A language and runtime for readable AI workflows

What you can do

model compare ["fast", "code", "best"]
  on suite "examples/eval_suite.json" -> pick
model build blueprint into "out/model.md"

use auto
ask "Summarize: {doc}" -> text
./spark --dry-run my_task.spark

voice {
  listen -> user
  classify Intent { support, sales } from user -> intent
  ask "Reply as {intent}: {user}" -> reply
  speak reply
}

include "lib/ai.spark"
ask "Fix this test failure: {msg}" -> fix

# today: model + ask + voice + classify
# roadmap: retrieve / embed via gateway

Create & tune models

Built-in steps analyze catalog entries, compare them on your eval suite, suggest improvements, and write a blueprint markdown file you review — sugar for planning, not weight training.

1. 1 Analyze Read metrics for one model or your whole catalog
2. 2 Compare Run fast, code, and best on your eval suite
3. 3 Improve Pick quality, speed, cost, or local preference
4. 4 Build Write a blueprint markdown file — not weights

# tune-model.spark — copy, save, run
model code

model analyze "fast" -> report

model compare ["fast", "code", "best"]
  on suite "examples/eval_suite.json" -> comparison

model improve from report prefer quality -> blueprint

model build blueprint into "out/my-model.md"

model build writes a plan and config file only — never starts training jobs. ./spark --dry-run uses fixtures (no keys, no network). Optional live ask uses ./spark --live with any OpenAI-compatible AI_GATEWAY_URL. Open the model wizard or language reference.

Voice & phone workflows

Optional capability: receptionist-style bots, IVR flows, and outbound dial scripts in the same language — dry-run with stub audio; live speech and --pstn-live stay gated.

voice {
  listen -> user
  classify Intent { support, sales, billing } from user -> intent
  ask "Reply helpfully to: {user}" -> reply
  speak reply -> "out/turn.wav"
}

# PSTN off by default — placeholders only until you enable gates
voice pstn status -> st
voice pstn dial "+15555550100" -> call

See AI in 5 Minutes — voice, Playground voice tab, and language reference (listen/speak/pstn).

Native network & web

Optional capability: network, engine fetch, and browser / MITM ops — dry-run fixtures by default; opt in with --allow-net or --allow-net-capture for live HTTP or capture.

network capture probe -> info
network open "examples/fixtures/sample.pcap" -> pcap
network analyze pcap -> traffic_report

engine fetch "file://examples/fixtures/engine/sample.html"
browser run "examples/browser_main.spark"

Not a Python stub driver — asm dispatch today. First-class http get / http post are [roadmap]; use engine fetch for HTTP now. Network + web guide · Language reference · Browser / MITM

Core vs optional

SparkLang is the language and runtime. Gateways, voice, and capture are capabilities you turn on — not the product identity.

Spark IDE + AI coding

Core surface: verified ide ops plus playbooks and review / builder — readable diffs and dry-run tests. Live gateway is optional when you are ready.

include "lib/ai.spark"
ide new "out/ide/task.spark"
ide ask "Explain this buffer" -> reply
./spark --dry-run examples/ide_ask_show.spark

Terminal-first IDE today — not Electron product chrome. IDE status · AI models guide · Programming guide

Learn Spark

Follow the tutorial path — same structure as official language docs for Java or C++.

Hello world

# Dry-run — no network, no API key
./spark --dry-run examples/hello.spark

# Optional live ask — any OpenAI-compatible gateway
export AI_GATEWAY_URL=http://127.0.0.1:4000
./spark --live examples/ask_live.spark

Sample program: use code then ask "…" -> text. See full programming guide and language reference.