The prompt ends. The company keeps moving.
OrgX lets a person manage a fleet of agents from the AI client they already use—without losing the goal, the decisions, the quality bar, or the proof when work changes hands. It is the shared operating context beneath the clients, not another chat destination.
Output, provenance, quality, and review state are inspected together—not reconstructed after the fact.
The consequential problem
The model could draft, research, code, and coordinate. But the work scattered across prompts, clients, repositories, and human memory. A handoff between Claude and Codex could erase the goal, the decision that shaped it, and the evidence already gathered.
More autonomy made the gap more dangerous. Activity increased while the founder or team lead had less confidence about what moved, why it moved, and what deserved attention.
What I saw
The next agent needs more than a summary. It needs the goal, definition of done, decisions and why, available tools, missing permissions, budget, confidence, and the next useful action. Those become a compiled handoff instead of a transcript dump.
That reframed OrgX from an orchestration destination into infrastructure that can meet the operator where the work already happens.
The decision that changed the system
The work graph connects goals, initiatives, agents, decisions, artifacts, receipts, cost, and value. The owner's quality bar decides what returns for review. Tool policy pauses publishing, payments, messages, merges, and other external effects at the human boundary. Recovery can retry, narrow scope, ask a specialist, checkpoint, or stop.
Intent, constraints, decisions, and prior evidence enter together.
Specialists act in the interface best suited to the work.
Consequence determines when human judgment must enter.
The artifact, provenance, and quality outcome become memory.
System anatomy / rationale / surfaces
The difficult part is preserving the cause chain: why the work exists, what the agent knew, which tools it could use, where a person had to decide, what the result proved, and whether the next move is still worth its cost.
A new agent receives a task title and reconstructs the company from scattered chats, docs, and repo state.
Compile the goal, definition of done, decisions and why, proof, permissions, confidence, and next action into one context pack.
The next client can continue the work without pretending a transcript is organizational memory.
Claude, ChatGPT, Codex, Cursor, VS Code, Windsurf, Zed, OpenClaw, and other MCP-capable clients enter the same organizational context without being flattened into one UI.
MCP clients · native plugins · web appStreamable HTTP and SSE coexist behind OAuth 2.1, PKCE, and dynamic client registration. Each MCP session is isolated in a Durable Object rather than trusted as a stateless chat request.
Cloudflare Workers · OAuth Provider · Durable Objects · SQLiteA canonical tool grammar moves from bootstrap and search through plan, spawn, decide, write, attach, act, and submit receipt. Zod contracts keep calls structured and interoperable.
Model Context Protocol · Zod · structured resultsInitiatives, workstreams, milestones, tasks, agents, decisions, approvals, artifacts, and outcomes retain the relationships a new session needs in order to continue responsibly.
Next.js · TypeScript · Supabase · React QueryAgent runtimes, queues, sandboxes, and durable workflows execute the work. Trust ladders and consequence-aware gates determine when an operator must enter.
OpenAI Agents SDK · Anthropic Agent SDK · Inngest · E2B · Trigger.devArtifacts return with versions, provenance, evaluation, review state, and a receipt. Proof rooms and embedded widgets make that state legible beyond the dashboard that created it.
MCP Apps · artifact renderers · evaluators · proof roomsThe next agent can resume from decisions, owners, artifacts, approvals, and proof instead of reconstructing a transcript.
Clients keep their native strengths while organizational state remains portable and accountable.
Human attention is reserved for irreversible or ambiguous boundaries—not every unit of agent activity.
A reviewer can inspect the artifact, status, provenance, and next action inside the client where the work arrived.
The architecture is only complete when every operator and client boundary has a legible surface.
Focus, delegation, approvals, tool calls, and outcomes stay attached to the agent's current work.
Active execution, handoffs, blocked decisions, and run state become legible without pretending raw telemetry is judgment.
Code, design, video, data, diffs, marketing work, receipts, and pull requests render on their own terms.
Versioned quality bars remain separate from observed signals; autonomy is bounded by consequence.
Selected outcomes become durable, shareable capsules instead of screenshots without provenance.
Initiative pulse, morning brief, decisions, search, status, and task surfaces bring the work graph into AI clients.
OpenClaw and other client bridges inherit host strengths while adding shared organizational memory.
Judged criteria, receipts, and publication artifacts turn quality claims into a repeatable evidence system.
Next.js App Router · React · TypeScript · React Query · Xyflow
Supabase · PostgreSQL · Clerk · OAuth 2.1 · PKCE
OpenAI Agents SDK · Anthropic Agent SDK · Inngest · E2B · Trigger.dev
Model Context Protocol · MCP Apps · Cloudflare Workers · Durable Objects · Zod
Sentry · PostHog · OpenTelemetry · Upstash · Stripe
A curated record of where each system earned its place—not a wallpaper of configured integrations.
These are working MCP and operator surfaces, not concept renders.
Organizational health, the blocking boundary, workstream progress, and a live continuation action in one embedded surface.
The widget distinguishes current focus, blocked work, review, artifacts, and progress instead of compressing everything into online or offline.
The next session begins with grounded organizational state and explicit judgment requests—not a blank prompt.
The information needed to decide, the consequence, and the approval action stay together inside the client.
A new session can recover the relevant decision and artifact without reading the entire organizational transcript.
The output is not a paragraph called a plan; it is an inspectable structure with owners, boundaries, and a next action.
Authentic proof
The interface privileges current focus, the next consequential boundary, and grounded history over raw activity.
Decision, trust, and work events remain attributable in the same timeline instead of dissolving into logs.
The bar is explicit, versioned, and task-specific; observed signals stay visible without masquerading as the standard.
What changed in my operating model
OrgX changed my operating model from “automate the workflow” to “design the cause chain.” Every meaningful action should preserve context, expose its boundary, and return proof that improves the next decision.
Autonomy remains useful. Continuity is what makes it compound.