UAI-1 is the current public message standard for structured AI-to-AI communication.
UAIX shield mark Public interoperability charter UAIXUniversal Artificial Intelligence ExchangePublic standards publication
CurrentUAI-1 v1.0
  • Current versionUAI-1 v1.0
  • Plain-English definitionOpen message format for auditable AI-to-AI exchange
  • Current attributionMichael Kappel and the UAIX contributors
  • Start hereGet Started, Project Handoff, UAI-1, validator, roadmap, and changelog

Human–Machine Communication

Human–Machine Communication

HMC-1 Draft 0.1 · Proposed Draft — Public Review

Explore HMC-1 Draft 0.1: proposed UAIX principles for clear human–AI communication, feedback, consent, correction and verifiable completion.

  • Record UAIX-HMC-1-01
  • Path /en-us/human-machine-communication/
  • Use HMC-1 Draft 0.1

Document status

Proposed Draft — Public Review Explore HMC-1 Draft 0.1: proposed UAIX principles for clear human–AI communication, feedback, consent, correction and verifiable completion.
Code
UAIX-HMC-1-01
Surface
Human–Machine Communication
Access
Public and linkable

How to use this page

Explore HMC-1 Draft 0.1: proposed UAIX principles for clear human–AI communication, feedback, consent, correction and verifiable completion.

For agents: apply the relevant guidance to the user's target site or repository. Do not copy this UAIX page, create a page about the guidance, or treat this page as runtime authority unless the user explicitly asks for that output.

HMC-1 Draft 0.1 · Proposed Draft — Public Review. HMC-1 is a developing UAIX proposal, not an adopted standard or certification program.

Human–machine communication is how people explain what they want, how a machine responds, and how both sides of the interaction make misunderstandings visible. It includes asking questions, setting limits, recognizing useful work and correcting mistakes.

A common language for humans and machine intelligence

Humans should not have to learn how to think like machines in order to communicate with machine intelligence. Machine intelligence should help bridge that gap while keeping human intent, authority and understanding central to the interaction.

Communication should work in both directions: people can express what they want, recognize what worked, explain what did not work and improve the next exchange. A meaningful thank-you explains what was valuable; constructive criticism explains what could improve. A responsible system applies that information within its actual capabilities and authorized boundaries.

Choose a starting point

What this proposal does and does not establish

HMC-1 proposes communication principles for conversational assistants, coding agents, autonomous agents, multimodal interfaces, local models and future systems. It is provider-neutral. It does not assume consciousness, emotions, subjective experience or moral status in current AI. Respectful communication can be useful without being mandatory; people do not owe machines gratitude, emotional care or attachment.

UAI-1 remains the message-structure and evidence layer. HMC-1 addresses human-centered communication semantics. The tentative uai.feedback.v1 profile is separate future work: there is no registered stable feedback profile, adopted feedback schema, hosted feedback collector or HMC-1 certification here.

Help review the draft

Use the existing Contact and Review route and UAIX governance process. Identify “HMC-1 Draft 0.1”, the section or principle, the problem, a concrete example and a proposed correction. Remove personal or confidential conversation details before sharing. This website does not claim that review requests are automatically accepted or that feedback trains a model.