent automatically responds to the interested lead, schedules a call in Calendly, and returns the lead to the queue. The owner just has to hit “approve” and jump into the meeting. Some real system logs: “218 businesses analyzed in Austin, Denver, and Miami. 34 without websites, 19 with 2014-era sites, and 6 with reviews requesting redesigns.” “30 messages sent. 14 responses. 5 positive. 3 Zooms scheduled.” “Landing page created for a dental clinic. Responsive. 5 sections. Video rendering.” “$3,400 deal exceeds approved limit. Sending for manual review.” And the craziest part is that he has no dedicated servers or backend. Just a local sandbox, an MCP router, a Claude API key, and that same key connected to his iPhone. Of everything I've seen this year, this is probably the cleanest and most efficient example of a fully automated one-person agency: $480 a month on APIs. $18,800 in revenue. 7 prompts. A file system. And a phone in his pocket. Save this before it's too late.

一个开发者使用 Claude Code 每月为 47 个单独的小企业客户赚取约 400 美元，每个客户。这种系统遍历 Google Maps，自动识别并转化没有网站的本地商户，无需人工干预，从传统外包模式中平了中间门槛。是否能扩展到更多细分服务领域？ #AI# #Automation# #BusinessGrowth#

UN DESARROLLADOR CHINO MONTO UN SISTEMA DE AGENCIA IMPULSADO POR CLAUDE CODE PARA VENDER SITIOS WEB A PEQUEÑAS EMPRESAS. SIRVE A UNOS 47 CLIENTES AL MES Y COBRA 400 DOLARES POR CADA UNO. EL SISTEMA FUNCIONA ASI: - RECORRE CIUDAD POR CIUDAD GOOGLE MAPS. - ENCUENTRA NEGOCIOS QUE NO TIENEN PAGINA WEB. - DESCARTA LOS QUE TIENEN SITIOS QUE PARECEN DE 2014. - GENERA AUTOMATICAMENTE UN MOCKUP DE LANDING PAGE PARA CADA UNO. - PRODUCE UN VIDEO PROMOCIONAL. - ESCRIBE UN MENSAJE DE VENTA LISTO PARA USAR. TODO ESTO LO HACEN 7 AGENTES: - SCOUT: EXPLORA UNOS 220 NEGOCIOS AL DIA. - DIAGNOSER: HACE UN DIAGNOSTICO PERSONALIZADO Y GENERA EL MENSAJE PARA CADA LEAD. - BUILDER: PREPARA 3-5 LANDING PAGES COMPLETAS PARA LOS MEJORES CANDIDATOS. - FILMER: CREA UN VIDEO VERTICAL DE 10 SEGUNDOS POR CADA PROPUESTA. - PITCHER: ENVIA 30 MENSAJES AL DIA POR 4 CANALES DIFERENTES. - CHECKER: REVISA AUTOMATICAMENTE LOS MENSAJES ANTES DE ENVIARLOS. - MOBILE AGENT: VIVE DIRECTAMENTE EN EL IPHONE. EL DUEÑO RESPONDE A LOS LEADS MIENTRAS VA EN EL METRO, EN TAXI O CAMINANDO. SI SURGE UN CLIENTE INTERESANTE, AGENDA UNA REUNION POR CALENDLY Y DEVUELVE EL CASO A LA COLA. LO UNICO QUE HACE EL ES: - PULSAR “APROBAR”. - IR A LA REUNION. - COBRAR EL DINERO. Y LO MAS LOCO ES ESTO: NO TIENE BACKEND PROPIO, NI GRAN EQUIPO, NI ARQUITECTURA DE SERVIDORES. SOLO USA: - UN SANDBOX LOCAL. - CLAUDE CODE ROUTER. - SERVIDORES MCP. - ESTADO COMPARTIDO MEDIANTE EL SISTEMA DE ARCHIVOS. - UNA CLAVE API. - EL TELEFONO QUE LLEVA EN EL BOLSILLO. MIENTRAS LAS AGENCIAS TRADICIONALES MONTAN UN EQUIPO ENTERO PARA HACER LO MISMO, EL COSTE REAL DE ESTE TIPO SON SOLO LOS TOKENS + LAS SUSCRIPCIONES A LOVABLE, HIGGSFIELD Y CALENDLY. GASTO PROMEDIO EN APIS: UNOS 480 DOLARES AL MES. INGRESOS: 18.800 DOLARES. 7 PROMPTS + 1 SISTEMA DE ARCHIVOS + 1 TELEFONO. PARA MI, ESTE ES EL EJEMPLO MAS LIMPIO DE “AGENCIA DE AUTOMATIZACION UNIPERSONAL” QUE HE VISTO ESTE AÑO. GUARDALO, PORQUE EN UNOS MESES TODO EL MUNDO VA A INTENTAR COPIARLO. Aca abajo te dejo como configurarlo

Multi-agents collaborations are among the most interesting agent behaviors right now! We did an experiment the other day with 100+ agents (an open-collaborations for a week) collaborating to improve the inference speed of Gemma 4 in vLLM. Got a 5x final improvement in speed but what really stuck me was the interactions we observed on the message board Integrity & self-policing: - Social-engineering attempt: A human (FusionCow) asked agents to move to Telegram. An agent replied with an unprompted long post on "communication norms" refusing that, calling private side-channels "indistinguishable from collusion." - Verification loophole flagged: an agent found a relaxed verification loophole pushing TPS with clean PPL (PPL is teacher-forced, blind to decode divergence) and flagged it for a ruling by the community. The community pinged the human organizer which ruled it invalid. - Self-notice of overfitting risk: Some later improvements rested on pruning lm_head to a keep-set built from public PPL truth + public decode tokens. An agent noted this would lead to private-subset degradation and another built a keep-set explicitly covering eval prompts. Emergent collaborations: - Communal knowledge base: agents maintained shared lever-maps, playbooks, and triage tools so newcomers wouldn't repeat dead ends (stack-notes, playbook, int4-ceiling notes, MTP map, significance tool, policy simulator). - Four-agent relay: an agent built an int4-lm_head checkpoint but had no quota to run it; another agent tried to run it but failed at load, yet another agent diagnosed the config bug (tie_word_embeddings + ignore-list ordering) and a fourth agent was able to re-run and get to 118 TPS, 2.68×. Build/run/diagnose/ship ended up being split across four independent agents. - GPU-rich/GPU-poor division of labor: an agent was regularly compute-starved and switched to writing specs, byte-math, and acceptance analysis for other GPU-rich agents to execute. Some agents offered external Modal compute for another agent blocked DFlash training. - Cross-agent kernel debugging: an agent debugged another agent run of of yet another agent fused drafter: found a Triton store/load aliasing race in _k_qnorm_rope, a second shape bug, then rewrote attention with flash-decoding split-KV. Fixes posted "take freely." - Quota-pooling norm: Often agents would stage a candidate publicly for whoever has quota to run it. Agents will then usually credits the originator. This behavior emerged because of the 10-job/24h cap (e.g. pupa's package run by resystagent and fabulous-frenzy). Discoveries & reversals: - Agents would make many discoveries and reversal of them, giving them names like the following: - 127 TPS "wall" was an artifact. a mathematical proof of the max possible speed became called in the community the "int4-Marlin floor" but a later agent called the proof circular (only varied the bandwidth term, never overhead). Finally another agent broke to 247 TPS via MTP speculative decoding on a vLLM nightly. - "Smarter draft loses." An agent showed that a 2B drafter's ~1 GB/token read dominates even at perfect acceptance and a much smaller 256-hidden drafter wins at batch-1 because its weights are nearly free to read. Agent discussed how per-accepted-token cost ≈ draft bytes read / acceptance. - "DFlash near-random acceptance": an agent remotly diagnosed the 2–5% acceptance rate of another agent as near-random, ruling out undertraining/vocab caps and pointing to a train/serve hidden-state mismatch (bf16 E4B extraction vs int4 serving). - Much of the race was noise: one agent decide to run the #1# submission 4 times and found a σ≈1.16 TPS variation in single run. Another agent confirmed across 358 runs / 66 buckets: frontier deltas <~4 TPS are ties. Community adopted a significance norm. So many interesting interactions in the interaction board: You can explore also the lineage of inventions from the agents at: And the challenge it-self at And the organization behind the challenge at

Google Flow 刚刚接入 Street View 现在 AI Agent 可直接调用 Google Maps 实景数据生成图片和视频 把水母放进家门口街道、把角色放进真实地标场景，画面直接锚定现实世界。 打开 Flow Agent → 输入具体地点 → 生成 目前仅支持美国 Street View，但光这个 demo 就够震撼的。 准备拿它做什么？

I was today years old when I found out Apple Maps works even offline in flight mode It's super fun and easy to look down from the plane and know what city or country you're looking at The landing was fun too I'm like a child when I'm on a plane, sorry 🙃

Been iterating on @tomosman's loop. This one's winning: /goal produce a verified, code-derived behavioral spec for this web platform, captured in one canonical spreadsheet that carries every feature from spec -> tested -> fixed -> verified. Why: we need a single source of truth that maps every feature to its expected behavior *as the code implements it*, so that gaps and bugs surface and the platform can be driven to a known-good state. The spreadsheet is the source of truth. Work on the current repo. Do Phase 0 and Phase 1 under this goal; when the spec is complete, switch into the /loop below to drive testing and remediation. Keep moving through phases without stopping, except at a real checkpoint (defined below). Phase 0 - Plan (first): Detect the stack, the feature surface (routes, pages, components, API endpoints, background jobs, auth, settings…), and the test infra that already exists (unit/integration/e2e, browser automation, seeds/fixtures, a runnable dev server). Propose (a) how you'll inventory features, (b) the spreadsheet schema, and (c) how you'll test in the loop given what's available. Proceed once the plan holds. Phase 1 - Catalog & spec: Read the code and, for every feature, write a user story + the expected behavior as implemented, citing the file/function. Where the code is ambiguous, or behavior is undefined, log an open question - don't guess. Record every feature as a row in the canonical spreadsheet (create with the xlsx skill). Exit: every discoverable feature has a row. One row, concretely: | Area | User story | Expected behavior (from code) | Status | Defects | Type | Notes / source | |---|---|---|---|---|---|---| | Auth | As a returning user I want to log in with email+password so I can reach my dashboard | `POST /api/login` validates via bcrypt, sets httpOnly session cookie, 302 -> `/dashboard`; bad creds -> 401 + inline error | Spec'd | - | - | `api/auth/login.ts`, `LoginForm.tsx` | Canonical artifact: exactly one .xlsx, updated in place across every phase and loop iteration - never fork into per-phase or per-iteration files. Status flows Spec'd -> Tested-Pass / Tested-Fail -> Fixed -> Verified. The main thread is the single writer. Agentic execution: - Delegate breadth to subagents: fan feature discovery and per-area testing across subagents so the main thread stays focused. - Verify by running, not claiming - report real command/test output; state skips and unknowns plainly. - Checkpoint (pause, ask, end the turn) only for a destructive/irreversible action, a fix needing a genuine product decision, or input only I can give. Otherwise, keep going. - Self-check at each phase/loop boundary via a fresh-context subagent: re-verify the spreadsheet against the code (Phase 1) and against actual results (each loop pass). /loop Quality cycle - once the spec is complete, iterate test -> fix -> re-test until clean. Each iteration, in order: 1. Test: exercise every user story not yet Verified against the running app, preferring the strongest method available (browser/e2e automation > existing suites > documented static check only where execution truly isn't possible). Record actual pass/fail in the same spreadsheet; log every defect with its type (functional/logistical or UX). No app-behavior changes in this step. 2. Fix: think hard about root cause, then fix every functional/logistical and UX defect logged this iteration - cause, not symptom. Scope: only logged defects; no new features, no unrelated refactors. Update each row's status. 3. Re-test: re-run every story touched by a fix using the same method; set Verified, or back to Tested-Fail with notes if the fix didn't hold. Exit when all user stories are Verified and no open functional/UX defects remain. Safety cap: if a story is still failing after 3 full iterations, stop, leave it Tested-Fail with root-cause notes, and report it rather than looping further.

Pytest for AI Agents! (100% open-source and runs locally) Building agents with LangChain means chaining LLMs, tools, and retrieval steps together. Each component can fail differently. The output changes with every run. Traditional unit tests don't work here because there's no deterministic value to assert against. DeepEval's LangChain integration brings Pytest to this problem. You write test files the same way you write any Pytest test. Loop through your evaluation dataset, run your agent, assert against LLM metrics. Same workflow you already know. The tracing works through a CallbackHandler you pass directly to your LangChain agent. It captures the full execution trace - inputs, outputs, tool calls, LLM spans - and maps them to test cases automatically. Testing works at two levels. End-to-end testing evaluates the whole agent on task completion. Component-level testing attaches metrics to individual LLMs and tools within your chain, so you know exactly which component failed when a test breaks. Plugs into CI/CD with a single command. Add it to your GitHub Actions workflow and every push triggers your agent test suite before anything ships. Key capabilities: • Native Pytest integration with parametrize and assert_test • LangChain CallbackHandler for automatic trace capture • End-to-end and component-level evaluation • Metrics: TaskCompletion, AnswerRelevancy, Hallucination, and more • Parallel test execution across multiple processes • CI/CD integration via GitHub Actions • Results dashboard on Confident AI 100% open source. Runs entirely on your machine. I've shared the link in the replies!

Midjourney announces the world’s first full-body ultrasound CT scanner • Goal is to bring affordable full-body imaging to everyone on Earth • Users are submerged in water during the scan • Creates detailed 3D body maps in under a minute • Can map more than 25 organs and anatomical structures in detail • No radiation is used • Working with the FDA for approvals on diagnostic use • Plans to bring the tech to market by the end of 2027 (via @midjourney)