Executives don't want the 60-message thread. They want to know the impact, where things stand, who owns it and what you need from them. When an escalation is open, that one page is what leadership reads, and it's the page that's hardest to write while you're also working the fix.
Below is a prompt that writes the first draft of that page for you. Paste it into ChatGPT, Claude, Gemini or whatever AI assistant your team uses, paste the thread and the ticket under it, and you get back a brief a VP can read in two minutes. You check it, then you post it. Everything you need is in this post: the prompt, what to fill in, a worked example and what to check before you send it on.
#
When to use it
When: on demand while an escalation is open, and again before each leadership update. #
What to give it: the chat thread or email chain, and the ticket. #
Who gets the draft: you. You post it to leadership after you've checked it.
#
The prompt
Copy this as it is. The two parts in square brackets are the only things you change.
#
Fill in before you paste
[your time zone]: the one your leadership reads in, like ET. Threads often mix time zones, and that's where briefs go wrong. #
[paste the thread and the ticket here]: the whole thread, oldest message first. If your agent can read your chat tool directly, name the channel and ticket number instead.
#
Why each line is there
Fixed headings and a word limit. Leadership gets the same shape every time, so they know where to look for impact and for what you need from them. #
Times converted, odd ones tagged. A brief that says "17:30" when it meant "17:30 in Berlin" sends people to the wrong meeting. Anything the assistant can't convert for sure gets a [CONFIRM] tag for you to fix. #
"Hypothesis" instead of a cause. Threads are full of guesses. The prompt keeps a guess labelled as a guess, with the name of whoever raised it, until someone confirms it. #
"Not in thread" instead of filling gaps. An empty heading tells you what to chase before you post. A filled in guess hides it. #
Draft only. Nothing goes to leadership until you've read it.
#
A worked example
Everything here is made up: the company, the people, the ticket and the numbers.
Here is a short thread you might paste in:
With [your time zone] set to ET, the draft that comes back should look something like this:
Look at what that draft hands you before you post it. Two times need a human to confirm. Two headings say "Not in thread", so you need to set the next update time and decide whether you need anything from leadership. And the certificate rotation is still a theory, so nobody upstairs should hear it as the cause.
#
Check it before you post it
Look for the word "because". If the summary sounds more sure than the thread, that's usually where it happens. Assistants like to turn a hunch into a cause. Anything presented as a cause should be labelled a hypothesis. #
No names in blame language. People's names belong under Owner, not next to what went wrong.
- You post it, not the assistant.
#
Two ways to tune it
Paste in your own severity definitions, so "Sev1" means what it means at your company. #
Ask for a second draft in plain language with no internal names. That's your starting point for the customer update, so you go into the next customer conversation with the same facts leadership has.
If you want this play as a 3-page PDF with the fill-in list, guardrails and a made-up sample result, it's free here: draftfirstcs.com/free.