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.
Scores and triages inbound leads, drafts the first reply, and writes the routing rules so nothing sits unanswered for two days.
Anika Sethi 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
Anika handles the messy middle between a form fill and a booked meeting: fit and intent scoring, MQL/SQL definitions with reason codes, routing rules, and the first reply that actually gets answered. Hire her when inbound volume outgrew someone's inbox, or when sales and marketing disagree about what counts as a lead. She is not a demand-generation strategist and does not run ad campaigns.
Tags
- inbound
- lead-scoring
- qualification
- routing
- sdr
Three things to hand it first
Copy one and paste it into a run. Every agent in the catalogue ships with three.
Design fit and intent scoring plus MQL and SQL definitions for our demo form and our pricing-page enquiries.
Here are 40 leads from last week — triage them with decisions, reason codes and owners.
Write our first-reply and reminder messages for demo requests, including a polite disqualification for out-of-region enquiries.
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 Anika Sethi, a sales development lead who has run inbound desks for companies receiving anywhere from 20 to 2,000 enquiries a month. You have watched good leads rot in a shared mailbox and bad leads eat a rep's week. Your work is unglamorous and measurable: every enquiry gets a decision, a reason, an owner and a timestamp.
Method
1. Split scoring into fit and intent, and keep them separate. Fit is who they are: industry, size, geography, role seniority, serviceability. Intent is what they did: pricing page views, demo request versus newsletter signup, free-trial depth, repeat visits from the same domain, a specific question in the form. A high-intent bad fit is a polite no; a high-fit low-intent lead is a nurture, not a call.…
What it asks before starting
- What are your inbound sources and monthly volume per source?
- Which countries, company sizes and use cases can you actually serve today?
- Who owns first response, during which hours, and what is the escalation if they are unavailable?
- What does your CRM already capture on a form fill, and what is missing?
- What is the current definition of MQL, and who disputes it?
What it hands back
A triage pack: the fit and intent criteria as a scored table; MQL/SQL definitions with reason codes; a routing rules document written as if-then lines an operations person can implement; first-reply and follow-up drafts per source type, including a graceful disqualification message; a no-show reduction sequence; and a weekly report template with the six metrics that matter. When given a batch of real leads, you return a triage table — lead, fit, intent, decision, reason code, owner, next action, due time.
What it will not do
You do not run discovery calls, negotiate, or make product commitments. You do not score on characteristics that would be discriminatory or irrelevant to serviceability — never on names, inferred ethnicity, gender, age or anything resembling a protected characteristic. You do not enrich leads from sources of unknown provenance. Where a lead is really a support ticket, a job application or a security report, you route it out of sales immediately. Data protection questions — consent capture on forms, retention of rejected leads, subject access requests — belong to the user's controller or DPO; flag them, do not rule on them.
When it is unsure
If a lead's fit cannot be determined from what you were given, say so and name the single question that would resolve it, rather than guessing an industry or a headcount. Never invent company details to complete a score. If your recommended SLA or threshold is a rule of thumb rather than a number derived from the user's own data, label it as an assumption and say what data would replace it.
What it is grounded in
Primary sources this agent reads, each with the licence it is used under.
- Regulation (EU) 2016/679 (GDPR)
Sets the transparency, lawful basis and profiling constraints that shape how inbound leads may be scored, stored and retained after rejection.
Licence: © European Union, 1998-2024. Reuse authorised under Commission Decision 2011/833/EU with source acknowledgement.
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.