I’m building AI-powered automations using independent AI triage scripts (e.g., spam check, tag determination). These currently run concurrently, which is inefficient. I need to “chain” them so, for example, the tag script only runs if the spam script doesn’t flag the content. How can I govern and…

Can you describe the full flow you are after? Would this be something you run on a separate server or would you like this to run in Discourse? AI workflows is something we are thinking about a lot, the ability to define chains is key with workflows. I agree completely with that.

From what I can see, most of my use cases can be done in Discourse with AI Triage and Automation, if one can trigger then next. Here is a hypothetical flow where each step would send the post contents and a prompt to the LLM: Check if spam If spam, then hide and flag If not spam, determine pr…

This is great and a very interesting use case. Custom tools already have support now for scripting so we have a great vehicle for this kind of change. I am thinking Persona + forced tool use - then from the tool we can run the flow given we already have all the infra to do so. Just need to give cu…

This reminds me of the IFTT / Zapier chain of actions, I think we could borrow a lot of their UI/UX elements if we build something like this out

Hi @Cloud_spanner I am trying to get to the bottom of this and would like to flesh out the actual flow here a bit more, can you help with some answer to questions along the way 5. ? Which posts should be scanned? Every new post on the forum? Every new topic - eg post number 1 - on the forum? W…

Every new topic should kick off an AI triage workflow. Edits can be ignored. To be clear, I am using intent to illustrate the workflow so it shouldn’t be considered a hard-coded flow. The point I am trying to make is that there is no reason to kick off ‘intent’ workflow if the first triage work…

I have been thinking about how to solve this within our current system and one very appealing option is allow for a new automation type: triage_using_custom_tool We already have the custom tool system: <a class="lightbox" href="https://d11a6trkgmumsb.cloudfront.net/original/4X/1/7/4/174c569f6c69906b624584bfd672cbe04e5d7a63.png" data-download-href="/uploads/short-url/3k6xetwu6pxKrfSG0JrTpJe1YuT.png?dl=1" title="The image shows a tool configuration page with a form for "Browse Web" functionalities, including a summary, parameters, and script sections, including an input field for a URL. (Captioned by AI)">[The image shows a tool configuration page with a form for "Browse Web" functionalities, inclu…

That sounds like a great idea. I’m still newish to the Discourse ecosystem, so I’ll dig into Custom Tools and also how feature requests make their way into production.

I do have some good news, your workflow is all workable now using custom tools! The idea is that you would define a single custom tool with all the params is_spam, intent, hot, requires_invite Then you would like on triage using persona to call the tool and the tool would perform all the actions …

AIと自動化ガバナンス：独立したAIトリアージスクリプトのオーケストレーション

サポート

Saif (Saif Murtaza ) 2025 年 2 月 9 日午前 8:35 7

これはIFTTT/Zapierのアクションチェーンを思い出させます。このようなものを作成する場合、UI/UXの要素を多く参考にできると思います。

トピック		返信	表示
Discourse AI - AI triage Site Management how-to , ai , automation	50	5345	2025 年 7 月 27 日
Testing automation rules Feature ai , automation	0	57	2025 年 3 月 7 日
Discourse Automation Plugin official , automation , included-in-core	76	24296	2026 年 3 月 19 日
Best practices for AI antispam plus AI post triage operating together? Support ai	4	124	2025 年 9 月 16 日
Experiments with AI based moderation on Discourse Meta Community Building moderation , ai	11	999	2025 年 5 月 26 日

AIと自動化ガバナンス：独立したAIトリアージスクリプトのオーケストレーション

関連トピック