Build a weighted pipeline forecast
The quarterly review costs two days in Excel before the meeting. The agent pulls plan against actual, who contributed what, and the open-deal forecast.
Hard · 40 min · once a quarter
What you get
Quarter: plan 45m ₽, actual 38.4m ₽ — 85% Largest deals: Romashka 6.2m, Vektor 4.1m Ivanov 12.8m (plan 12), Petrova 7.3m (plan 11) Forecast to quarter end — 9.6m ₽ from open deals Of that, 2.1m sits on deals with no close date 7 clients were duplicated across Bitrix24 and amoCRM
A sample on made-up data — your numbers will be your own.
Who it fits
- The quarterly meeting with the owner, prepared in Excel over two days every single time.
- After a merger sales run in two CRMs, and the figures have to become one picture.
When it won't work
No quarterly plan was ever approved — there is nothing to compare the actual against.
How the agent does it
Give the plan
Send the quarterly plan in the form it was approved in. Say which statuses count as a win for you: the two CRMs name them differently.
Assemble the summary
The agent counts the actual by close dates, not by creation dates. It will not merge the two CRMs into one figure before mapping their stages.
Check the numbers
The owner will read this summary, and every figure in it comes back to you as a question.
What you set
Bitrix24, amoCRM. From you: the revenue plan, the quarter boundaries, the period to compare against, and which statuses count as a win.
What you'll need
amoCRMStarter prompt
Copy the prompt or open it straight in a chat with the agent.
Build the [quarter] sales summary from Bitrix24 and amoCRM and compare it with [the previous period]. Give plan versus actual on revenue overall and by [breakdown — line of business / manager / region]: plan, actual, variance. For each manager: closed amount, number of deals, average deal size, share of the total actual. Separately — the five largest won and five lost deals with the stated loss reason. Don't add up deals from the two systems until you show that their stages and statuses are comparable; count what isn't comparable separately and say so. Build the forecast for the next quarter from open deals with a close date inside it, honestly stating the share of deals with no date. Output XLSX: "Plan vs actual", "Managers", "Deals", a totals line.
Open in chatCheck the quarterly summary. List: — deals counted into the actual by creation date rather than close date; — revenue counted with VAT in one source and without VAT in the other; — managers whose result grew from transferred deals rather than their own; — loss reasons you generalised yourself because the CRM field was empty; — the share of the forecast resting on deals with no close date or no amount; — duplicate clients between Bitrix24 and amoCRM counted twice. Fix the calculations yourself and show what changed; leave the interpretation of reasons and the forecast to me.
A second prompt — the agent uses it to review its own work and show what's left for you.