Your Monday list, without you.

An unattended lead engine for Ugoki House

Prepared ForNadege Pannetier
Ugoki House

Prepared ByAamir Bajwa
Independent Contractor

Date11 September 2026

Nadege,

Good talking on the call. I read your brief twice. You are not short of demand, callers or data. You are short of hours. Nothing here rebuilds your engine in Clay. Here is what I would do instead.

The problem.

Six clients is the ceiling, and the ceiling is your own week. Every new client costs about a day a week of list building, so two more clients is a week you do not have.

Problem 01

You are the bottleneck

Your words: "That's fine at six clients, but it won't be as we grow." You are not capped by demand or by callers. You are capped by your own hours, and each new client takes another day of them.

Problem 02

Bad data is spending your callers' day

Your words: "Bad data is the single biggest drain on a caller's day." Phone age runs to two years, nothing washes ACMA automatically, nothing checks the person is still there, and the callers sit at about one meeting an hour.

Problem 03

Nothing you have built learns

Your words: "instead of me re-guessing the ICP every month." Transcripts, call logs and booked meetings all exist. Nothing joins them, so which signal actually produced meetings lives in your head, not in the system.

Problem 04

The Lead Map may be working against you

Your words: "it isn't being updated correctly or constantly and so is actually doing more harm than good." A stale suppression layer quietly hides accounts you could have called, and you cannot see what it wrongly excluded.

Problem 05

You cannot audit your own build

Your words: "I'm a designer by background, not a developer." You built a working engine without being one. What you cannot see is the failure modes you have never met, because nobody meets them until they run one of these at twenty clients.

The fix.

Five fixes, one per problem, built on the engine you already have.

Solution 01

It runs without you

Your existing Python skills wired into one scheduled run per client per week. The stages call each other instead of calling you. On Monday you read a finished ranked list in Notion rather than build one.

Solution 02

Data quality with a number on it

ACMA washing every thirty days and on re engagement. A currency check at build time. A three provider phone waterfall so a stale number never reaches a caller. A weekly scorecard per list: wrong number rate, wrong person rate, DNC hits.

Solution 03

The loop closes

One join between Lemlist outcomes, call logs and lead attributes. A weekly read of which signals produced meetings, and a ranking model that uses those measured weights instead of last month's guess.

Solution 04

The Lead Map becomes a ledger

Split from TAM mapping and given one job: recording every brand you have touched, updated on every run, with a freshness stamp and an exceptions view showing what it excluded and why.

Solution 05

And you get me, fortnightly

Everything built in the open and written down plainly so you can change it without me. Fortnightly sessions where you bring what you are building and I tell you what I would do differently.

The proof.

Two of these are the same shape as your build. The rest are in my Upwork portfolio, with case studies and client videos.

Some of the teams I have built this for

Closest match

Origin

Financial wellness platform backed by more than $70M, with clients including DocuSign, DraftKings, Chime and the NBA. Their SDR team worked from static lists with no automation. I built the trigger based playbooks and the priority score, the same mechanism you asked for when you said every lead needs a priority number. On your question about the 35 percent: those calls were warmed. Email went first, then the call, so it is a connect to meeting rate on warmed dials, not cold ones. Plan on a lower number for cold only.

13,000 contacts enriched across 4,900+ target accounts per quarter
Cold call connect rate moved from about 3 percent to 11 percent on AI scored priority lists
25 meetings booked in the first quarter
21.6 percent LinkedIn reply rate across 1,473 touches

Closest match

Brink's

NYSE listed, about $5B in revenue, operating in 100+ countries. I built their SMB outbound engine end to end, aimed at cash heavy multi location operators who do not appear in standard B2B databases. Every account is scored by a custom model estimating monthly cash volume from third party signals, so only real fits reach a rep. A six month engagement is now twelve.

76 SDR appointments tagged to my work in their own Salesforce
$3M+ in pipeline credited to my outbound
Ranked third of twenty lead sources
24,244 sends at 98.7 percent delivered and 0.95 percent hard bounce

Also

Oyster HR

A $1.2B global employment platform. A signal based outbound engine wired into Salesforce, SalesLoft, Clearbit and G2, with the qualification logic, six campaign playbooks and automated account routing. Four months, renewed twice, into twelve months and beyond.

Also Nice Shoes, about 40 meetings in one quarter from cold email. Tearsheet, around 80 meetings from one campaign targeting Money20/20 attendees. Energea, BioStar Renewables, Hiline, Finimize, Montara, Settle, Arist, Open, and more than 50 B2B teams in total. Meetings booked with senior decision makers at Apple, Meta, Airbnb, Visa, Mastercard, Stripe, CVS Health and Business Insider.

Certified on the tools this runs on

Clay Certified Solutions Partner, top 10 percent worldwide, with $100K in revenue referred to Clay in twelve months and Clay implemented for 20+ growth stage teams. Smartlead Certified Expert. HeyReach Expert. Instantly Partner. Better Contact Partner. Prospeo Partner. Five years running outbound.

What you get.

The Build

Eighteen deliverables across eight to ten weeks, grouped by the stage that delivers them, so neither of us can be vague about it later.

0 of 18 Delivered

The timeline.

Eight to ten weeks from kickoff, inside the eight to twelve you set out. The range is deliberate: I would rather test each stage against a real weekly run than call it done on a calendar date.

Audit and mapWeek 1

All six client configurations read end to end. Every stage, every manual step, every silent failure named and ranked by cost.

OrchestrationWeeks 2 to 4

Scheduled unattended runs per client. Run manifests, failure handling, and the Notion approval view.

Data qualityWeeks 4 to 6

ACMA washing, the phone waterfall, the currency check, and the weekly scorecard that makes quality visible.

Feedback loopWeeks 6 to 8

The outcome join, the weekly signal report, and a ranking model per client built on measured results.

Lead Map and handoverWeeks 8 to 10

Suppression ledger rebuilt, documentation written, walkthrough recorded, thirty days of support begins. The last two weeks are there for testing against real runs, not for building.

Total: 8 to 10 weeks

Your investment.

Hourly at $85, with every hour tracked on Upwork. My estimate for the full build, testing included, is 47 to 65 hours. That is an estimate, not a cap and not a floor. The real number is whatever the tracking records, and it can come in under or over.

1. Audit and mapAll six client configurations read end to end6 to 8 hrs$510 to $680

2. OrchestrationScheduled unattended runs, manifests, approval views, tested on a live weekly run14 to 20 hrs$1,190 to $1,700

3. Data qualityACMA washing, phone waterfall, currency check, scorecard10 to 14 hrs$850 to $1,190

4. Feedback loopOutcome join, signal reports, ranking model12 to 16 hrs$1,020 to $1,360

5. Lead Map and handoverSuppression ledger, documentation, walkthrough5 to 7 hrs$425 to $595

EstimateThe full build, testing included47 to 65 hrs$3,995 to $5,525

Rate$85 per hour

Trackedon Upwork, visible to you as it happens

The estimatecan land under or over. You only ever pay for hours actually worked

You approvestage by stage, and can stop after any one

How it runs

Hourly, stage by stage, nothing locked in

You fund one stage at a time. At the end of each I send a written update showing what shipped, the hours it took against the estimate, and what the next stage should take. You decide whether to carry on. If the audit says something is not worth doing, we do not do it, and you have spent a few hours finding that out rather than a few weeks.

What moves the hours

Four things can push a stage past its estimate

A stage that turns out to be broken and has to be fixed before it can be automated. A provider changing its API mid build. Access or approvals arriving late. Data messier than either of us expected. Each of these gets flagged the week it happens, with the hours it will add, before the hours are spent. Never after.

If the number needs to move

Nothing here is take it or leave it

I am flexible on this, and I would rather talk than have you hesitate. If the estimate needs to land somewhere else, or there is a stage you would drop or add, tell me. Book a call or message me on Upwork and we go through the scope together. Trimming or deferring stages is a ten minute conversation, and I re estimate before anything starts. I would rather build a smaller version you run than a full one you sit on.

Your feedback

Open to changes before we start

If anything in this document reads wrong, or you want something removed, say so. This is a first draft of the scope, not the final word on it. Your read of your own engine is better than mine, and I would rather change the plan now than in week three.

After the build

The advisory half, same rate

You wrote that the other half of this is you. Fortnightly sessions where you bring what you are building and I tell you what I would do differently, plus a second opinion before you commit to a direction. Same $85 an hour, billed only for time used, no retainer and no minimum. Most sessions run an hour.

Everything runs on Upwork as weekly fixed price milestones sized to the stage in progress, each funded before the week starts and released against the Friday update. Payment is handled on Upwork throughout, subject to Upwork's fixed price escrow terms.

Provider and API costs stay on your own accounts at cost. Nothing is marked up and nothing is bought in my name.

Guarantee Active

Our Guarantee

Two things sit outside this build and would be quoted separately. Moving the engine onto a VPS, blocked today by the logged in Chrome session over CDP. And onboarding automation for new clients, worth doing once the six are running unattended and not before.

The terms.

Clause 01

Scope of Work

I will deliver the eighteen items listed under What you get, for Ugoki House, across the eight to ten weeks in the timeline.

Anything outside that scope is quoted before any work starts, never assumed into the price. Specifically outside it: rebuilding any stage in Clay, n8n or another platform, moving the engine to a VPS, a purpose built approval interface beyond the Notion views, onboarding automation for new clients, and any work on the outreach or calling side.

Clause 02

Payment Terms

Hourly at $85, with every hour tracked on Upwork. My estimate for the full build is 47 to 65 hours across the five stages, broken down in Your investment. It is an estimate, not a cap or a floor: you pay for the hours recorded, which can come in under or over it, and any stage heading past its estimate is flagged to you before those hours are spent.

It runs as weekly fixed price milestones sized to the stage in progress, each funded before the week starts and released against a written Friday update. You approve stage by stage and can stop after any stage without penalty. If the estimate needs to land lower, scope is trimmed by agreement before work starts.

Advisory after handover is the same $85 an hour, billed only for time used, with no retainer and no minimum. Provider and API costs are billed to your own accounts at cost.

Clause 03

What you provide

So the timeline stays honest, you provide the following.

Access to the existing Claude Code repository and skills
API access to Lemlist across all six accounts
API access to Firmable, AI Ark, Coresignal, ClearOut and ACMA
Notion access to the control panel and the deal trackers
One client's ICP and requirements to build the first end to end run against
Approval turnaround inside two business days at each stage gate

Clause 04

Ownership and confidentiality

Everything I build is yours from the day it is written. Your repository, your API keys, your accounts, your data, your documentation. Nothing is held on my side.

Your client list, your data, your ICPs and your engine stay confidential. Nothing about your business, your clients or your systems is shared, published or reused.

Clause 05

Support and termination

Thirty days of support after handover covers anything in this written scope not working as written. Outside that, and for provider API changes that are nobody's fault, work is quoted before it starts.

Either side can stop with 30 days notice. Milestones already funded and delivered are not refunded, and milestones not yet started are released back to you.

Clause 06

What I will not promise

I will not promise you a wrong number rate, a connect rate or a meeting count. Those depend on your market, your callers and your clients' ICPs, and anyone putting a number on them without having run your lists is guessing. What I commit to is the scope above, on the timeline above, with the quality measured and visible to you every week.

Accepting the Upwork contract constitutes acceptance of this proposal.

Saying yes.

Everything here runs through Upwork, so there is nothing to sign on this page and nothing to pay here.

Step 01

Tell me it is a yes

Message me on Upwork. If anything in the scope is wrong, say so now rather than later, and I will change it before we start.

Step 02

I send the Upwork contract

It carries the same scope, the same weekly milestones and the same dates as this document. Payment is handled on Upwork throughout, subject to Upwork's fixed price escrow terms.

Step 03

Fund the first week and we start

Accepting the Upwork contract constitutes acceptance of this proposal. The audit starts the day the first milestone is funded.

Aamir Bajwa · Confidential · Ugoki House