THE MEDIA FOR AI THAT ACTUALLY HELPS.English edition · Understand & take action
Spotted on the web

Pre-analyze each technical support ticket and update procedures

Use described publicly by Dust — Wayflyer (25 August 2026), summarised by the desk. Not tested by iadujour.

The result to aim for

Wayflyer, a Dublin fintech that finances growing brands, has built two agents: one prepares the diagnosis as soon as a ticket arrives, the other updates the procedures after its resolution.

What was done

According to the case study published by Dust on August 25, 2026, information useful to support was dispersed between Notion, Slack, Jira and the memory of the engineers. As soon as a Jira ticket is opened, a sorting agent triggers: in about a minute, he browses ticket history, procedures (runbooks) in Notion, Slack conversations, queries internal tools via MCP, then writes an internal synthesis with the recommended sorting steps and its sources. When the ticket is solved, a second agent checks if the solution reveals a lack of documentation and writes an update if necessary; It can also be called at the end of a Slack wire to draw a structured procedure. According to the source, the time required to create and maintain procedures has decreased by more than 90%.The teams are free to build and publish their own agents; monthly usage reached almost the entire enterprise in six months.

Before you start

Tool cited by the source: Dust. Gather the information the prompt asks for. Strip confidential data that is not needed and check your tool’s access terms. Features and plans can change.

The method, in three steps.

  1. Gather the context

    Gather the information described in the prompt.

  2. Adapt the prompt

    Copy the prompt below, replace the bracketed items, then paste it into Dust.

  3. Reread before using

    Reread the result, correct it if needed and keep the final decision. Caveats are detailed below.

Your starting point.

Replace the bracketed items, then adapt the proposal to your situation. This prompt is written by the iadujour desk It is not a quotation from the source.

The prompt to customise
New ticket support:
Here's what you can see:

1. Summarizes the problem in 3 lines.
2. Lists neary tickets or procedures, with their link.
3. Proposed the diagnostic steps in order, specifying what is confirmed and what remains a hypothesis.
4. After resolution, I will give you the solution: then indicate whether a procedure should be created or corrected, and write it for rereading.

What deserves your attention

A diagnosis proposed by the agent remains a hypothesis: the engineer checks the case data before acting, and the procedures written automatically are reviewed before being published.
Origin of the case. Use described publicly by Dust — Wayflyer (25 August 2026).
Proof level: Statement by the tool’s publisher. Source checked on 10 November 2026. Use described by the source, not tested by the desk. Original summary written by iadujour.fr: figures and claims are the source’s; the prompt is a desk proposal, not a quotation.
TO GO FURTHER

Other ideas to put to work.

The whole Customer support theme
DISCUSSION

Comments.

A field note, a question, a precision on this use case? Comments are reviewed before publication.

Published comments

Loading comments…

    Leave a comment

    Moderation charter. Every comment is reviewed before publication. We refuse hate speech, insulting or discriminatory language, advertising, spam and promotional links, off-topic posts and other people’s personal data.