Find bottlenecks in the pipeline by stage
A stand-up needs specific deals, not pipeline theory. The agent names the ones sitting past the norm for their stage and says what is holding each.
Medium · 25 min · once a week
What you get
Stage "Approval", norm 7 days — sitting longer: Romashka, 6.2m, 21 days — waiting on client budget Vektor, 1.4m, 15 days — no meeting with the director Stage "Contract", norm 5 days: Stroydetal, 900k, 19 days — lawyers redrafting clause 4 For 3 deals no reason was found in the correspondence: ask the manager — the agent does not invent one.
A sample on made-up data — your numbers will be your own.
Who it fits
- A stand-up where you go through specific deals and decisions, not the pipeline in general.
- The quarter is ending and you need to know which stuck deals can still be pulled through.
When it won't work
Stages are kept formally and a deal only moves on payment — everything will look stuck.
How the agent does it
Set the norms
Say how many days a deal normally sits at each stage — from your experience, not from an average. Set an amount threshold so small deals stay out of the review.
Collect the list
The agent picks the deals past the norm for their stage and takes the reason for the stall from the correspondence. Each gets one proposed action.
Drop the dead ones
This list becomes the stand-up agenda. Discussing a deal that was lost long ago eats the whole team's time.
What you set
Bitrix24, amoCRM. From you: how many days a deal normally sits at each stage, and the amount below which a deal is not worth reviewing.
What you'll need
amoCRMStarter prompt
Copy the prompt or open it straight in a chat with the agent.
Find open deals in Bitrix24 and amoCRM above [threshold] that have been sitting at their stage longer than the norm: [stage — period; stage — period]. For each deal: amount, stage, how many days it's been sitting, owner, last contact, whose court the ball is in — ours or the client's. Take the reason it stalled from comments and correspondence. If it isn't there — don't infer the reason from the stage and the amount, write "reason not recorded" and set "find out the status" as the first action. For each deal propose one specific action for this week and state what you need from me. Don't calculate stage conversion percentages — a list of deals is what's needed. Sort by amount, with what can be closed before the end of [the period] on top.
Open in chatCheck the analysis of stuck deals. List: — deals where the reason for stalling was guessed rather than taken from the correspondence; — deals stuck for an external reason — a tender, the client's budget, the decision maker's holiday — where pushing is pointless; — deals that are effectively lost and should be closed rather than analyzed; — duplicates of the same deal created in both CRMs; — proposed actions that have already been tried and didn't work; — deals where the time at stage is counted from creation rather than from entering the current stage. Edit the wording of the actions yourself; leave the decision to close a deal or not to me.
A second prompt — the agent uses it to review its own work and show what's left for you.