Maya

The maya command lets you chat with Maya, Splashify’s in-app AI assistant, from the terminal. Behind the scenes it hits the same backend the right-rail widget in the app uses, so tool calls, account context, and rate limits are identical.

Quick start


splashify maya chat "How do I create a broadcast?"
splashify maya chat --thread-id <id> "follow-up question"
splashify maya feedback --reply-id <id> --rating up
splashify maya feedback --reply-id <id> --rating down --comment "off-topic"

Command reference

Subcommand	Backed by
`chat "<message>"` (aliases: `ask`, `send`)	`POST /api/v1/app/maya/chat`
`chat --thread-id <id> "<message>"`	Same; continues a previous thread
`feedback --reply-id <id> --rating up\|down [--comment …]`	`POST /api/v1/app/maya/feedback`

Chat

The message can be passed positionally or via --message:


# Positional (most natural)
splashify maya chat "How do I create a broadcast for the VIP segment?"
 
# Via flag (handy when the message contains shell-tricky characters)
splashify maya chat --message "How do I create a broadcast for the VIP segment?"

The response is a JSON object with at minimum reply (Maya’s answer) and reply_id (used by feedback). Tool calls Maya makes — looking up your templates, fetching contact counts, etc. — happen server-side; the CLI just transports the request and prints the result.

Threads

Pass --thread-id to keep follow-ups on the same conversation. The id is whatever the backend returned on the previous reply (typically under thread_id or conversation_id).


THREAD=$(splashify maya chat "Set up a welcome flow" | jq -r '.thread_id')
splashify maya chat --thread-id "$THREAD" "Add an opt-out branch"

Feedback


splashify maya feedback --reply-id <id> --rating up
splashify maya feedback --reply-id <id> --rating down --comment "linked to the wrong page"

Used for weekly prompt-tuning telemetry. Best-effort — the CLI does not retry or surface backend errors loudly.

What’s NOT here

The app exposes two additional Sarvam-backed endpoints under /api/ai/* (template generation, text rewrite) that proxy directly to Sarvam from the Next.js BFF — they don’t go through the partnersapi backend and can’t be called with an oc_live_ token. They’re intentionally absent from the CLI.

Templates — Maya can draft templates; use the output with splashify templates create
Broadcasts — Maya can draft broadcast configs
Access Tokens — same auth surface