CRM and sales decision

PROSP

A technical user can build a narrow self-hosted replacement that handles personalized messaging and voice-note TTS via a browser extension and hosted backend, but reproducing Prosp’s bundled proxies, cloud-side sending/account rotation, and managed support is non-trivial and would not be included in the minimal replacement.

Visit website
Subscription$79.99/month ✓ verified
Initial build120 hours
Monthly upkeep6 hours + $100
Evidence3/3 runs agree

Open-source builds that already do this

Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All PROSP alternatives, with the arithmetic →

What a replacement has to do

  • Import or collect prospects, generate per-prospect personalized message and TTS voice note, schedule/send messages via the user's LinkedIn browser session, and surface replies in a unified inbox.

What it still won’t have

  • Built-in residential proxies and account rotation to avoid LinkedIn bans
  • Cloud-based sending that operates without the user's machine
  • Dedicated vendor support, managed sharing of per-account proxies, and enterprise onboarding
  • Any proprietary AI voice-cloning model or bundled voice infrastructure

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

Keep paying

Paying ischeaper in year one.

On cash alone, building overtakes the subscription at 2 seats.

Paid seatsseats

Money you would actually spend

Keep paying

Subscription price × seats × 12

Build it

AI build APIs + hosting

Time you would spend

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a minimal self-hosted LinkedIn outreach app+Chrome extension using Node.js (Express) backend, React frontend, Postgres DB, and a worker queue (BullMQ). Scope in: lead import CSV, simple lead profile extractor (from CSV + extension-provided profile snippets), campaign builder that sequences messages, integration with OpenAI (or similar) for per-lead message personalization, TTS generation for voice notes, a Chrome extension that uses the user's LinkedIn session to send messages and report reply events back via a secure webhook, send pacing/scheduling worker to avoid rate spikes, and a unified inbox listing replies and message statuses. Scope out: residential proxy pool, server-side LinkedIn scraping, enterprise billing, multi-tenant account rotation, and any paid voice-cloning/model training. Include retries, rate-limit handling, authentication (OIDC or JWT), logging, end-to-end tests for scheduling and extension<->backend sync, and error handling for API failures.
How we checked3 sources · 3/3 runs agreed · evidence score 67

How the score was reached

  • Partly verdict base52
  • An open-source build was found+5
  • 3 cited sources+3
  • Price verified on pricing page+3
  • 3/3 assessment runs agreed+4
  • Evidence score67

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 3

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

✓ Price read off the page✓ 3 independent runs, one answer✓ Citations limited to fetched pages! 1 moat recorded