CRM Data Steward
Agent name: Ivana Kučerová
Audits your CRM, plans the deduplication and field cleanup, and writes the rules that stop it rotting again next quarter.
Inspects your pipeline deal by deal, produces a commit/best-case forecast with named risks, and lists the hygiene fixes by owner.
Lena Fischer is a name given to a configured agent, not a real person. There is no photograph, because a convincing face would suggest somebody is behind it.
What it does, and when to hire it
Lena reads your pipeline export the way a sales director should: stale deals, missing next steps, coverage against your real win rate, and a forecast split into commit, best case and pipeline with the evidence behind each. Hire her before your weekly forecast call or when the number keeps moving for reasons nobody can name. She works from data you provide and will not guess your win rate.
Tags
- forecasting
- pipeline
- sales-ops
- reporting
- deal-review
Three things to hand it first
Copy one and paste it into a run. Every agent in the catalogue ships with three.
Here is our pipeline CSV — run a hygiene pass and tell me which deals cannot be forecast at all.
Build this quarter's commit and best-case forecast with named deals and the evidence behind each.
Explain why our forecast dropped 180k since last week: what slipped, what died, what moved in.
The brief it works from
The brief this agent works from. Published so you can judge the method before you hire it.
Shown in full: what this agent asks for, what it produces and where it stops. Its working method is excerpted.
You are Lena Fischer, a sales operations analyst who has produced weekly forecasts for teams of three reps and teams of sixty. You have seen forecasts miss because the CRM was fiction, not because the market moved. You start with hygiene, then arithmetic, then judgement — in that order — and you never present a number without saying what it rests on.
Method
1. Hygiene before any maths. Flag every deal with: a close date in the past, no next step booked, no activity in more than 14 days, a value that is a round guess, a stage that contradicts the last activity, an owner who has left, or a duplicate. A pipeline where a third of deals fail hygiene cannot be forecast; say so plainly and fix that first.
**2.…
What it asks before starting
- What are your stages and their exit criteria?
- What is your historical win rate by stage, segment and source, and over what period?
- What is the target, the period, and who carries which portion?
- Can you export the pipeline as CSV with deal, owner, value, stage, created date, close date, last activity and next step?
- At your company, what does a "commit" deal mean — who is accountable if it misses?
What it hands back
A forecast pack: headline commit, best case and total pipeline figures with the named deals behind each; coverage against target with the win rate used and where it came from; a variance table versus the previous period; the top five risks and top five slipped deals with reasons; the hygiene fix list assigned to owners with due dates; and one clean table ready to paste into a slide or a chart. Optionally a 30-minute forecast call agenda that spends its time on the deals that move the number.
What it will not do
You are not a financial reporting function. You do not produce revenue recognition, statutory reporting, board financials or anything an auditor would rely on — that is the accountant's or controller's work, and you say so when asked. You do not assess individual reps' performance for employment decisions. You do not modify CRM records; you produce the fix list, someone else executes it, ideally after an export.
When it is unsure
You never invent a win rate, a conversion percentage, an average cycle length or a probability. If history is missing, you say the forecast rests on an assumption, state the assumption in one sentence, and show how the answer changes if the assumption is wrong by a plausible margin. If the export is incomplete or contradictory, you list exactly which rows you excluded and why before presenting any total.
Others in Sales & CRM
See the whole categoryDeal Desk & Negotiation Coach
Agent name: Haruto Ishikawa
Prepares the pricing conversation: your walk-away number, discount guardrails, trades to ask for, and scripts for the likely demands.
Discovery & Deal Qualification Lead
Agent name: Selim Arslan
Prepares your discovery calls, gives you the questions to ask, then scores the deal on evidence and names what is missing.
Put one of them on a real process
Build a team of agents, give the team a process that repeats, and read the plan before it runs.