Amazon Lex
Managed service for building voice and text chatbots using the same speech recognition and language understanding that powers Alexa.
Verified against AWS documentation · 2026-08-24
Key facts
- 01A bot is intents (what the user wants), utterances (how they phrase it), and slots (the data needed to act on it)
- 02Same ASR + NLU engine as Alexa — one bot accepts speech or typed text, and a V2 bot holds multiple language locales
- 03Lambda hooks twice: dialog code hook to validate and steer mid-conversation, fulfillment hook to actually do the work
- 04Limits: 5-minute default idle session TTL (24h max); build on the draft version, publish immutable numbered versions, point aliases at them
Exam triggers
Phrases and scenarios that point here.
- "Chatbot", "conversational interface", "virtual agent", "understands natural language"
- "Same technology as Alexa" → Lex, every time
- Phone menu that understands what callers say instead of press-1 → Lex inside Amazon Connect
- Bot needs to look something up or write to a system → Lex intent fulfilled by Lambda
- One bot serving multiple languages → Lex V2 locales, not one bot per language
Not this service
- Speech to text only, no conversation → Transcribe
- Text to speech only → Polly
- Sentiment, entities, or key phrases out of text → Comprehend
- Natural-language search across documents → Kendra
- The contact centre itself (queues, agents, routing) → Amazon Connect; Lex is only the bot inside it
Use cases
- 01Order-status self-service — caller says "where's my delivery", Lex elicits the order number as a slot, Lambda queries DynamoDB, bot answers without an agent
- 02IVR front door in Amazon Connect that routes on intent instead of a nested keypad menu, and hands off to a human only when the fallback intent fires
- 03Internal helpdesk bot in Slack for password resets and laptop requests, with Lambda opening the ticket and returning the ticket ID
- 04Appointment booking where date, time, and service are slots — the dialog code hook rejects a closed-Sunday slot before the fulfillment hook ever writes to the calendar
- 05One support bot serving EN/ES/FR locales against a single Lambda backend, instead of three bots and three deployments to keep in sync
How it's charged
- 01Priced per request, split into text requests and speech requests — speech costs materially more per request
- 02Request-and-response and streaming conversations are billed on separate rate cards
- 03No charge for building, storing, or idling a bot — you pay only when someone talks to it
- 04A 12-month free tier covers a monthly allowance of both request types for new accounts
- 05Everything you wire in bills separately: Lambda invocations, Amazon Connect minutes, Kendra queries
