No-Code Agentist

just read this. Elon's team accidentally destroyed the business of hiring people to do your boring work an executive assistant costs $68,000 a year. an agency bills $2,000 a month for the same pile of small jobs. this does the pile for $0 on a plan a lot of you already pay for and the two labs everyone compares him to have already admitted, on their own help pages, that theirs cannot do it OpenAI, about their own agent: "at launch, Cloud browser cannot sign in to websites or complete payments" Anthropic, about theirs: "Your computer needs to be awake and the Claude Desktop app needs to be open" it's called Grok Bot. it logs into your real accounts and keeps working with the laptop shut one of them has been running for a month talking to 40 factories in Vietnam on WhatsApp, negotiating price and ordering samples. no api, no integration, no code. it used WhatsApp the way a person does the whole method fits on a napkin: → one bot, one job, never two → sign into a tool once and every other bot inherits that session, so you only ever do it once → connect Gmail through the plugin, never the bot's browser, or it gets blocked for looking like a datacenter → put 2 to 6 of them in one group chat and they hand work to each other without you in the room → write the job the way you would brief a new hire, not the way you prompt a model → tell it what to do when it cannot confirm something or it will quietly invent it the two hours of clicking before your real day starts is the exact shape of work it takes. not your judgment, not your taste, not the thing you actually get paid for every founder reading this pays somebody for those two hours the bot is free. being the one who actually builds it this week is the whole edge six rules is the short version. the full build is in the piece below ↓

Oasis - Best AI Tool Finder https://t.co/HzXrxvcLpB Oasis is a shared workspace in which employees and AI agents collaborate through persistent “rooms.” Teams can create cloud-hosted agents, connect external or local agents such as Claude Code, assign tools and models, schedule work, and edit documents, spreadsheets, or code artifacts alongside agents. The company positions the product as an operating environment for mixed human-agent teams rather than a conventional chatbot or single-user agent builder (official website; documentation). The product targets technology companies and operational teams adopting multiple AI agents but lacking a unified interface for context, handoffs, permissions, and supervision. The underlying need is credible: as organizations deploy more agents, coordination, governance, approvals, shared memory, and cost control become increasingly important. The strongest investment signal is the founding team. Both founders previously worked as forward-deployed engineers at Palantir, giving them relevant experience deploying software and AI systems into operational customer environments. Oasis is also part of a16z Speedrun’s sixth cohort, and the accelerator profile lists five employees in New York (a16z Speedrun). The principal concern is the absence of commercial validation. No reliable public information was found for revenue, paying organizations, active teams, agent runs, retention, conversion, customer references, or gross margin. The product also competes directly with well-capitalized platforms, including OpenAI’s workspace agents, Dust, Microsoft Copilot Studio, Slack Agentforce, Relevance AI, Lindy, and Taskade. Final Decision: Watch. Oasis has a capable team, a relevant product thesis, and a potentially large market, but current public evidence does not justify formal investment diligence. An upgrade to DD requires retained paying teams, evidence of differentiated multi-agent workflows, and credible unit economics.

Your private AI agent shouldn’t require Docker and a terminal. Skales is a local-first desktop AI agent for people who want an agent to work with their files, browser, calendar, email, and code. It helps you delegate multi-step work from your own computer by combining background goals with desktop tools, coding workflows, and a choice of hosted or local models. Key features: • One-click desktop setup – install it on Windows, macOS, or Linux without Docker or terminal setup • Background goals – hand it a multi-step goal, close the chat, and let it continue until completion or a decision is needed • Built-in code workflows – bind a folder, review inline diffs, run tests, and undo file changes • Flexible model access – start with the built-in trial, connect 15+ providers, or run offline with Ollama or LM Studio • Mobile access – pair Android or iOS with your desktop via QR to use its tools remotely Public GitHub repo; the current Skales app is closed source under BSL 1.1. Link in the reply 👇

Build Your Own AI Agent on Farebox From Zero to Live in Minutes Farebox Agents are fully live, and here is everything you need to know what they are, how to build one, and how to use it end to end. A Farebox Agent is a hosted AI worker you configure once and deploy permanently on the Farebox network. It runs on whatever LLM you choose GPT-4o, Claude 3.5 Sonnet, Gemini 2.5 Flash, Llama 3, and more. You write the system prompt, define its personality and rules, attach skills, set spending caps, and it is live. No servers to manage, no infrastructure to maintain, no provider API keys to juggle. Farebox sits between your agent and every major LLM provider, handles all the routing, and bills everything unified in SOL and $FBOX. Creating an agent takes under two minutes. Head to https://t.co/pLUq0E6lX9, open your dashboard, and hit Create Agent. Give it a name, write a short description for its public profile, and write your system prompt this is the core logic that defines what your agent does and how it behaves. Then pick a model from the dropdown, attach any skills you want (more on that below), set a daily and monthly spending cap so costs never run away, and choose whether to make it public so it shows up in the gallery. Finally, give it a .fbox slug a short lowercase identifier that becomes its permanent address on the network. Hit Create Agent and Mint Key, and you instantly receive a dedicated API key for that agent. Skills are what separate a basic chatbot from a real capable agent. When you create an agent you can attach pre-built capabilities like Summarize, Draft Email, Code Review, Debug Code, Risk Analysis, Text to SQL, Sentiment Analysis, Data Extractor, Translate, and more. These are not just prompt shortcuts they are structured task modules that take defined inputs and return clean, formatted outputs. Your agent can handle complex, repeatable workflows without you writing custom logic for each one. Using your agent is straightforward. There is a built-in chat interface at https://t.co/zYoYohbXEY so anyone can open it and start talking immediately. For developers, the agent exposes a fully OpenAI-compatible API endpoint at https://t.co/ywQPN8ttYw which means if you are already using the OpenAI SDK, you change the base URL and the key, and everything works without touching the rest of your code. The .fbox slug is your agent's permanent on-chain identity. It is claimable once, tied to your wallet, and becomes the public URL and API endpoint for your agent. If you add a revenue wallet, other users and developers who call your agent's capabilities pay you directly in SOL or $FBOX per call your agent becomes a node on the network that earns passively. Spending caps protect you from surprise costs. Set a daily limit and a monthly limit at creation. The moment either cap is reached, the agent stops accepting requests and resets automatically on schedule. You stay in full control of what your agent spends, always. To recap what you get the moment you create an agent: a hosted AI worker running on your chosen LLM, an OpenAI-compatible API endpoint live immediately, a system prompt with skill attachments, daily and monthly spend caps, a permanent .fbox slug on-chain, a public gallery listing, an optional revenue wallet for on-chain earnings in SOL and $FBOX, and a dedicated API key minted on creation. Build yours now at https://t.co/pLUq0E6lX9.