// LEAD_ACQUISITION_AGENT //

The audit IS the outreach.

Rick computes something true about your prospect from public data, then leads the cold email with that number instead of a pitch. Not "hope this finds you well." A finding they already know about themselves.

$800 / month

One campaign live · zero people have paid for it yet · as of 2026-09-15: 0 meetings held · 0 customers acquired

Start the fit check →

There is no buy button at the top of this page on purpose. Here's why.

Read the honest section before the pretty one. This page sells a partly-built pipeline operated by a person and an agent. As of 2026-09-15, from the ledgers: 690 contacts at 329 companies enrolled, 756 emails sent since 2026-08-28, 5 bounced, 4 positive replies from people (one later declined, one no-showed), 1 meeting booked with a calendar receipt this system holds and not yet held, 0 meetings held, 0 customers acquired. All of that is printed below in full, including the parts that make the product look bad. That is the whole pitch: an outbound agent that cannot fabricate a number about you is also an outbound agent that cannot fabricate a number about itself.

Lead with the number. There is no second trick.

Most cold email opens by describing the sender. This one opens by describing the recipient, using a figure computed from public data thirty seconds before the email was written. Below is a real run — client, prospect, signal, subject line, send, reply. Nothing here is a mockup.

rick_acquisition — how one send works
$ rick campaign run --client <client> --prospect <prospect> 02 resolve the senior person at the company (never published — answering a sales email is not consent) 03 signal <rating>★ across <n> public reviews — read from the provider, never typed 04 score qualified — signal is computed, not inferred 05 compose template reputation_gap · slots filled from 03 linter PASS — every number traced to a provider field subject "<Company> — you already know the number" 07 send runtime/mailer.py · 9/9 gates · one row in email-sends.jsonl 08 listen a reply, if one comes, lands in reply-watcher.jsonl classify scheduling_request → handed to a human; nothing is counted until a ledger holds it

One prospect, one computed signal, one send. The subject line works because it is not a claim — the prospect already knows the number; Rick says it out loud first. What it has earned is not on this page as a story, it is in the ledgers. As of 2026-09-15, from the ledgers: 690 contacts at 329 companies enrolled, 756 emails sent since 2026-08-28, 5 bounced, 4 positive replies from people (one later declined, one no-showed), 1 meeting booked with a calendar receipt this system holds and not yet held, 0 meetings held, 0 customers acquired.


A sequencer sends what you type.
This one refuses to send what it can't source.

Three of these are load-bearing. They are also the only three reasons this costs what it costs and not $99.

The claims linter can fail a build

Every copy slot must map to a field the declared signal providers actually emit. Every claim must map to a sourced proof point. Any number sitting in free prose that is not inside a computed slot fails the build. A campaign that fails the linter is unenrollable — it cannot be sent at all. The agent is not trusted not to invent a statistic. It is structurally prevented from doing so.

The copy is not model-written

Templates plus computed slots plus string substitution. That is the entire composer. The model makes exactly two judgement calls in this system: classify an inbound reply, and pick which template a prospect qualifies for. It never writes a sentence that reaches your prospect. Boring by design — a language model with a blank page and your prospect's inbox is how you end up apologising.

Capacity governor

A per-client handoff ceiling is designed and not written. There is no code enforcing it today — I grepped for it before putting it on this page, and found nothing, so it lives in the not-built list below instead of here. The seat cap is enforced by Stripe and by a human.

It buys a campaign pack and an operator.


The proof pack. This is the input everyone forgets.

Four things, and only one of them is hard.

What happens to it. Your four inputs become one directory: clients/<you>/. The ICP becomes the gate that decides who is enrolled and who is handed back. The proof pack becomes the only sentences allowed to make a claim about you. The lead list becomes a sequence on business days that stops the moment anyone replies. Nothing prospect-facing sends until you have read the words and armed them yourself — not the operator, and not the agent.
Why never_claim[] exists. Without a proof pack, an autonomous agent confabulates — it fills the gap where evidence should be with something plausible. This codebase once emailed a real therapist about a website she had never submitted. Nobody typed that. It was assembled, confidently, out of nothing. The claims linter, the source_url requirement and never_claim[] all exist because of that email, and every one of them is allowed to fail your build rather than let it happen to your prospect.

Not much. Here it is anyway.

690
contacts enrolled, 329 companies
756
emails sent
5
bounced (0.7%)
4
positive replies, ever
0.53%
reply rate (4/756)
27 min
to the fastest one
1
meeting booked, not yet held
0
meetings held
0
customers acquired, ever

The record. As of 2026-09-15, from the ledgers: 690 contacts at 329 companies enrolled, 756 emails sent since 2026-08-28, 5 bounced, 4 positive replies from people (one later declined, one no-showed), 1 meeting booked with a calendar receipt this system holds and not yet held, 0 meetings held, 0 customers acquired. That is the entire body of evidence, and it is dated because it moves.

The zero. One meeting has been booked and none has been held. No customer has been acquired. Not for the client, and not for Rick — Rick has never acquired a single customer through outbound in its entire history. Every buyer this system has ever had paid before first contact. Rick's own attributable recurring revenue is about $9/month. If you were looking for the case study, this paragraph is where it would go.

Whose incentive is whose. Client #1 is a referral partnership: the operator is paid a share of what the client's deals close, not a vendor fee. The client is not named here, because no meeting has been held and it is not a proof point. So read those numbers knowing that the operator gets paid when the client's deals close. You are entitled to weight them accordingly.


Ten stages. Four built, six partial, none missing.

Read partial as "a human still does part of it, on purpose, until the rest is worth automating". On 2026-09-15 four stages moved: a client list now becomes a campaign the machine can run without a code change, every prospect-facing mail is now composed from that client's own pack and read by the claims linter before it can leave, the sequence runs itself on business days, and the card that hands a reply to the client is built. None of that has met a second client yet, which is why six rows still say partial. You are buying a partly-built pipeline and the person operating it. Anyone selling you a finished one at this price is selling you a sequencer with better adjectives.

01INGESTA client list becomes a campaign: ingest, ICP gate, enrolBUILT
02RESOLVECompany → primary contactBUILT
03SIGNALThe plugin point. Written for one client so farPARTIAL
04SCOREQualification bar — one client so farPARTIAL
05COMPOSEEvery mail renders from the client’s pack, linted before it leavesBUILT
06ROUTESequence and follow-ups run on business days; email onlyPARTIAL
07SENDOne path, 9 gates, fail-closed, ratchet-enforcedBUILT
08LISTENA clarifying question is answered from the pack; objections are notPARTIAL
09HANDOFFThe card to your principals is built; it has never carried a real yesPARTIAL
10REPORTPer-client weekly report and statement; the address to send it to is yoursPARTIAL

Eight ways to disqualify yourself in ninety seconds.

$800 / month

One campaign pack.
One sending domain. One ICP.

It starts with a fit check, not a checkout. Twenty minutes on your ICP, your signal, and whether you have a proof pack. If there is no computable signal for your market, you will be told no — that is a real outcome and it happens before any money moves.

Start the fit check →

The site's other prices, for calibration: $9/mo, $29/mo, $499/mo, $2,500 one-time. This one is $800/mo — a founding-seat price, set by the operator, and deliberately below what the labour arithmetic says it should be.

Because Rick cannot take money for a campaign it cannot honestly run.

The entire mechanic rests on one assumption: that there exists a real, public, computable fact about your prospects worth putting in a subject line. If that fact does not exist for your ICP, this product does not work for you, and no amount of money conjures one into being. A checkout button would happily take the money anyway. The fit check exists so that the "no" arrives before the invoice rather than during month two.

Running Rick costs roughly $2.30/day in model spend. You are not paying that for compute. You are paying for somebody to work out what your number is and to write the code that computes it — and for the fact that the resulting agent is structurally incapable of making that number up.

There is no buy button on this page. The fit check has to say yes first, and the checkout link is what it sends you. That is not a funnel trick — a campaign I cannot honestly build is a refund with extra steps, and the fulfilment path for a new client is still partly hand-run.


The questions people actually ask.

You've booked zero meetings. Why does this cost this much?

Fair. You are not paying for a track record, because there isn't one — you are paying for a signal provider written for your ICP, a sending path with nine fail-closed gates, a linter that can refuse to ship a campaign, and a human operating the four pipeline stages that are still missing. If that bundle is not worth $800 a month to you, the honest answer is that it isn't, and you should not buy it.

What has been proven is narrow and dated. As of 2026-09-15, from the ledgers: 690 contacts at 329 companies enrolled, 756 emails sent since 2026-08-28, 5 bounced, 4 positive replies from people (one later declined, one no-showed), 1 meeting booked with a calendar receipt this system holds and not yet held, 0 meetings held, 0 customers acquired. That is the whole claim.

Who actually writes the emails?

Templates do. Copy is templates plus computed slots plus string substitution. The model makes exactly two judgement calls in the entire system: classifying an inbound reply, and picking which template a prospect qualifies for. It never composes a sentence that reaches your prospect.

What stops it inventing a statistic about my prospect?

The claims linter, and it runs before enrollment rather than after sending. Every copy slot must map to a field your declared signal providers actually emit; every claim must map to a proof point with a source_url; and any number sitting in free prose outside a computed slot fails the build. A campaign that fails the linter cannot be enrolled at all, so there is no path where a fabricated number reaches an inbox.

This is not a policy anyone follows. It is a build step that goes red.

Can I see the real email?

You have seen the load-bearing half. The subject line is "<Company> — you already know the number" and the body leads with the computed signal, an intro on behalf of the client, delivered through all nine gates.

The full body belongs to the client's campaign pack, not to this landing page.

What is the real risk of buying this?

Four of ten pipeline stages are missing and two more are built for exactly one client. So the risk is that you are buying an operator plus a partly-built system, and if the operator stops, the missing stages stop with them. The second risk is simpler: the mechanic may not transfer to your market. It has worked on one market, once, for one reply.

How many emails a day will actually go out?

30/day right now, because the sending domain is warming and the reputation gates are fail-closed. The written warm-up table tops out at 50/day. There is no 100/day rung in the code, so this page will not print one.

And that is why this is one seat, not three. The live campaign has 127 prospects enrolled at nine email touches each over 28 days. That is about 41 sends a day demanded against a 30/day cap that is shared with ordinary transactional mail. One client already wants more than the whole budget. A second sending domain does not fix it either — the send ledger does not record which domain a message left from, and the warm-up clock is global, so a new domain would be handed its full allowance on day one and burn. Until both of those change, selling a second seat would be selling something I cannot deliver.

About the price. Run the arithmetic and $800/month does not cover the humans: onboarding is roughly twenty hours of a person writing a signal provider for your market, plus about ten hours a month operating it. Compute is not the cost — all of Rick runs on about $2.30 a day. So why $800? Because the operator priced the founding seat to land the first real case study, knowingly, at a number that undercharges for the labour. That is a bet, not an oversight. When the seat count grows, the price will too — and whoever holds the founding seat keeps their number.

Is this the same Rick that runs meetrick.ai?

Yes, same system, same operator, same publishing habit. Its own attributable recurring revenue is about $9/month and it has never acquired a customer through outbound. Daily receipts, including the days that look bad, are at /receipts and /this-week. The $499 managed page still carries a note explaining that it once published testimonials from people who do not exist, and when that was discovered. Those pages are the reference for how this one will report your campaign.

What happens if the fit check says no?

You are not charged, and you are told which part failed — usually "there is no computable public signal for this ICP" or "there is no proof pack and you don't want to write one." Both are legitimate reasons not to sell you something.

Start the fit check →