A verifiable trust layer for AI workflows, tools, agents, and orchestration frameworks.

The PromptFlow™ System is a persistent re-usable process layer that evolves along with the underlying models in a federated remunerative ecosystem. It sits above MCP servers, n8n workflows, LangChain agents, hosted models, and custom pipelines — providing what they individually lack.

Specification v0.2 · federation extensions Trademark · USPTO 97913988 ↗ Patent · US 18/677,796 ↗

Four things the ecosystem is missing.

Every AI framework claims to solve the same problems. The PromptFlow™ System doesn't compete with them — it measures them. It's the infrastructure above the substrate that makes federation actually work.

01

A way to distinguish which paths actually achieve an outcome under which constraints.

Every execution produces evidence — completion rate, cost, latency, schema conformance, audit verdicts. The graph doesn't trust claims; it trusts measurement.

02

A way to compose new capabilities rapidly from existing ones.

Once every capability has a typed interface and measured behavior, building a new one becomes picking the right nodes and wiring them — not writing glue code.

03

A mechanism for reducing process complexity as the underlying models improve.

When a new model can do in one call what previously took five steps, the older path becomes alternate. Complexity sheds automatically. This mechanism is unique to the PromptFlow™ System.

04

A settlement system that pays contributors when their work is used.

Every execution pays every party whose work contributed — the composer, the sub-process authors, the MCP operators, the eval contributors, the auditors. Proportional to contribution.

Anything that performs AI work becomes a node.

The graph is agnostic about implementation. MCP servers, n8n workflows, agents, hosted models, `.promptflow` files, and typed HTTP services all become addressable capabilities with the same interface, the same verification, and the same settlement treatment.

MCP servers

Tools auto-discovered

Tools surfaced via tools/list, registered as capability nodes. Every operator gains discovery and revenue.

n8n workflows

Webhook-triggered

Workflows with declared I/O schemas become composable capabilities. Creators gain distribution and monetization.

Agents

Framework-agnostic

LangChain, AutoGen, CrewAI, or custom — any agent with an addressable endpoint. Framework choice is invisible to the graph.

Hosted models

Metered pass-through

Anthropic, OpenAI, Google, open-source — every model API is a provider type. Calls pass through at cost; settlement is metered.

.promptflow files

Typed compositions

Authored files that compose any of the above. The universal contributor path — anyone can build one without infrastructure.

HTTP services

Typed endpoints

Generic endpoints with request/response schemas. If it's accessible and typed, it composes.

The design isn't just described — it's validated.

Six load-bearing mechanisms validated end-to-end in a reproducible simulation with real LLM decisions: distinctness classification, autonomous graph growth via composition, ranking convergence, spot flips, simplification when newer implementations dominate older ones, and multi-party settlement with lineage royalties.

6/6
Load-bearing mechanisms validated end-to-end
30
New capabilities autonomously composed by LLM users
307
Settlement entries across 12 contributors in single run
$0.60
Total cost of the full reproducible simulation

The future of AI work is federated. The trust layer is what makes it work.

The specification is open. The reference implementations are MIT. The trademark and system are protected. The graph is meant to be owned by the people who build it.