Build the funnel from CRM and find where deals leak
Plenty of leads come in, few reach payment, and nobody can point to the exact stage. Stage-to-stage flow gets counted and compared with last period.
Medium · 20 min · once a month
What you get
Bitrix24 funnel, June (May in brackets) Stage Deals Moved on Time New 840 Qualified 512 61% (66%) 1.2 days Quote sent 291 57% (58%) 3.4 days Invoice issued 140 48% (61%) 6.1 days Paid 98 70% (69%) 2.0 days Invoice stage down 13 pp; 34 deals moved in a batch
A sample on made-up data — your numbers will be your own.
Who it fits
- The sales head is sure it's the price, and nobody has the numbers stage by stage.
- You changed the script or the stage order and want to see if the transitions moved.
When it won't work
Reps move stages retroactively in batches: the history shows a CRM cleanup day, not the actual process.
How the agent does it
Keep the real stages
Drop the admin and technical stages: deals pass them as a formality and their percentages mean nothing. Say which period we compare against.
Run the calculation
The agent counts what share of deals gets from one stage to the next, using the change history rather than current status. Skipped stages are shown apart.
Check before concluding
Ask the agent to review its own work: where a percentage rests on ten deals, and what it did with deals that are still moving through the funnel.
What you set
Connect Bitrix24 or amoCRM. From you: the period, what to compare against, and which stages are real work rather than admin.
What you'll need
amoCRMStarter prompt
Copy the prompt or open it straight in a chat with the agent.
Calculate the sales funnel from [Bitrix24 / amoCRM] data for [period] and compare with [the previous period]. For each stage: how many deals entered, how many moved on, the conversion into the next stage and the end-to-end conversion from the first stage, the mean and median time in status. Count from the transition history, not from the deal's current status. Show deals that skipped a stage on a separate line rather than spreading them across the adjacent ones. Don't give a list of specific deals or recommendations on them — only figures and the differences between periods. If a stage has fewer than [30] deals, mark its conversion as unreliable and don't draw conclusions from it. Output a table by stage with the two periods side by side and the three stages with the largest conversion drop.
Open in chatReview the funnel calculation. List: — stages where conversion was calculated on fewer than [30] deals; — deals whose stages were changed retroactively in a batch on a single day; — open deals still moving through the funnel, and how you counted them in the denominator; — stages you merged or skipped, and on what basis; — conversion changes explained by a change in the funnel itself rather than by the team's work.
A second prompt — the agent uses it to review its own work and show what's left for you.