AI assistants and search decision

Textwork

A single developer can build a narrow SMS lead-qualification workflow and host it cheaply, but reproducing TextWork's integrations, scale, deliverability, polish, and commercial features would be more work and justify paying the vendor.

Visit website
You pay

$99/mo

$1,188/yr

Read off the official pricing page.

You’d pay instead

$50one-off28 h to build

$150/mo3 h/mo upkeep

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

No open-source build does this yet

Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.

What a replacement has to do

  • Accept a new lead (webhook or CSV) → send initial SMS → receive reply and run LLM-based qualification prompts → extract structured fields and save transcript → surface qualified leads in a simple handoff view or webhook to ATS/CRM.

What it still won’t have

  • Polished, enterprise-ready UI and workflow polish
  • Built-in carrier/phone-number scale and SMS deliverability tuning
  • Official integrations with ATS/CRMs listed (e.g., SmartRecruiters, Salesforce)
  • Commercial SLAs, priority support, and compliance handling for mass texting
  • Ongoing analytics and usage dashboards as provided by the vendor

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

Keep paying

Paying is—cheaper 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 self-hosted SMS lead-nurturing agent using Node.js (Express), Postgres, React for a minimal dashboard, Twilio for SMS, and OpenAI-compatible API (e.g., OpenAI or Anthropic) for conversational qualification. Core features: webhook/CSV lead ingestion, mapping leads to phone numbers, outbound SMS sending and inbound webhook handling, a prompt-driven conversational engine that asks qualification questions, extraction of structured fields into the DB, transcript storage, a REST endpoint to webhook qualified leads to an ATS/CRM, and a tiny dashboard to view conversations and handoff. Out of scope: multi-tenant billing, enterprise SLA, large-scale carrier deliverability tuning, and built-in connectors for specific ATS (except a generic webhook). Include error handling, retry logic for SMS failures, basic unit/integration tests, and deployment instructions (Docker + one-click Postgres).
How we checked2 sources · 3/3 runs agreed · evidence score 60

How the score was reached

  • Partly verdict base52
  • 2 cited sources+1
  • Price verified on pricing page+3
  • 3/3 assessment runs agreed+4
  • Evidence score60

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 · 2

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