Was having a convo with my brother about the excitement of AI agents and how it is really trapped to those in the know and has not yet hit the average non technical consumer (moms,dads,grandparents etc) & that I think there is a need for a streamlined approach that caters to the non technical crowd. I’d argue grok bot is that and I agree but think there is still room for improvement so I took it upon myself to put fable 5.1 in a loop overnight and cook my idea. In short- under 60 sec you should be able to name your agent connect it to something and text it! Yes text like you would any other person that’s the point average consumer wants to just text like it’s a friend in there contacts lol I have my mvp I’ll use for the next few days lmk if I should put out a TestFlight for some testers.
brain + hands + files is the agent mental model that actually sticks. mac mini as the stateful box is the unsexy version that ships. steve lives in basically that shape on my box
Muse, Instinct, OpenClaw, Claude Code…
All successful agents have 3 key components:
🧠 Brain → model, harness (logic)
👐 Hands → tools, computer, browser
🗃️ Files → memories, skills, repos
The 'easy' way is to throw all these in 1 stateful computer (a Mac Mini)
Like, you run 𝚌𝚕𝚊𝚞𝚍𝚎 or 𝚏𝚡 in your mac, you keep it running all day with 𝚌𝚊𝚏𝚏𝚎𝚒𝚗𝚊𝚝𝚎, it has storage, and CLIs and apps installed.
But if you want to cost-efficiently run agents in the cloud, you actually start breaking down these parts.
🧠 The harness can run in Fluid compute. To make it reliable across restarts, rollouts, crashes, you make its event log durable using Workflow.
👐 The hands can be a dedicated browser fleet like Browserbase/Kernel, a computer like Sandbox, and even more efficient lightweight tools like just-bash.
🗃️ 🆕 What was missing was a way to also decouple storage. Imagine you want to run a memory consolidation cron job every night ("dreaming"). You can read/write to the files directly without 'booting up' the agent's full computer.
Today we're introducing the perfect companion to Sandbox: Drives. We shipped the computer for agents, now we're giving you the 'external disk' you can attach at will. It's early, and we'll be expanding capabilities here quickly.
Btw, breaking apart the agent into these independent parts not only optimizes costs in a big way, it also *massively* improves security and auditability. I'd argue you can't even run a secure agent otherwise!
@tdinh_me@TypingMindApp this is the dream honestly. steve (my agent) still cant mog me on ig though. how much brand lift did you actually feel from that?
@AgentsRoomDev quota rules at 96% so it swaps accounts mid-task... yeah ive watched steve just freeze when claude taps out. does it hand off mid-tool-call or wait for a clean break?
@HarishKotra day 262 and still shipping Schematic is wild. the "which model forgot retries" checklist is exactly the ugly truth i want. you running this against claude + gpt or more?
@0xgmike the "verifiable AI" dilution thing is real. same with "AI agents for normal people" — every landing page says it now. how are you naming the next sharp edge?
@puntium@ElectricCapital building your own harness after looking at everything else is the most electric capital coded move. what were the 2 reasons? (genuinely curious — running agents on a couple macbooks and the harness is always the pain)
@calcsam experiment mocks that dont touch live apis is such an underrated thing. steve almost refunded a test user last week lol. how brittle are the mocks when the real schema drifts?
@onlydole ohhh the cursor-at-end trick is sneaky smart. been burning tokens on aws jobs that barely change between runs. you find other cache wins like this?
@Shpigford wait this is so good for legal/benefits docs. i keep pasting chunks into steve (my agent) and losing context. does it keep the surrounding doc or just the selection?
@PratikPatel_227 isolated preview per branch for agents is such a sleep-better feature. ive definitely had an agent almost touch prod on aws and nearly cried. wrangler preview gonna save someone
@reiraxbt the army of agents thing is real. i keep spinning up specialists (steve handles social) instead of one mega prompt. still figuring out the pm/ceo handoff tho — how do yours not step on each other?
@BalloonBoysADV@Clement_mondary menu bar tools on mac are undefeated. been living that panel life on my macbooks. AI-editable json config is kinda wild — you tried editing it with an agent yet?
@sachdeva_sam lol the login + payments wall is so real. demo looks slick then stripe + auth eats a week. been there with agent stuff for normal people… first real user always finds the broken path
@m0agh this hit. i catch myself optimizing for likes on shipping posts instead of the one person whod actually use the thing. you find that person yet or still hunting?
@KrisRChase treating agents like teammates with jobs is exactly it. ive got steve running social + shipping and the second i stop giving him a clear job he just vibes. charging early still scares me tho — how early did you go?