AI assistants for business

How to Use AI to Detect Urgent Enquiries and Rank Your Morning Briefing

BOTrento Team8 min read

Yes, AI can detect urgent enquiries: it reads the text of each email for deadlines, tone and decision-maker language, then ranks the enquiry against rules you have written down. What it cannot do is know your business, so the quality of the ranking depends on how clearly you define "urgent".

This article gives you the signals worth looking for, a simple scoring scheme you can use in a spreadsheet today, and a way to check whether an AI ranking matches your own judgement before you rely on it for your morning list.

What makes an enquiry urgent (and what only sounds urgent)

Urgency is not the same as importance. A large enquiry for an event months away matters, but it can wait until tomorrow. A small enquiry that needs an answer by noon cannot. Separate three things:

  • Time pressure: a real deadline, either the customer's or yours (a quote validity date, a rental start date, a promise you made).
  • Risk of losing the customer: frustration, a chaser, or a mention that someone else has already replied.
  • Value and authority: who is asking and how much is at stake.

Words like "urgent" and "ASAP" are weak signals on their own. Some buyers write them on every email. A date, a named event or a stated consequence is far more reliable.

The signals AI can read from email text

An AI assistant works from the words in the message and the thread. That is enough for several useful signals.

Deadline signals

  • Explicit dates: "we need this by Thursday", "the event is next Tuesday".
  • Relative phrases: "by end of week", "before the board meets", "this afternoon".
  • Dependencies: "we can only book once we have your price".

Tone and sentiment signals

  • Chasers: "following up again", "still waiting", "as per my last email".
  • Frustration: complaints about delay, or a shorter, sharper tone than earlier in the thread.
  • Comparison: "we have another quote", "your competitor already sent".

Decision-maker signals

  • Role words in the signature: managing director, head of procurement, owner.
  • Decision language: "we are ready to confirm", "please send the contract", "budget is approved".
  • Someone new copied in at a senior level.

Routine signals

  • General questions with no date: "what do you offer?", "do you cover our region?".
  • Newsletters, supplier mail and automated notices, which should not compete with real enquiries.

Be aware of the limits. The AI reads email text only. A deadline hidden in an attached brief will not be seen, so ask your team to repeat key dates in the email body or check attachments themselves.

A simple scoring scheme you can copy

Before you hand anything to AI, write the scheme down. Give each enquiry a weight on a few questions, then sort by the total.

SignalWeight
Deadline within the next couple of working daysHigh
Deadline within the next fortnightLow
Chaser, frustration or competitor mentionedMedium
Decision-maker language or senior senderMedium
Existing customer or open quote in the threadLow
Missing information that blocks a quoteSlightly negative

These weights are a starting point, not a rule. A rental company may weight start dates most heavily. An agency may care more about senior senders. Adjust after a week of real mail.

Then add two overrides that ignore the score entirely:

  1. Anything where you promised a reply by a given day goes to the top.
  2. Any complaint goes to a person, not a template.

For more on setting rules for categories and ranking, see our article on categorising and prioritising enquiries with an AI assistant.

Step by step: set up urgency ranking for your morning list

  1. Collect a batch of recent enquiries from Gmail, Outlook or your CRM (HubSpot and Pipedrive both export). Include some that went well and some that went cold.
  2. Mark them yourself as urgent, normal or can wait. Do this before looking at any AI output.
  3. Write your scheme in plain sentences, as above, including your two overrides.
  4. Run the same batch through the AI and compare. Note every disagreement and ask why.
  5. Fix the rule, not the single case. If it missed "before the board meets", add relative-deadline phrases to your rules.
  6. Check the top of the list each morning for a week. If you would reorder it, record what was wrong.
  7. Review weekly. Seasons change what is urgent, so revisit the weights.

The point of the comparison is trust. You are not looking for perfection, just for a ranking that puts the right things in front of you first and shows its reasoning so you can overrule it.

What your morning briefing should look like

A good briefing is short. It lists the few enquiries that need a person today, says why each one is there ("deadline Thursday, sender is head of procurement"), and keeps everything else below the line. It should also include promises you made, such as "I'll get back to you by Friday", because those are deadlines too. If that is your weak spot, our answer on how to stop forgetting quote follow-ups covers the basics, and the morning inbox routine shows how the list fits into your first half hour.

Event and production teams feel this most, because dates drive everything. If that is you, see how this works for event and production companies. Service firms with ad hoc requests can look at the B2B services page.

How BOTrento handles it

BOTrento Chief of Staff is a managed process rather than a chat window you have to prompt. It watches enquiries and quotes in your mailbox and in the data you upload. Every working day it shows a morning overview called Today 1+3, in the app and by email, so the most pressing items are in front of you before you open your inbox. It also catches promises such as "I'll be in touch by Friday" and reminds you of them.

For the items that need a reply, it prepares draft replies, quotes and follow-ups in four languages (Czech, English, German and French). Nothing is sent without a person approving it. BOTrento does not send anything by itself, does not confirm dates or bookings, and does not read attachments, only the email text. It does not replace your CRM or accounting either.

AI use is included in the plan, with a monthly usage limit: you get a warning at 80% and new work pauses at 100% until the next month, with no automatic extra charge. Your own API key is optional. You can see the flow in the process demo, and the plans are on the pricing page.

On privacy: data is stored on servers in Germany (EU). The text needed for a task is processed by the model provider through its API, so a server in the EU is not the same as a closed environment. If GDPR is your concern, the GDPR checklist for AI sales tools is a good place to start, and for specific cases it is worth talking to a lawyer.

The free trial lasts 14 days, with no card and no API key of your own. The 14 days start with your first successful data upload, and you have 7 days to prepare. A person from our team will contact you within 24 hours on working days to help connect your mailbox. We make no promises about revenue or number of orders, which is why you test it on your own enquiries first. The 14-day trial plan shows what to measure.

Mistakes to avoid

  • Trusting keywords alone. "Urgent" in every subject line makes the word meaningless.
  • Treating negative tone as always bad. A blunt message from a decision-maker may simply be efficient.
  • Ignoring the existing customer. A short, calm message from your best account can outrank an angry stranger.
  • Letting the ranking replace judgement. It is a sorted list for a person, not a verdict.

FAQ

Can AI really detect an urgent enquiry?

It can spot written signals such as dates, deadlines, chasers and decision-maker wording in the email text. It cannot see what is only in an attachment or what you know from a phone call, so a person should check the top of the list.

How does AI sentiment analysis work on sales emails?

It reads the wording and compares it with the rest of the thread, looking for frustration, repeated chasers or a sudden change in tone. Treat the result as a hint for you to review, not as a final judgement of the customer.

How do I prioritise sales enquiries by urgency without AI?

Give each enquiry a weight for deadline, tone, sender seniority and existing relationship, then sort by total in a spreadsheet. Add overrides for promised replies and complaints so they always go to the top.

Will the AI reply to urgent enquiries automatically?

Not with BOTrento. It prepares draft replies, and a person approves each one before anything is sent.

Summary

  • Real urgency comes from dates, chasers, decision-maker language and promises you made, not from the word "urgent".
  • Write your scoring scheme down first, with overrides for promised replies and complaints.
  • Test on a batch of real enquiries: mark them yourself, then compare with the AI and fix the rules.
  • Keep the morning briefing short and make it explain why each item is on it.
  • AI ranks and drafts; a person checks the top items and approves everything that is sent.

Try BOTrento free for 14 days

Try BOTrento Chief of Staff on your real enquiries for 14 days, free. Nothing is sent without your approval, and a person from our team will help you connect your mailbox. Fill in a few details and your access arrives by email right away. We are happy to help you connect your mailbox.

14 days free, no card and no API key of your own. The trial starts only once your data is first loaded. Then from €79 per month excl. VAT, AI included.

Nothing is sent without your approval. You add a card at the end, only if you continue; without payment access is blocked until you pay, we keep your data for 30 days and the export stays available. Pricing · See the process demo

No card and no API key of your own. Plan prices exclude VAT.

Related articles