Score C · 5.76/10Free to read$100K Hackathon · November 16, 2026 → December 16, 2026Nov 15, 2026

Boomerang Brief

Upload a CSV of dormant client accounts and get back a finished reconnection packet — one page per account with a source-linked public change signal and a ready-to-send note in your voice — as PDF and CRM-importable CSV.

One product, one founder, thirty days. Everything below is built to be executed inside the contest window — the official rules still decide what counts.

Decide in 20 seconds

The facts that decide whether this is worth thirty days of yours.

Speculative5.76/10
MVP build (solo)
5 days
Launch price
$99
Sales to $1,000 revenue
11 customers
First paying customer
Direct cold email to agency owners sourced from public partner directories, with LinkedIn DM as the secondary touch.
Who pays

Owner or partner at a 5–50 person B2B agency or consultancy in the US, UK, Canada or Australia with 40+ past clients and no dedicated salesperson, triggered by a quarter where referrals slowed.

Biggest execution risk

Market demand 3.4/10

Narrow the buyer to a segment with an urgent, already-budgeted problem and reference the specific trigger event that creates willingness to pay.

Why this could work in 30 days: one founder can ship the MVP in 5 days; the plan targets a first sale on day 8; 11 sales at $99 clears $1,000 of collected revenue; strongest signal is speed to first revenue at 8.1/10.

Score and projections come from the generated report and are not guarantees. The $100K Hackathon is run by Ship or Die — read the official rules before you build.

Your first 24 hours

13 concrete actions. Tick them off as you go — nothing is saved or sent.

0/13
Entry price
$99
Solo build
5 days
30d base revenue
$2,160
30d hackathon profit
$1,975
Section 1 of 8

Product opportunity and positioning

Target customer

Owner or partner at a 5–50 person B2B agency or consultancy in the US, UK, Canada or Australia with 40+ past clients and no dedicated salesperson, triggered by a quarter where referrals slowed.

Why now

Agency owners already own the relationship and the data, so there is no marketplace cold-start, no integration and no procurement — a $249 one-time file is an owner decision they can make the same day.

Problem

Reactivating past clients takes 15–25 minutes per account of guessing, checking company pages and writing from scratch, so the old client list rots in a spreadsheet and nothing gets sent.

Solution

Buyer uploads a CSV (company, domain, contact first name, last project, last invoice date), picks a tone, pays, and receives a one-page-per-account PDF plus a CRM-ready CSV where every signal carries a source URL and date, or is honestly flagged 'no signal — manual check'.

Differentiation · Signal platforms sell a CRM-integrated subscription that needs weeks of setup and a revenue team; Boomerang Brief sells the finished artifact from one CSV export, with no integration and no dashboard.

1. Product opportunity and positioning

A 5–50 person agency sits on the cheapest pipeline it owns and never touches it. A web/dev shop, HubSpot or Webflow partner, or RevOps studio typically has 40+ past clients, a spreadsheet listing them, and nobody whose job is to call them. Reactivating one account means remembering who bought, guessing what changed at that company, opening five tabs to check, and writing a note from scratch — 15–25 minutes per account. So the list rots and nothing is sent.

The trigger is specific and observable: a quarter where referrals slowed and the owner is staring at an old client list. At that moment the buyer does not want a platform, a trial or an integration. They want the finished thing.

What is sold. A reconnection packet. The buyer uploads a CSV they already own — company, domain, contact first name, last project summary, last invoice date — picks a tone (warm peer, direct, formal), and pays. The pipeline fetches each account's public pages (homepage, /careers, /blog, /news, /about) plus public search results, keeps only dated change events that resolve to a live source URL (new role, new hire cluster, new service line, funding or press mention, office move), and writes a 90–120 word note citing exactly one signal and exactly one past project. Output: a one-page-per-account PDF plus a CSV with account, signal, source URL, signal date, subject line and note body. Accounts with no citable signal get flagged 'no signal — manual check' rather than a fabricated hook.

Positioning. UserGems proved the core insight — that a former buyer's public change is the warmest reason to reach out today — but delivered it through Salesforce integration, licensed data and a multi-week enterprise setup. Boomerang Brief keeps the insight and strips the delivery: no CRM sync, no continuous monitoring, no prospect database, no SDR agent, no subscription. It sells the artifact to the smallest buyer who feels the pain.

The honest read on the score. JEV scores this concept 57.6/100 (band C, confidence 0.74). It is strongest on speed to first revenue (8.06) and solo build feasibility (7.26), weakest on market demand (3.43) and monetization potential (4.21). That is the correct diagnosis: the build is not the risk, the buyer's urgency is. This plan therefore spends days 6–30 almost entirely on outreach volume and on one proof — that an owner will pay $99–$249 for a file this week, with no demo and no trial. Repeat revenue is explicitly a post-30-day question. The narrow wedge is a one-time packet; the repeat path is the same buyer's next list next quarter.

Section 2 of 8

Smallest sellable MVP

CSV upload with column mapper, public-page fetch plus signal extraction that only emits records with a resolvable source URL and date, a note generator with three tone presets, and a server-rendered PDF plus CRM-ready CSV delivered behind a Stripe Checkout payment.

Must-have features

  • CSV upload with column mapper (company, domain, contact first name, last project, last invoice date) and validation up to 100 rows
  • Per-domain fetcher for homepage, /careers, /blog, /news, /about with timeout, robots-aware fetching and per-account caching
  • Signal extractor returning only {signal_type, evidence_quote, source_url, observed_date} and dropping anything without a resolvable URL and date
  • Note generator with three tone presets that must cite exactly one extracted signal plus the CSV past-project text
  • Server-side PDF renderer producing one page per account plus a summary page
  • Matching CSV export with CRM-ready columns including source URL and signal date
  • Stripe Checkout gating generation, signed download link emailed on payment, 7-day re-download page
  • Confidence gate flagging zero-signal accounts as 'no signal — manual check'

Explicitly out of scope

  • No Salesforce, HubSpot or any CRM integration or sync
  • No continuous monitoring, recurring alerts or subscription automation
  • No contact email or phone enrichment and no contact database resale
  • No LinkedIn or gated-source scraping
  • No self-serve dashboard, team seats or analytics
  • No packets above 100 accounts in v1
  • No free tier and no public trial

Demo flow (what the buyer sees)

  1. Buyer opens the landing page and uploads a CSV of past clients
  2. Column mapper auto-detects headers and asks for the five required fields
  3. Buyer picks a tone preset and sees a row count and price
  4. Stripe Checkout collects payment and the job is queued
  5. Pipeline fetches public pages, extracts dated cited signals and drafts one note per account
  6. PDF packet and CRM-importable CSV are generated and emailed as signed links, with a 7-day re-download page
Build plan

Technical implementation plan

Stack

Next.js on VercelSupabase Postgres + StorageStripe Checkout + webhookManaged web search and fetch APILLM API for signal extraction and note draftingReact-PDF for packet renderingResend for delivery emailPlausible for page counts

Architecture

A single Next.js app on Vercel handles upload, column mapping, checkout and download pages. Supabase stores jobs, parsed rows, extracted signals and generated files. On Stripe webhook confirmation the job flips to paid and a background worker processes accounts one at a time: fetch public pages through the managed fetch API, run the LLM extractor, validate each signal against a live URL and a parsed date, then draft the note. Only validated signals reach the note generator. The renderer assembles the PDF and CSV into Supabase Storage and Resend emails signed links. Failed accounts are retried once, then written into the packet as 'no signal — manual check' so a job always completes.

Build steps

  1. Create Next.js repo, Supabase project and job/row/signal/file tables
  2. Build CSV upload, header auto-detection and the five-field column mapper with row validation
  3. Implement the per-domain fetcher with timeouts, robots handling and caching
  4. Build the LLM signal extractor against a strict JSON schema and add the URL-plus-date validator
  5. Add the note generator with three tone presets and a check that each note cites one signal and one project
  6. Render the PDF (one page per account plus summary) and the CRM-ready CSV
  7. Wire Stripe Checkout, the webhook, job state transitions and signed download links
  8. Add Resend delivery email and the 7-day re-download page
  9. Run three end-to-end test packets on the founder's own CSV and record per-packet cost and failure rate
  10. Add a no-signal fallback path, retry logic and a per-job admin view

AI components

  • LLM signal extraction over fetched page text returning structured records with evidence quotes
  • LLM note drafting constrained to one signal plus one past-project string, with three tone presets
  • Post-generation check that rejects notes citing zero or more than one signal
Hardest technical risk: Signal coverage: a large share of small dormant accounts have thin public footprints or anti-bot protection, so too many pages could come back 'no signal' and the packet reads as empty — the URL-plus-date gate must never be loosened to compensate.
Section 3 of 8

Pricing and monetization

Starter Packet

Entry offer
$99 one-time

For Solo consultant or small studio testing reactivation on a short list

  • Up to 25 accounts
  • One-page dossier per account with source URL
  • Reconnection note per account
  • PDF + CSV export

Full Packet

$249 one-time

For Agency owner with 40+ past clients who wants the whole list worked at once

  • Up to 100 accounts
  • One-page dossier with source URL and observed date
  • Reconnection note with tone preset
  • Suggested subject lines
  • CRM-importable CSV
  • 7-day re-download

Model: One-time purchase per packet, priced by account count, paid up front through Stripe Checkout before generation runs.

First revenue offer: A free 5-account sample brief built from five of their own past clients, with source URLs visible, followed by the Full Packet at $249 with same-day turnaround.

Expected ACV: $180

Upsell path: Repeat packets for the next list next quarter, extra accounts above the tier cap at a per-account rate, and a referral credit of 25 extra accounts for introducing a peer agency owner.

Target customers
36
Revenue model
$8,964
Costs
$240
Profit model
$8,724
Section 4 of 8

First-customer acquisition

Primary channel

Direct cold email to agency owners sourced from public partner directories, with LinkedIn DM as the secondary touch.

Where to find them

  • HubSpot Solutions Partner directory
  • Shopify Partners directory
  • Webflow Experts directory
  • Clutch and DesignRush agency listings filtered to 5–50 person shops
  • Agency 'about' and 'our work' pages that name past clients
  • LinkedIn search for Owner, Founder, Partner, Managing Director at 5–50 person agencies in US, UK, CA, AU

Exact outreach motions

  • Send a 60-word cold email offering a free one-page brief on one of their own former clients, naming that client from their public site
  • Deliver the free 5-account sample brief as a PDF within 24 hours with source URLs visible
  • Follow up on day 3 quoting one line from the sample brief
  • Follow up on day 7 with a deadline-free one-liner and the $249 Full Packet link
  • DM the same owner on LinkedIn only after the second email, one sentence, no attachment
  • Ask every buyer for one referral to a peer agency owner in exchange for 25 extra accounts

Message template

Subject: A brief on one of your former clients\n\nHi {first_name} — I saw {past_client} on your site. I built a one-page brief showing one public change at their company this quarter and a short reconnection note, with the source link so you can check it. Want me to send it free? If it is useful I can do the same for up to 100 of your past clients as one PDF. No call needed.
Week-one goal: 300 owners listed, 200 cold emails sent, 8 free sample briefs delivered, 1 paid packet collected.
Section 5 of 8

30-day execution roadmap

MVP deadline: day 5First sale target: day 830 days planned
Week 1 · Build & validate · 7 days
Day 1Build core

Repo, schema, checkout skeleton

  • Create Next.js repo and Supabase project
  • Define job, row, signal and file tables
  • Stub Stripe Checkout and the success page

Deliverable: Deployed skeleton with database schema and Stripe test checkout

Day 2Build core

CSV ingest

  • Build upload and header auto-detection
  • Ship the five-field column mapper with row validation
  • Persist parsed rows per job

Deliverable: Working CSV upload that rejects malformed rows with clear errors

Day 3Build core

Fetch and extract

  • Implement the per-domain fetcher with timeouts and caching
  • Write the LLM extractor against a strict JSON schema
  • Add the URL-plus-date validator that drops unverified signals

Deliverable: Signal records with live source URLs and dates for a 10-account test set

Day 4Build core

Notes and rendering

  • Write the note generator with three tone presets
  • Add the one-signal/one-project citation check
  • Render PDF and CRM-ready CSV

Deliverable: Full packet generated end to end for the founder's own test CSV

Day 5Ship MVPMVP shipped

Payment gate and delivery

  • Wire Stripe webhook to job state transitions
  • Add Resend delivery email and 7-day re-download page
  • Run three paid test packets and record cost per packet

Deliverable: Live product that takes payment and delivers a packet; MVP complete

Day 6List

300 agency owners

  • Pull 300 owners from partner directories and agency about pages
  • Capture owner name, agency domain and one named past-client logo per agency
  • Load into a spreadsheet with a reply status column

Deliverable: 300-row outreach list with named past clients

Day 7Outreach

First batch and demo packet

  • Build a demo packet from founder test data, labelled as a demo
  • Send 60 cold emails to batch 1
  • Send 15 LinkedIn DMs to owners already emailed

Deliverable: 60 emails sent, demo packet live, reply log started

Week 2 · Launch & first sale · 7 days
Day 8OutreachFirst sale target

Samples and first sale

  • Deliver 3 free 5-account sample briefs within 24 hours
  • Send Full Packet checkout links to every replier
  • Log every objection verbatim

Deliverable: First paid packet collected, or a written reason why not

Day 9Outreach

Batch 2

  • Send 70 cold emails to batch 2
  • Follow up day 3 on batch 1
  • Fix any failed job reported by a buyer

Deliverable: 130 total emails sent, follow-up log current

Day 10Quality

Signal coverage

  • Measure no-signal rate across all packets so far
  • Add two fetch fallbacks for blocked or JS-heavy sites
  • Tune the search query used per account

Deliverable: No-signal rate measured and documented per hundred accounts

Day 11Outreach

Batch 3 and DMs

  • Send 70 cold emails to batch 3
  • Send 40 LinkedIn DMs with one-sentence ask
  • Deliver all outstanding samples

Deliverable: 200 emails and 55 DMs sent cumulatively

Day 12Review

First-sale checkpoint

  • Review reply rate by source directory
  • Kill the two lowest-converting list sources
  • Rewrite the subject line based on replies

Deliverable: Documented reply rate and one revised message

Day 13Quality

Note quality

  • Read 20 generated notes and flag generic ones
  • Tighten the prompt to force one concrete signal and one project detail
  • Add an input hint on the CSV upload for project summary length

Deliverable: Rewritten note prompt and before/after sample pair

Day 14Outreach

Second wave

  • Send 80 cold emails to fresh names
  • Follow up day 7 on batch 1 with one line from their sample
  • Post the offer in two agency owner communities

Deliverable: Second wave sent and community posts live

Week 3 · Repeat & systematize · 7 days
Day 15Outreach

Sample delivery day

  • Deliver all queued sample briefs
  • Add source URLs to every page in the sample format
  • Ask each sample recipient for a yes or no on the paid packet

Deliverable: Every sample delivered with an explicit yes/no ask

Day 16Growth

Referrals

  • Ask every buyer for one peer referral
  • Ship the 25-extra-accounts referral credit
  • Send referral credit to the first two introductions

Deliverable: Referral mechanic live and at least one introduction requested

Day 17Outreach

Message test

  • Split the next 80 emails across two subject lines
  • Track reply rate per subject line
  • Keep the winner, retire the loser

Deliverable: Two-variant subject test with reply counts

Day 18Outreach

Volume

  • Send 80 cold emails
  • Run all pending follow-ups
  • Update the status column for every row

Deliverable: Pipeline spreadsheet fully current with no stale rows

Day 19Review

Mid-point economics

  • Compute collected revenue, refunds and per-packet delivery cost
  • Compare Starter vs Full Packet demand
  • Decide whether to push or retire the Starter tier

Deliverable: Mid-point economics note with one pricing decision

Day 20Proof

Buyer quote page

  • Ask two buyers for permission to quote their packet result
  • Add a short quote block to the landing page only with written permission
  • Remove any claim that lacks permission

Deliverable: Landing page proof section built only from permitted quotes

Day 21Outreach

Wave

  • Send 80 cold emails to a new directory slice
  • Follow up all sample recipients who went quiet
  • Send a short reminder to every checkout-link holder

Deliverable: 80 new emails sent plus a reactivation pass on warm replies

Week 4 · Scale what works · 6 days
Day 22Outreach

Starter push

  • Offer the $99 Starter Packet to everyone who stalled on price
  • Send 60 cold emails with the Starter as the entry offer
  • Log which tier converts from which source

Deliverable: Tier-by-source conversion table

Day 23Outreach

Peers of buyers

  • Ask each buyer to name one peer agency
  • Send a sample brief to every named peer the same day
  • Track peer replies separately

Deliverable: At least three warm peer introductions in progress

Day 24Outreach

Follow-up sweep

  • Follow up every email older than seven days without a reply
  • Send one-line DMs to all unopened-email owners
  • Archive dead rows

Deliverable: Complete follow-up sweep with a clean list

Day 25Offer

Close-out framing

  • Add a same-day turnaround promise to the checkout page
  • Send a short deadline note tied to the founder's capacity
  • Push checkout links to all warm replies

Deliverable: Revised checkout page and close-out email sent

Day 26Outreach

Final new volume

  • Send 80 cold emails to the last list slice
  • Post the offer once more in a different community
  • Deliver all outstanding packets within 24 hours

Deliverable: Final list slice exhausted, delivery SLA held

Day 27Reliability

Cost and failures

  • Measure cost per packet across all jobs
  • Fix the top two failure modes
  • Add a manual retry button to the admin view

Deliverable: Documented cost per packet and two fixes shipped

Days 29-30 · Consolidate · 3 days
Day 28Outreach

Last wave

  • Send 60 cold emails
  • Follow up all sample recipients one final time
  • Confirm every buyer download still works

Deliverable: Final outreach wave sent, all buyer links verified

Day 29Close

Convert everything open

  • Call or DM every warm-but-unpaid contact once
  • Offer Starter pricing to price objectors
  • Confirm payment account and TrustMRR reconciliation

Deliverable: All warm contacts closed out with a recorded outcome

Day 30Wrap

Accounting and submit

  • Reconcile collected revenue, refunds, chargebacks and fees
  • Submit hackathon entry with verified numbers
  • Write a one-page retro on signal coverage and reply rate

Deliverable: Submitted entry with reconciled figures and retrospective

Section 6 of 8

Revenue and profit scenarios

How the numbers are defined

Hackathon profit — Collected revenue − refunds − chargebacks − payment processing fees − paid marketing spend.

Business profit — Hackathon profit − operating costs (hosting, domains, tooling, AI/API delivery costs).

The contest ranks entrants on hackathon profit only. Hosting, tooling and AI/API delivery costs are not deducted by the organisers, but each sale still has to cover them — so we show both. Definitions verified on 2026-11-15 against the official rules.

Stated assumptions

  • All three scenarios are projections built from the stated outreach volumes, not verified revenue or existing customers
  • Conservative assumes 4 packets at a blended $150 average order value from roughly 200 cold emails and modest sample conversion
  • Base assumes 12 packets at a blended $180 average order value from 300+ emails, DMs and referrals
  • Upside assumes 28 packets at a blended $205 average order value with referrals compounding and one $150 sponsored newsletter placement
  • Blended average order value sits between the $99 Starter and $249 Full Packet tiers
  • Payment processing is modelled at Stripe's standard 2.9% + $0.30 card rate, rounded to roughly 4% of collected revenue across all tiers
  • Refunds are modelled under the 10% assumption in the concept, with one Starter refund in Base and one Full Packet refund in Upside
  • Paid marketing is zero in Conservative and Base because the primary channel is organic cold email and DMs
  • Operating costs cover Vercel, Supabase, domain, fetch/search API and LLM inference at roughly $5–$7 of delivery cost per packet plus fixed tooling

Conservative

4 customers
$600
collected revenue · avg payment $150
Refunds
$0
Chargebacks
$0
Payment fees
$24
Paid marketing
$0
Hackathon profit
$576
Operating costs
$30
Business profit
$546

Base case

12 customers
$2,160
collected revenue · avg payment $180
Refunds
$99
Chargebacks
$0
Payment fees
$86
Paid marketing
$0
Hackathon profit
$1,975
Operating costs
$75
Business profit
$1,900

Optimistic

28 customers
$5,740
collected revenue · avg payment $205
Refunds
$249
Chargebacks
$0
Payment fees
$247
Paid marketing
$150
Hackathon profit
$5,094
Operating costs
$160
Business profit
$4,934

Model your own numbers

Runs in your browser · nothing is saved
Collected revenue
$1,188
Payment fees (3.9%)
$46
Paid marketing
$0
Hackathon profit
$1,142
Business profit
$1,067

Hypothetical arithmetic, not a forecast. The fee rate is a flat 3.9% assumption, refunds and chargebacks are left at zero here, and none of this is tracked data.

All figures are scenario projections derived from stated assumptions. They are not verified revenue, not existing customers and not traction.

Section 7 of 8

Main risks and validation experiments

Risk 1Signal coverage is too thin: too many dormant accounts return no citable public change, so the packet feels empty and the buyer asks for a refund.

Mitigation

Keep the URL-plus-date gate strict, flag zero-signal accounts honestly, and show the coverage rate on the sales page before purchase.

Validation experiment

Run the pipeline on 100 public agency past-client domains and measure the share that returns at least one dated cited signal.

Kill criteria

If fewer than 40% of accounts return a citable signal, narrow the target to sectors with heavy public hiring and press activity before selling more packets.

Risk 2Cold outreach converts far below the modelled rate, collapsing the revenue projection.

Mitigation

Send in small batches from day 7 and rewrite the message every three days based on actual replies rather than sending one message 300 times.

Validation experiment

Send 60 emails across two subject lines in week 1 and measure reply rate per line before scaling to 300.

Kill criteria

If reply rate stays under 3% after two message rewrites, change the list source or the offer before spending the remaining days on volume.

Risk 3Free sample briefs are delivered but never convert to paid packets because the owner never acts.

Mitigation

Every sample ships with an explicit yes/no ask and a one-click checkout link for their full list.

Validation experiment

Track sample-to-paid conversion across the first 8 samples delivered.

Kill criteria

If zero of the first 8 samples convert to paid, the artifact is not the bottleneck — test a smaller $99 first packet before continuing.

Risk 4LLM notes read generic because the buyer's past-project text in the CSV is one or two words.

Mitigation

Add an upload hint requiring a short project description and have the generator refuse to draft when project text is under a minimum length, asking for a rewrite instead.

Validation experiment

Compare note quality ratings between CSVs with rich project descriptions and thin ones on the same ten accounts.

Kill criteria

If notes stay generic even with rich CSV input, reposition to signal-only dossiers and drop the note feature from the offer.

Risk 5A buyer runs one packet, learns the format and replicates it manually instead of buying again.

Mitigation

Design the repeat path around the next list next quarter and the referral credit, and price the Starter tier so the first purchase is low-friction.

Validation experiment

Ask every buyer at delivery whether they would run a second packet next quarter on a fresh list.

Kill criteria

If no buyer says yes to a second packet, treat the business as a repeatable one-time service and stop investing in retention features.

Section 8 of 8

Hour-by-hour: the first 24 hours

Hours 1-2

  • Create the Next.js repo, Supabase project and Vercel deployment
  • Write the job, row, signal and file table definitions

Output: Deployed skeleton with a live database schema

Hours 3-5

  • Build CSV upload with header auto-detection
  • Ship the five-field column mapper and row validation

Output: Working CSV ingest that accepts a real agency export and rejects bad rows

Hours 6-8

  • Implement the per-domain fetcher with timeouts and caching
  • Write the LLM signal extractor with the strict JSON schema
  • Add the URL-plus-date validator

Output: First real signal records with live source URLs on a 10-account test set

Hours 9-11

  • Write the note generator with three tone presets
  • Add the one-signal and one-project citation check
  • Render the PDF and CRM-ready CSV

Output: A complete end-to-end packet generated from a test CSV

Hours 12-14

  • Wire Stripe Checkout, webhook and job state transitions
  • Add the Resend delivery email and 7-day re-download page
  • Run one paid test transaction end to end

Output: A live product that takes payment and delivers a packet

Complete report

Full 30-day launch report

Read the full generated report

Boomerang Brief — 30-Day Launch Report

Window: 16 Nov 2026 13:00 UTC to 16 Dec 2026 13:00 UTC. One founder. No customers, no payments and no brand before launch.

1. Product opportunity and positioning

A 5–50 person agency sits on the cheapest pipeline it owns and never touches it. A web/dev shop, HubSpot or Webflow partner, or RevOps studio typically has 40+ past clients, a spreadsheet, and nobody whose job is to call them. Reactivating one account means remembering who bought, guessing what changed at that company, opening five tabs to check, and writing a note from scratch — 15–25 minutes each. So the list rots and nothing is sent.

The trigger is observable: a quarter where referrals slowed and the owner is staring at an old client list. At that moment the buyer does not want a platform, a trial or an integration. They want the finished thing.

Boomerang Brief sells the artifact. The buyer uploads a CSV they already own, picks a tone, and pays. The pipeline fetches each account's public pages plus public search results, keeps only dated change events that resolve to a live source URL, and writes a 90–120 word note citing exactly one signal and exactly one past project. Output: a one-page-per-account PDF plus a CRM-importable CSV. Accounts with no citable signal are flagged 'no signal — manual check' rather than given a fabricated hook.

UserGems proved the insight — a former buyer's public change is the warmest reason to reach out today — but delivered it through Salesforce integration, licensed data and a multi-week enterprise setup. Boomerang Brief keeps the insight and strips the delivery: no CRM sync, no monitoring, no prospect database, no SDR agent, no subscription.

The honest read on the score: JEV rates this 57.6/100 (band C, confidence 0.74), strongest on speed to first revenue (8.06) and solo build feasibility (7.26), weakest on market demand (3.43) and monetization (4.21). The build is not the risk; the buyer's urgency is. Days 6–30 are therefore almost entirely outreach and one proof — that an owner will pay $99–$249 for a file this week, with no demo and no trial.

2. Smallest sellable MVP

CSV upload with a five-field column mapper, a per-domain fetcher, an extractor that emits only source-URL-and-date-backed signals, a three-tone note generator, a server-rendered PDF plus CRM CSV, and Stripe Checkout gating generation. That is sellable. Everything else — dashboard, seats, analytics, monitoring, enrichment, CRM sync — is out of scope for 30 days.

The confidence gate is a feature, not a limitation. A packet that says 'no signal — manual check' on 30% of accounts is more trustworthy than one that invents a hook, and source URLs let the buyer verify before they act.

3. Technical implementation plan

Next.js on Vercel handles upload, mapping, checkout and download. Supabase stores jobs, rows, signals and files. A Stripe webhook flips a job to paid and a worker processes accounts one at a time: fetch, extract, validate, draft, render, email. Only validated signals reach the note generator. Failed accounts retry once, then land as no-signal rows so a job always completes. Resend delivers signed links with a 7-day re-download page.

The hardest risk is coverage, not code. Small dormant accounts have thin public footprints and some sites block fetching. The URL-plus-date gate must never be loosened to make the packet look fuller.

4. Pricing and monetization

Two one-time tiers: Starter Packet at $99 for up to 25 accounts, Full Packet at $249 for up to 100 accounts with subject lines and re-download. One-time pricing matches an owner decision made without procurement. Repeat revenue comes from the same buyer's next list next quarter and from a referral credit of 25 extra accounts. Modelled blended order value is $180.

5. First-customer acquisition

One channel: direct cold email to agency owners found in public partner directories, with LinkedIn DM as a second touch. Build 300 owners with name, domain and one named past-client logo from their own site. Offer a free five-account sample brief with visible source URLs, deliver it within 24 hours, then ask for the $249 Full Packet. Follow up on day 3 with one line from the sample and day 7 with a deadline-free reminder. Ask every buyer for one peer introduction.

Week one goal: 300 owners listed, 200 emails sent, 8 samples delivered, 1 paid packet.

6. 30-day execution roadmap

Days 1–5 build the MVP: schema, CSV ingest, fetch and extract, notes and rendering, then payment and delivery, with a live end-to-end packet on day 5. Days 6–12 are list building, the first 200 emails and the first sale target on day 8. Days 13–19 fix signal coverage and note quality while pushing volume to 300+ emails, adding referrals and a two-variant subject test. Days 20–26 press the Starter tier, run referral introductions, sweep follow-ups and exhaust the list. Days 27–30 harden reliability, measure cost per packet, close every warm contact and reconcile collected revenue before submitting.

7. Revenue and profit scenarios

Projections only, not verified revenue. Conservative: 4 packets at $150 blended, $600 gross, $24 fees, $30 operating. Base: 12 packets at $180, $2,160 gross, $99 refunds, $86 fees, $75 operating. Upside: 28 packets at $205, $5,740 gross, $249 refunds, $247 fees, $150 paid placement, $160 operating. Hackathon profit deducts refunds, chargebacks, fees and paid marketing; business profit further deducts operating cost. Delivery cost stays around $5–$7 per packet, so no sale is below cost.

8. Main risks and validation experiments

Coverage: test 100 public past-client domains and require 40%+ citable signals before scaling. Outreach: split-test two subject lines on 60 emails and require 3%+ reply before sending 300. Sample conversion: track the first 8 samples and require at least one paid packet. Note quality: compare rich versus thin CSV input; if notes stay generic, drop the note feature. Repeat demand: ask every buyer about a second packet next quarter; if nobody says yes, run it as a one-time service.

9. First 24-hour action plan

Hours 1–2: repo, Supabase schema, Vercel deploy. Hours 3–5: CSV upload and column mapper. Hours 6–8: fetcher, extractor and URL-plus-date validator. Hours 9–11: notes, PDF and CSV render. Hours 12–14: Stripe, webhook, Resend delivery and one paid end-to-end test. The day ends with a deployed product that accepts a real agency CSV and returns a real packet.

All financial figures in this report are scenario projections derived from stated assumptions. They are not verified revenue, existing customers or traction.

This brief was generated from public data about established startups, then narrowed and scored for a solo 30-day launch. Revenue and profit figures are scenario models, not verified results, guarantees or evidence of existing customers. Validate demand yourself before you spend a month on it — and check the contest rules for what counts toward your score.

Related ideas

All ideas →
Boomerang Brief: Past-Client Reactivation Packets