Can I code this? An AI Customer Support Chatbot

A chat widget answering questions from your own documentation is a well-documented pattern (retrieval + an LLM call). Handing off to a human cleanly, and not confidently making things up, is where the real engineering care goes.

Borderline
Effort: a weekendRunning cost: $5–$10/mo

Why CanICodeThis says Borderline

  • A website chat widget with real-time messages is the same buildable core as any chat app on this register
  • Retrieval-augmented generation (search your own docs, feed relevant chunks to an LLM) is a well-documented, mature pattern now
  • Logging conversations for later review is ordinary CRUD

The parts that'll cause problems

  • Keeping the bot from confidently inventing wrong answers (hallucination) needs real prompt and retrieval discipline, not just 'add an LLM call'
  • Clean handoff to a human agent when the bot can't help is a genuine, separate workflow feature
  • Multi-channel support (email, SMS, not just website chat) is real integration work per channel

How I'd build this

frontendNext.js
databaseSupabase (with pgvector for retrieval)
hostingVercel / Cloudflare Pages

MVP scope

  • A website chat widget with real-time messages
  • Answers generated by retrieving relevant docs and calling an LLM
  • Conversation logging for review
  • A clear 'talk to a human' escape hatch

Postpone to v2

  • Email and SMS channels, not just website chat
  • Analytics on what people ask and where the bot fails
  • Fine-tuned handoff routing to specific team members

What it actually costs to build

AI agent — with a subscription (Claude Pro/Max, Cursor, etc.)$0 marginal
AI agent — pay-per-use API, no subscription$43–$86 one-time
Hosting, once it's running$5–$10/mo
Domain name, if you want your own~$12/yr

Existing tools solving a similar problem typically run $39–$55/mo — see how they compare below.

The build prompt

Build me an AI support chat widget: embed a chat bubble on my site, index my documentation into a vector database, and on each message retrieve relevant doc chunks and call an LLM API to generate an answer grounded in those chunks. Always include a clear 'talk to a human' option. Log all conversations for review. Real-time widget over WebSockets. Skip email/SMS channels for v1.

← try another idea · browse the full register