We mirror a company into a living twin, rehearse decisions on it, and hand the routine to an AI agent that runs on a heartbeat — every second, minute, hour and day.
Inbox, follow-ups, reports, scheduling, small fixes. A 5–50 person company can't hire for all of it, so most of it just doesn't happen.
Chat windows and copilots wait for a human to prompt every step. They assist. They don't run anything.
Autonomous agents loop, hallucinate and act outside their remit. No audit trail, no limits, no memory of why — so nobody hands them real work.
Messages, tasks, calls, payments and decisions become signed events in one append-only log. Replay it and you get the company as a living model.
Changes are tried against the twin and its real history. Where the agent isn't sure, it escalates to a person with the full story.
An agent that lives by ticks takes the routine, with real tools. Every action feeds back into the twin, so it gets sharper over time.
| 1 s | Reflexes telemetry, alerts, bot commands — no LLM, zero cost |
| 1 min | Triage inbox, routing, quick fixes |
| 1 h | Execution tasks end-to-end with real tools + hourly digest |
| 1 day | Planning larger work, daily manifest, nightly self-training |
Busy levels skip a beat instead of piling up. Only digests travel upward.
ed25519-signed, hash-chained event log. 3.1M events verified end-to-end.
Rights come from verified identity, never from message text. A guard checks every tool call before it runs.
Rules and fast decision models filter before an LLM wakes. Reflexes and quiet beats cost nothing.
Small student models train nightly on real outcomes — and only replace the rules after beating a baseline on fresh data.
1 Owner — full tools
2 Board — work, no secrets
3 Members & agents — scoped
4 Everyone else — reply only
1 s reflex
1 min triage
1 h execution
1 day planning
D0 just this message
D1 the conversation
D2 relevant past episodes
D3 the archive
Memory is private by circle: a board-level conversation can never surface the owner's private chats. The same code serves a two-person studio and a 500-person company — only the table changes.
Every lab is a real business — a founder plus AI agents on shared infrastructure inside Cooperative 42. Each one is a live test bench for the autopilot.
Source: production event store and cooperative portal, 18 Oct 2026. Every number above is a query, not an estimate.
Every decision is logged with what happened next — a reaction, a retry, a fix.
Small models train on that experience and stay in shadow until they beat a baseline.
Repeated failures turn into a proposed rule, sent to the owner for a yes.
Code changes close only with a commit and a passing test. No silent self-edits.
Example from this week: the agent improved its own Telegram behaviour, then tried to close the task without a test. The new gate now refuses that — the change shipped with a commit and a passing test.
Our lab MCP, Claude Code and the autopilot for anyone building a product. Self-serve, community-run. The studio keeps 10%+ of sales made through its payments.
Startups in a cohort, worked with personally. Each month: the larger of $999 or a revenue share (10%+). Any shortfall is paid now or deferred as BTC-indexed debt.
The best founders join the studio payroll — as the core team is today — and keep building their own startups while running cohorts for the next ones.
every rung pays the studio · every rung has a reason to climb · the studio is run by people who climbed it
One SAFE in Shkor Labs — exposure to every lab, the community and the platform.
Each quarter investors vote on how the studio's investment pool is split across its startups.
Votes are informed by each startup's live record: revenue, shipped tasks, agent activity — signed, not self-reported.
Fees and revenue shares from every rung return to the studio and fund the next quarter.
The voting machinery already exists: Cooperative 42 runs investment votes and awards on its portal today. The pool can reach beyond the labs — to the strongest community builders.
Agents with real tools now finish multi-step work end-to-end. Orchestration, not intelligence, is the bottleneck.
Sub-second decision models and local embeddings let the autopilot think constantly and call a large model only when it matters.
Every company wants autonomy; almost none can audit it. A signed, bounded, self-correcting autopilot is the missing layer.
Lab cohorts led by studio members, with the autopilot as facilitator. The playbook becomes software.
$99 self-serve: lab MCP + Claude Code, deploy in a day from the portal.
Quarterly allocation of the investment pool across lab and community startups.
First founders from the cohorts join the studio and run the next cohorts themselves.
Founder & managing member. Architect of the Simbiot autopilot; chairman of Cooperative 42. US entity, payments and production infrastructure.
Board. 14 years building products and businesses; finance, tax, legal and M&A. Runs Vybirai and Monetix.
Board. End-to-end video production with his own studio; runs ReelsUp, Avatar and xSaleBot.
Sixteen agents in production — sales, content, research, finance, operations — each with its own server, memory and signed track record.
Pre-seed · uncapped SAFE with MFN · rolling close
Capital for the studio's startups, allocated quarterly by investor vote.
Salaries for cohort leads, so new cohorts start without the founder.
Autopilot, lab MCP and the self-serve $99 community.