AI Lead Generator
Scores every inbound lead against your actual ICP
4 of 8 leads need attention.
8 leads checked. 4 flagged. The longest delay is 29 days.
Start with Stark. Website has the most flagged.
Which lead is worth chasing is a sales call; the list shows leads nobody has contacted and contacts that came too late.
Why rows were flagged
- Qualified lead, never contacted50%
- First contact came over 7 days after creation25%
- Not contacted after 2 days25%
Value flagged by Source
- Website2
- Referral1
- Ads1
Items to act on, worst first
| Item | Source | Value | Days waiting | Why |
|---|---|---|---|---|
| Stark | Referral | 1 | 29 | Qualified lead, never contacted |
| Globex | Website | 1 | 15 | Qualified lead, never contacted |
| Hooli | Ads | 1 | 15 | First contact came over 7 days after creation |
| Umbrella | Website | 1 | 5 | Not contacted after 2 days |
What to do this week
- Resolve Stark first: it is the most urgent on the list.
- Fix the data or the status on every flagged row, then re-run.
- Re-run this check every time the list changes, before it reaches a decision.
Do
- Fix the highest-risk item first, then run the check again on fresh data.
Don't
- Don't act on one row alone: open the source record first.
How to improve
- Add more detail per row (owner, date, source) so the next report can trace each item.
- Add a second period of data so the next report can show whether things are improving.
Demo
Overview
Runs on every inbound lead: enriches from public sources, scores against the ICP you define, explains the score, and drafts a first reply.
The score is always accompanied by the reasoning, so your team can disagree with it — and the routing decision is a recommendation, not a silent action.
Benefits
< 1 day
Same-day response
Every lead handled the day it arrives.
Rep time on real deals
Low-fit leads are triaged out with a reason.
Tells you what it did not know
Every score carries the missing information behind it, so a low-confidence result reads as a gap to fill rather than a verdict.
What it does
ICP scoring with reasoning
Every score comes with the argument behind it.
Public enrichment
Fills gaps from the company website.
Drafted first reply
A personalised opener your team approves before sending.
Routing recommendation
Suggests owner and priority; the write stays gated.
What this changes
What this changes about your week
- It takes over
- Finding and qualifying prospects that match what you actually sell.
- Done today by
- A rep, or an expensive list nobody trusts.
- How often
- Continuously.
- Typical manual effort
- Building and qualifying a usable list is days per campaign.
Why Sales in particular. A list of everyone is a list of nobody. Qualification against your own criteria is what makes the outreach worth sending.
Runs unattended
Started by you or by an event, and it finishes on its own. Nothing waits for someone to be at a desk.
The same standard every time
The two-hundredth item is held to the bar the first one was. Consistency is the part people cannot sustain.
It cannot act on its own
AI Lead Generator has no path to sending, spending or committing. That limit is why its output is safe to act on.
How it runs
This agent runs server-side through the PROMIVO runtime. Each run is logged step by step and every tool call is permission-checked before it executes.
- 1InputValidated against the agent input schema
- 2Modelclaude-sonnet-5 with automatic fallback
- 3Toolsfetch_web_page, extract_structured_data, send_email
- 4PermissionsRuns READ actions automatically; anything higher waits for approval
- 5OutputStructured result matching the output schema
- 6LoggingTokens, duration and every step recorded
Requirements
Integrations
Before you start
- A written ICP definition
- Somewhere to put the scored leads — the output is structured for import
- Connect an email provider if you want the drafted reply sent
- Requires the All-Access plan or higher
Use cases
Inbound triage
Score and route every form fill.
List qualification
Grade an imported list before outreach.
Pricing
All-Access
Billed monthly through your PROMIVO subscription. Cancel at any time.
Runs consume your plan allowance for agent executions and tokens. See plan limits
FAQ
Does it email leads automatically?
Not by default. Drafting is a read action; sending is a write action, needs an email provider connected, and is held for approval unless you raise the risk ceiling deliberately.
What happens to leads it cannot score?
They come back with a low confidence and the specific information that was missing, rather than a guessed tier. A lead you cannot judge is a lead to enrich, not one to discard.
Who pays for the AI usage?
You do, on your own key, billed by your provider. This one runs per lead, so cost tracks inbound volume — worth watching if you connect it to a busy form.
Reviews
Reviews open once customers have run this agent.
Need this agent to work differently?
Tell us what to change and our team will scope a customised version for your business.
Customize this agent