Meeting: January 13th, 2026

[earth2marsh]

Weekly meetings happen on Tuesdays

Time: 5pm GMT / 9am Pacific
Zoom: https://zoom-lfx.platform.linuxfoundation.org/meeting/93842243477?password=af4b5ce2-5124-4be5-960e-33f6e94a0e7e
Note:☝ new meeting info as of 2026.01.13

We use the LFX platform to manage this invite/calendar event.

This initiative is looking for a co-lead to help organize and drive progress.

Accessibility & Etiquette

• Participants must abide by our Code-of-Conduct.
• Meetings are recorded for future reference, and for those who are not able to attend in-person.
• We invited challenges to language or behaviour that is harmful or not inclusive during this meeting.
• We look forward to your participation, but please consider these acts of etiquette:
  • Remain on mute when not speaking to prevent interruptions.
  • Blur your background to reduce visual distractions.
  • Use the Zoom meeting "Raise Hand" feature to notify the group when you wish to speak.

Blur My Background	Raise Hand

Agenda Structure

Topic	Owner	Decision/NextStep
Intros and governance meta-topics (5 mins)	SIG members	--
General discussion topics (list below)	SIG members	--
Wrap-up and seed the next agenda (5 mins)	SIG members	--

Whether attending or not, anyone can comment on this issue prior to the meeting to suggest topics or to add comments on planned topics or proposals.

[earth2marsh]

While we discussed the early draft of the 2026 proposal, it was then heavily edited, updated, and moved to a standalone discussion #219 . The below code block contains the earlier draft as context, but do read #219 instead.

# **Moonwalk SIG Update: 2026 Orientation**

## **Status and Leadership**

The Moonwalk SIG is shifting its focus for 2026\. For at least the next six months, the intention is to focus on how OpenAPI intersects with LLMs as a new class of smart client.

Organizationally, **1-2 additional co-hosts are needed,** a collaborator to help organize and host sessions, manage the backlog, and drive consensus. If you are interested in that, please reach out to @earth2marsh via the OAI Slack.

## **Strategic Focus: The LLM-Mediated API Landscape**

As the work orients toward supporting a world where LLMs represent a new category of smart client, the goal is to move beyond the assumption of deterministic, human-coded clients. The focus is a model where APIs surface capabilities to low/no-code users interacting via autonomous or semi-autonomous agents. This shift requires re-evaluating what information an OpenAPI Description (OAD) must contain to be truly "agent-ready."

### **Proposed Roadmap (6-Month Horizon)**

*Note: This roadmap is a draft to promote discussion. The community is invited to discuss and refine these priorities and identify gaps.*

1. **Capability Discovery Phase:** Identifying how to signal *what* a service can do, rather than just *how* to call an endpoint.  
2. **Contract Evolution:** Moving from a purely technical contract to a "social" or "intent" contract that agents can interpret.  
3. **Workflow & Overlay Integration:** Determining how Arazzo (workflows) and Overlays can be used to tailor API surfaces for specific LLM-based journeys.  
4. **Drafting Recommendations:** Developing initial sign-posting standards for capability-based access.

## **Open Questions for Discussion**

The following questions are proposed to orient upcoming sessions. The SIG is invited to discuss these without the immediate pressure of finalizing implementations:

* **Capability Surfacing:** When technical details are delegated to an LLM or orchestration layer, what metadata is required in an OAD to effectively surface a "capability"?  
* **Sign-posting:** How can sign-posting for available capabilities be improved to support on-demand, non-linear user journeys?  
* **The Contract Shift:** How should the "social contract" of an API be defined versus the traditional technical contract?  
* **Organization:** Can `tags` and `tag-kinds` be leveraged to logically group capabilities for agents?  
* **Intersections:** How do Overlays (separating layers of responsibility) and Arazzo (workflows) intersect with agentic access?  
* **Optimization:** Can a service's complete description be simplified or optimized specifically to support LLM-based journeys (e.g., an `llms.txt` equivalent for APIs)?  
* **Discovery:** Is the discovery of these capabilities within or out of scope for the Moonwalk project?

## **Participation**

Interested contributors and potential co-hosts should join the next SIG meeting. Details for the meeting schedule and the project backlog can be found on the [SIG-Moonwalk GitHub repository](https://github.com/OAI/sig-moonwalk).```

[earth2marsh]

Following our discussion, this has been edited and moved to a new, pinned discussion: #219 .

[mikekistler]

Another topic to consider is the restrictions that some LLMs place on schemas for tools / functions:

https://platform.openai.com/docs/guides/structured-outputs#supported-schemas

[earth2marsh]

Video is available