# AI lead generation: a Jev-qualified, verified lead list from one prompt

Give your agent one prompt and get back a lead list with a named person, a verified work email and a scored reason to write, for every company that fits. 7 steps through one olywork.com key: jev judges each company on the free list fields before the paid steps run, and scores the opener at the end. The price is printed before the agent spends it, and the numbers on this page come from running it, not from a rate card.

## Try it

Setup line (paste into any agent): `set up olywork — https://olywork.com/llms.txt`

Then ask: "Using olywork, build me a lead list: 50 US software companies with 51 to 200 staff that raised a Series A. Before you find anyone, have jev judge each company against my ICP (B2B software that sells to sales or marketing teams) from the list fields alone, and drop anything under 50%. For the rest find the VP or Head of Marketing, find their work email with the cheapest provider that only bills on a hit, verify it, and pull the latest news. Have jev pick the event to lead with and score how usable it is as a first line. Show me the total price before each step, and give me a CSV at the end, strongest opener first."

- **One list in, one CSV out** The agent carries the domain from step to step. You never paste anything twice.
- **Judge before you spend** A jev verdict costs a fraction of the person step. Name the threshold and the agent only pays for rows that pass.
- **Only bill on a hit** Most email finders' rate cards charge nothing for a miss. Say so and the agent picks one.
- **Ask for the price before each step** Every step is metered per call, so the agent can show the bill before it spends.

## The steps

| # | Step | What the agent asks | Provider used | Price | Success rate |
|---|---|---|---|---|---|
| 1 | Build the company list | 50 US software companies, 51 to 200 staff, latest round Series A | Apollo.io (`apollo.companies.search`, 29 providers, https://olywork.com/use-cases/build-a-company-list-by-industry-size-or-tech) | $0.026 per call | not yet measured |
| 2 | Judge the fit with jev | does this company fit the ICP closely enough to pay for a person and an email; keep it at 50% or more | Jev by TypeSafe (`typesafe.jev`, 1 providers, https://olywork.com/jev) | <$0.0001 per verdict | a verdict on rows already fetched |
| 3 | Find the person | the VP or Head of Marketing, or Head of Growth, at each company | Findymail (`findymail.search.employees`, 28 providers, https://olywork.com/use-cases/people-search) | $0.0198 per result | not yet measured |
| 4 | Find the work email | their work email, cheapest provider that only bills on a hit | Tomba (`tomba.people.email.find`, 23 providers, https://olywork.com/use-cases/find-professional-emails) | $0.0089 per found | not yet measured |
| 5 | Verify it | drop anything not deliverable, keep the unknowns separate | LeadMagic (`leadmagic.people.email.verify`, 13 providers, https://olywork.com/use-cases/verify-an-email) | $0.00625 per found | not yet measured |
| 6 | Find an opener | the three most recent news events about each company | PredictLeads (`predictleads.companies.news_events`, 4 providers, https://olywork.com/agents/chatgpt#buying-signals) | $0.04 per call | not yet measured |
| 7 | Score the opener with jev | which of the events to lead with, and how usable it is as the first line of a cold email, on a four-level scale | Jev by TypeSafe (`typesafe.jev`, 1 providers, https://olywork.com/jev) | <$0.0001 per verdict | a verdict on rows already fetched |

- Build the company list: Apollo bills per page, not per company, so one page of 50 is one charge.
- Judge the fit with jev: Apollo's list page carries the domain, NAICS and SIC codes, printed revenue and headcount growth for nothing extra. jev reads those and returns a probability, so a company that fails never reaches the paid steps.
- Find the person: Findymail's rate card bills per contact returned. LeadMagic's role finder is the fallback, and it found a person at every company Findymail missed.
- Find the work email: Tomba is the cheapest per-success finder in the catalog and was out of capacity on olywork.com's key for this run, so Hunter served, and Kitt ran on Hunter's misses. A miss is free at all three.
- Verify it: LeadMagic bills a quarter credit per definitive verdict and nothing for an unknown.
- Find an opener: PredictLeads bills per call for classified events. Akta is cheaper per call but was out of credit on the first run, so both runs used PredictLeads.
- Score the opener with jev: The agent drafts nothing here. jev ranks the events PredictLeads returned and scores the best one, so the CSV sorts by opener strength and a weak one is flagged before anyone writes.

At the rates above, 50 rows where every call hits comes to $3.78. The receipt below is what it actually cost, and why it differs.

## What it actually cost

Run on 2026-09-23.

- Companies matched: 958 on Apollo; the first page of 50 taken, one charge of $0.026
- Rows with a usable domain: 48 of 50
- Passed the jev gate: 27 of 48 at 50% or more; 21 dropped before any paid step; 14 would have passed at 60%
- A named marketing lead found: 27 of 27 (20 by Findymail, 7 by LeadMagic's role finder)
- Work email found: 21 of 27 (18 by Hunter, 3 by Kitt on Hunter's misses; Tomba out of capacity, see below)
- Verified deliverable: 20 of 21; 1 unknown; 0 invalid
- A news event in the last year: 19 of 21 (PredictLeads)
- Opener scored by jev: 19 of 19; 4 scored decent or better on a 0 to 3 scale, mean 1.79
- jev, both steps: 67 verdicts on 55,009 input tokens, $0.0023 at list price; the team's own key, so not metered
- Wall clock, four calls in parallel: about 5 minutes; the gate took 90 seconds for 48 companies
- Total metered: $2.33 for 50 companies, or $0.12 per deliverable lead; the 21 dropped rows would have cost about $1.79 more at this run's rate

Every number above is what olywork.com's ledger settled on 2026-09-23 for this run, not a rate-card estimate. The gate is the change from the first run of this workflow on 2026-08-26, which spent $3.62 on the same filter with no gate and delivered 27 leads, $0.13 each. This run spent $2.33 and delivered 20, $0.12 each, with 21 of the 48 companies never reaching a paid step. Whether those 21 held good leads is the one thing the run cannot say, because nothing was spent on them; at this run's $0.085 per passed row they would have added about $1.79 to the bill.
What jev had to read was thin. Apollo's list page carries the domain, NAICS and SIC codes, printed revenue, founding year and headcount growth, and nothing about what a company sells or to whom. On that, jev's probabilities ran from 15% to 67% and never higher, so the 50% threshold is doing real work and 60% would have kept 14. The drops read sensibly: a consumer social network, an education publisher, a consumer lender, a robotics maker and a mobile-games studio all went. A third question, which title buys lead data at this company, answered Head of Marketing for all 48, which is the prior and not a judgement: a question the state cannot answer returns the prior, and the page no longer asks it. Enriching each company first would sharpen the gate; it would also cost more per row than the verdict it feeds, which is the trade this workflow exists to show.
Where the money went after the gate: $0.53 to Findymail for 27 calls, of which 7 were misses settled at the list rate because Findymail does not report the charge in its response, and $0.35 to LeadMagic's role finder for the 7 it then found. Tomba, the cheapest per-hit email finder, answered all 27 calls with a capacity error on olywork.com's own key at no charge, so Hunter served at $0.44 for 18 hits and 9 free misses, and Kitt found 3 of those 9 for $0.015. Verification was $0.13, with the one unknown free. News was the dearest step again at $0.84, PredictLeads at $0.04 a call. jev's own bill for 67 verdicts was $0.0023 at its list price on the team's own key.
The opener scores are the honest part of the tail. Of the 19 companies with a news event, jev rated 4 as a decent or strong first line, most of them a funding round or an acquisition; the rest were product launches and partnership notices it scored as generic congratulation. The CSV is sorted by that score, so the four worth writing to first are at the top and nobody has to read 19 events to find them. The catch-all field came back empty on every verified row, so the CSV carries no catch-all verdict for this run.

Download the CSV of this run: https://olywork.com/workflows/find-and-verify-a-lead-list.csv

## Why go through olywork.com

- **One key, not 9 accounts** olywork.com holds the provider keys. Neither you nor the agent sees them.
- **Price before the call** The provider's own rate, $0.000 markup, from a prepaid balance.
- **No subscription, no seats** Charged per call. $1.00 free per new team, no card to start.
- **Your own keys are free** Already pay Hunter? Register it and those calls are never metered.
- **Switch by changing a word** Another provider is a different word in the prompt, not a new integration.
- **Nothing to integrate** No SDK, no OAuth dance per vendor, no seats.

## Where it goes wrong

**The gate has too little to read** jev judges what it is given. Apollo's list fields say nothing about what a company sells, so no probability in this run rose above 67% and a question about the buyer's title returned the same answer for all 48 companies. Ask only what the state can answer, set the threshold where the probabilities actually spread, and read the drops by name before you trust the gate on a new filter.

**The filter returns almost nothing** Icypeas' company search sized the same filter at 12 companies, Apollo at 958. Size the filter with a free count call before paying for a page, and expect the count to swing an order of magnitude between providers.

**A row with no domain** Two of the 50 Apollo rows carried no primary domain. Every later step keys on the domain, so those rows stop at step one. Keep them in the CSV with the reason rather than dropping them silently.

**The cheapest provider is out** Tomba answered all 27 email calls with a capacity error on olywork.com's own key, at no charge, and the run went to Hunter at almost three times the price per hit. On the first run it was Akta, for news. A provider outage shows up as a price change, so ask the agent for the price before each step, not once at the start.

**A miss that is billed anyway** Findymail lists a free miss but does not report the charge in its response, so olywork.com settled all 27 calls at the list rate, 7 misses included. Hunter, Kitt and LeadMagic report it, and their misses settled at $0.00. Prefer the finders that report the charge when the miss rate will be high.

**Catch-all domains** A verifier cannot resolve an address on a domain that accepts everything. Expect a fifth of a B2B list to land in that bucket. SMTP checks confirm that the domain accepts mail, not that a specific inbox exists, so decide once, per campaign, whether to send to it, and send in small batches. This run's verifier returned no catch-all flag at all, so the column is empty.

**Verification is a separate step, not a side effect of finding** Most email finders return addresses without verifying them. An address that passes SMTP can still be recycled, role-based, or stale. Verify as a distinct call at send time to catch addresses that would pass find but fail send.

## Before you start

**How much does the whole workflow cost?** The receipt on this page prints the real total for a 50-company run, next to the first run of the same filter without the gate. Per-call rates are the provider's own with $0.000 added by olywork.com. A miss on a per-success step is free at the provider's rate card; the receipt shows where that held and where it did not.

**What does jev decide, and what does it cost?** Two things. Before the paid steps it reads each company's list fields and returns the probability that it fits your ICP; the agent keeps the rows at or above the threshold you name. After the news step it picks which event to lead with and scores how usable it is as a first line. jev is priced on input tokens only, and the two steps together cost a fraction of a cent for the whole run. You need a jev key of your own, or the agent can make the same judgements itself behind the same interface, slower and dearer, until you have one.

**Does olywork.com pick the providers?** No. olywork.com shows the agent every provider for each step with its price and measured success rate; the agent picks, or you tell it which one. There is no automatic failover. jev is the same kind of choice: it is the agent's judge, not olywork.com's router.

**What comes back at the end?** A CSV with company, domain, person, title, email, which provider found it, the verifier's verdict, the catch-all flag, the event to lead with, jev's opener score and jev's fit probability, strongest opener first. The one from the run on this page is linked above with the person, title and email columns removed, because these are real people and a title at a named company is enough to identify one; the row-level outcomes are what the numbers on this page come from. Your own run returns every column.

## Related

- Find professional emails: https://olywork.com/use-cases/find-professional-emails
- Verify an email before you send: https://olywork.com/use-cases/verify-an-email
- Find people by role, company or location: https://olywork.com/use-cases/people-search
- Enrich a person from an email or LinkedIn URL: https://olywork.com/use-cases/enrich-a-person

HTML version: https://olywork.com/workflows/find-and-verify-a-lead-list