As of 13 August 2026, AI can find deals with an overdue next step.

Most people should do this themselves; the prompt is on this page.

Can you do it?

5 minutesto a draft.

15 minutesto something you’d act on.

Cost, all in£0

Skill neededchat-fluent

Who has to check ityou

What the alternative costsApollo.io is a prospect database with AI outreach sequences and enrichment, rather than a tool for finding overdue steps in an existing sales pipeline.

If this goes wrong: a stale or missing CRM date causes you to chase the wrong deal or overlook one, but you can correct the list against the live record before acting.

What to actually do

Do it yourself

The route this page recommends

A chat interface, chat-fluent skill, and roughly 15 minutes until you can act on the result.

How to actually do it

Open your CRM pipeline and export open deals with the deal name, account, owner, stage, value, last activity date, next-step description, next-step due date and recent activity notes.
Remove unrelated personal data and keep the column headings visible, then save the export as CSV or copy the relevant rows.
Open a chatbot and paste the prompt followed by the CRM export.
Check that the chatbot has treated only open deals with a next-step date before 2026-08-13 as overdue and has not converted blank dates into overdue items.
Open each flagged deal in the live CRM and compare its stage, next-step date, activity history and owner with the returned table.
Send or assign the follow-up only after correcting any stale CRM record and confirming the recommended immediate check with the deal owner.

Prompt

Find deals with an overdue next step in the CRM data below.

Today is 2026-08-13. Treat a deal as overdue only when all of these are true: the deal is open, a next-step due date is present, and that date is before 2026-08-13. Do not treat a blank date as overdue. Exclude closed-won, closed-lost, cancelled and otherwise inactive deals.

Use the deal's current stage, value, owner, account, last activity date, next-step description, next-step due date and any recent activity notes to explain each result. Flag records with missing, contradictory or apparently stale information separately instead of guessing. Do not invent dates, owners, deal values or actions.

Return a table with these columns: deal name, account, owner, stage, value, last activity date, overdue next-step date, next-step description, days overdue, evidence, data-quality warning and recommended immediate check. Sort first by days overdue, then by deal value when a value is available. After the table, give me:
1. the total number of clearly overdue open deals;
2. the deals needing a data-quality check before contact;
3. a short follow-up queue for the owner of each deal.

Use only the supplied data. State any assumptions before the table.

CRM export:
[PASTE CRM EXPORT HERE]

Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.

Use a tool built for this
Second choice
Hand it to a person
The distant third
A person who owns the outcome does this end to end, worth it when the failure is dear.

What it gets wrong

AI cannot see your live CRM unless you give it an export or connect it through an approved integration.
It cannot know whether a postponed next step is still commercially important when the CRM notes do not explain the situation.
It cannot reliably distinguish a genuinely neglected deal from one deliberately waiting for a customer or internal decision.
It cannot keep the list current after the export unless you repeat the task or use a properly configured workflow.
It can rank by dates and supplied fields, but the salesperson still decides which relationship or opportunity deserves attention first.

Even on a YES, the friction has a name: context depth, judgement under ambiguity and real time truth.

How we scored this

Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.

Axis	Score (0–2)
Output	2
Inputs	2
Verification	2
Liability	1
Effort delta	2
Total	9 / 10

The methodology and its thresholds are published in full.

FAQ

Can ChatGPT find overdue deals in my CRM?: Yes, if you export the relevant deal fields and give the model the current date. It can filter open deals by next-step due date, but you must check the results against the live CRM because the export may be stale.
What data does AI need to find overdue sales tasks?: Give it the deal name, account, owner, stage, value, last activity date, next-step description, next-step due date and recent activity notes. It also needs a clear definition of an overdue deal, including how to handle blank dates and closed deals.
Can AI tell which overdue deal I should contact first?: It can create a defensible queue using supplied factors such as days overdue, deal value, stage and recent activity. It cannot know the commercial or relationship context that is missing from the CRM, so the owner should make the final priority decision.
Can AI monitor overdue next steps automatically?: A chatbot cannot monitor a CRM after you paste an export. An approved CRM workflow or integration can run the check repeatedly, but you still need to test its filters and confirm that dates and deal statuses are being updated correctly.

Nearby answers

All Pipeline & forecasting rulings

Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.

The newsletter

AI news, new answers and product picks, straight to your inbox.