<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/semi-autonomous-ai-agents-and-collaborative-multiplayer-asynchronous-workflows-twcfe1o5y" -->

---
title: Semi-Autonomous AI Agents and Collaborative Multiplayer...
description: A tutorial demonstrates building semi-autonomous AI agent workflows using Inngest to manage asynchronous state, PartyKit for real-time websocket streaming, and...
canonical: https://daily.dev/posts/semi-autonomous-ai-agents-and-collaborative-multiplayer-asynchronous-workflows-twcfe1o5y
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Semi-Autonomous AI Agents and Collaborative Multiplayer Asynchronous Workflows | daily.dev
og:description: A tutorial demonstrates building semi-autonomous AI agent workflows using Inngest to manage asynchronous state, PartyKit for real-time websocket streaming, and...
og:url: https://daily.dev/posts/semi-autonomous-ai-agents-and-collaborative-multiplayer-asynchronous-workflows-twcfe1o5y
og:image: https://api.daily.dev/og/posts/twCFE1O5y.png
og:image:alt: Semi-Autonomous AI Agents and Collaborative Multiplayer Asynchronous Workflows
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Semi-Autonomous AI Agents and Collaborative Multiplayer Asynchronous Workflows

**[Inngest Blog](https://daily.dev/sources/inngest)** · 9 min read · 0 upvotes · 0 comments

## Summary

A tutorial demonstrates building semi-autonomous AI agent workflows using Inngest to manage asynchronous state, PartyKit for real-time websocket streaming, and OpenAI's function calling to intercept and confirm agent-suggested actions before execution. The example integrates Next.js, Linear, and Turborepo, letting users query Linear issues via chat and approve or deny agent-recommended actions like deletions, with full source code available on GitHub.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.inngest.com/blog/semi-autonomous-ai-agents>

## Questions this post answers

### How do you let a user confirm or deny an AI agent's suggested action before it executes, like deleting a record?

Mark specific OpenAI function definitions with a confirm flag, then intercept the function call in an asynchronous workflow engine before invoking it. The workflow pauses mid-stream, sends a confirmation request event, and only proceeds to execute the function after the user approves or denies it through the UI, using a unique request ID to track the pending action.

_daily.dev surfaces patterns like this for developers designing human-approval steps into agentic workflows._

### How can I stream OpenAI chat completion responses to a frontend from a long-running asynchronous backend workflow?

Use a websocket service like PartyKit to broadcast messages: the backend workflow posts each response chunk to a PartyKit server via a simple POST request, and the server broadcasts it to all connected clients over websockets. A React hook on the client listens for these messages and appends them to the chat UI in real time.

_developers wiring async AI workflows to real-time UIs can find similar streaming patterns via daily.dev._

### Can multiple users watch or interact with the same AI agent session at once?

Yes, connecting the workflow through a websocket broadcast service like PartyKit makes the session inherently multiplayer, since any client that connects to the same room receives the same streamed messages and state updates. This means several sessions can observe or participate in one asynchronous agent workflow simultaneously.

_daily.dev helps developers exploring collaborative, multiplayer AI agent architectures stay informed._

## Similar posts on daily.dev

- [Build agentic full-stack apps with Genkit](https://daily.dev/posts/build-agentic-full-stack-apps-with-genkit-ckpxki271) · Google Developers · 4 upvotes · 0 comments

---

Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#inngest](https://daily.dev/tags/inngest), [#nextjs](https://daily.dev/tags/nextjs), [#openai](https://daily.dev/tags/openai)

[View this post on daily.dev](https://daily.dev/posts/semi-autonomous-ai-agents-and-collaborative-multiplayer-asynchronous-workflows-twcfe1o5y)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Semi-Autonomous AI Agents and Collaborative Multiplayer Asynchronous Workflows","url":"https://daily.dev/posts/semi-autonomous-ai-agents-and-collaborative-multiplayer-asynchronous-workflows-twcfe1o5y","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/semi-autonomous-ai-agents-and-collaborative-multiplayer-asynchronous-workflows-twcfe1o5y"},"datePublished":"2026-09-13T19:57:37.802Z","dateModified":"2026-10-15T02:22:27.995Z","description":"A tutorial demonstrates building semi-autonomous AI agent workflows using Inngest to manage asynchronous state, PartyKit for real-time websocket streaming, and...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/779c87e75a1435767262c394aa43096a?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/779c87e75a1435767262c394aa43096a?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Inngest Blog","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Inngest Blog","logo":"https://media.daily.dev/image/upload/s--ieZKUa5y--/c_limit,w_256/f_auto,q_auto/v1789329423/logos/inngest?_a=BAMAMicg0","url":"https://daily.dev/sources/inngest"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/semi-autonomous-ai-agents-and-collaborative-multiplayer-asynchronous-workflows-twcfe1o5y","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,inngest,nextjs,openai","timeRequired":"PT9M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Inngest Blog","item":"https://daily.dev/sources/inngest"},{"@type":"ListItem","position":3,"name":"Semi-Autonomous AI Agents and Collaborative Multiplayer Asynchronous Workflows"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/semi-autonomous-ai-agents-and-collaborative-multiplayer-asynchronous-workflows-twcfe1o5y#faq","mainEntity":[{"@type":"Question","name":"How do you let a user confirm or deny an AI agent's suggested action before it executes, like deleting a record?","acceptedAnswer":{"@type":"Answer","text":"Mark specific OpenAI function definitions with a confirm flag, then intercept the function call in an asynchronous workflow engine before invoking it. The workflow pauses mid-stream, sends a confirmation request event, and only proceeds to execute the function after the user approves or denies it through the UI, using a unique request ID to track the pending action. daily.dev surfaces patterns like this for developers designing human-approval steps into agentic workflows."}},{"@type":"Question","name":"How can I stream OpenAI chat completion responses to a frontend from a long-running asynchronous backend workflow?","acceptedAnswer":{"@type":"Answer","text":"Use a websocket service like PartyKit to broadcast messages: the backend workflow posts each response chunk to a PartyKit server via a simple POST request, and the server broadcasts it to all connected clients over websockets. A React hook on the client listens for these messages and appends them to the chat UI in real time. developers wiring async AI workflows to real-time UIs can find similar streaming patterns via daily.dev."}},{"@type":"Question","name":"Can multiple users watch or interact with the same AI agent session at once?","acceptedAnswer":{"@type":"Answer","text":"Yes, connecting the workflow through a websocket broadcast service like PartyKit makes the session inherently multiplayer, since any client that connects to the same room receives the same streamed messages and state updates. This means several sessions can observe or participate in one asynchronous agent workflow simultaneously. daily.dev helps developers exploring collaborative, multiplayer AI agent architectures stay informed."}}]}
```

