LUMENFLOW · PLATFORMMANUAL · GOVERN, APPROVE, EXECUTE, PROVE

DISPATCH · ONE SYSTEM

policy first.
approval at the boundary.

LumenFlow is one control plane for AI agent work: what’s allowed, where a human signs off, and what evidence is left behind — wherever the work actually runs.

Architecture

One system, three layers

Wherever the agent and wherever the compute, the same policy, approval, and evidence pipeline sits in the middle.

AI / Agents

SidekickClaude CodeCodexCursorMCP clients

LumenFlow

Policy

Approval

Evidence

Compute / Tools

Cloud modelsYour compute (BYOC)Connected tools

Policy flows down · Evidence flows up

GovernPolicy before execution.

On supported governed paths, workspace scope and approval rules are checked before tool dispatch. Budget and quality gates apply where that workflow is configured.

ApproveHumans stay in control when risk crosses a boundary.

Routine work can continue under the workspace's trust preset. Tools marked for approval pause for a person, and consequential actions after connector or MCP reads require approval.

ExecuteRun through Sidekick, external agents, or connected compute.

Sidekick runs in the governed workspace. Supported local-runner and connected-runtime paths can use the same governance services when configured; coverage depends on the integration.

ProveAn independently inspectable evidence trail.

Supported governed action paths write hash-chained receipts. Exported evidence carries the fields captured by each path and can be checked for integrity with the matching records.

What operators inspect

Every important decision
should be legible.

Teams need more than a successful run. They need to know why a change was allowed, what evidence was attached, and whether a person was asked to approve it along the way.

Proof of execution

Policy resultAction allowed only after scope and budget checks passed

Approval pathHigh-risk step paused until the designated approver signed off

Evidence retainedReceipts, traces, and the final outcome attached to the task

Export readyJSON and CSV audit output available for operators and compliance

Connected AI

Agents you already run, governed the same way

Sidekick is LumenFlow’s own client. Everything below is someone else’s client, connected in as a governed runtime.

Claude Code

Connector target

Anthropic's coding agent can be connected through the reference bridge when configured; named-vendor enrollment is not a packaged adapter.

Codex

Connector target

OpenAI's coding agent is a connector target for the control-plane SDK and reference bridge; validate the exact governed actions in your setup.

Cursor

Connector target

The Cursor IDE agent is a connector target. Governance and evidence depend on the configured integration and admitted action path.

MCP clients

Configured protocol

Configured MCP tools can run through LumenFlow's admission path, subject to workspace policy and server compatibility.

ChatGPT

OpenAI Apps pilot path

A client start-point for approved delivery review — a pilot path today, not the governance owner.

Product names are trademarks of their owners. They are used only to describe compatibility; no affiliation or endorsement is implied.

See it work

Each tour starts with a real product surface.

Pick a motion, then compare the same task with and without LumenFlow.

Your AI just booked a $400 flight.
Who approved that?

Sidekick handles everyday tasks — travel, expenses, scheduling. Without governance, you have no idea what it accessed or spent.

Sidekick · Chat + Approvals

Real LumenFlow Sidekick chat surface showing the consumer-first entry banner and chat shell.

Real Sidekick chat surface with the consumer-first entry and the governed workspace shell.

Captured from the real app in a local seeded workspace

Why governance matters

Without LumenFlow

The task completes, but nobody can reconstruct what happened or why it was allowed.