How Wang works

Wang is the assistant that builds and runs your Wok for you. Tell it what you need in plain words; it sets up the database, auth, storage, realtime, functions, scheduler, email, SMS, hosting, and the built-in AI model, then builds your app on top, checks each part actually works, and gives you something live. Wang builds against a live Wok throughout the process, so what you get back has already been provisioned, deployed, and tested on the real system you'll use.

✦

Try Wang now — open the dashboard, sign up, and type what you want to build. Wang has the full toolset (provision a Wok, run SQL, deploy functions, register domains, send email, top up credits) and will call the right tools, recover from errors, and show you what it did with verification links.

✦

Most tools hand you the parts and leave you to wire them together and put them online — and things break in the gaps. Wang does the whole job and checks it works before handing it over, so you don't get "it worked on my screen but broke when it went live."

How Wang builds your Wok

Every change — whether you asked for it or Wang did it — goes through the same four steps on your real Wok:

Work on the real thing — Wang changes your actual Wok, not a draft or a guess.
Build it — sets up the data, the rules, the automations and the app.
Try it — Wang actually uses what it just built: for a UI, it opens your app in a real browser and reads the console and network requests for errors a plain status-200 check would miss; for data and APIs, it runs the queries and calls and checks the responses.
Fix or finish — if something's wrong, Wang sees the real error and fixes the cause; if it works, it's already live.

Because Wang tests on the real, running Wok, the classic "it worked while I was building it but broke when it went live" problem doesn't happen.

What Wang can actually do

Ask in plain words and Wang takes the action — set up a Wok, change your database, deploy code, schedule recurring jobs, add logins, register and wire up a domain, put your site online, send and read email, search what you've taught it, top up credits, and connect Slack or Telegram. Developers can drive the same actions directly over the API.

Teach Wang about your business

Out of the box Wang knows the platform; it doesn't know you. So you can teach it, in the dashboard's Wang tab:

Instructions — a short set of rules Wang always follows: tone, naming conventions, "always provision in ca-central-1", "confirm with me before buying any domain", "we bill in CAD". They're layered on top of Wang's base behavior (and never override the safety rules), so every chat acts like it already works at your company.
Knowledge base — drop in your docs: menus, policies, SOPs, product details. Wang searches them on each question (typo-tolerant) and answers from your facts instead of generic defaults — e.g. a customer-support agent that actually knows your refund policy.

Both apply everywhere Wang runs — the dashboard chat and the per-org sidecar — so the whole team gets the same context-aware Wang.

Picks up where you left off

Wang's answer appears as it's written, so you see progress instead of waiting for a wall of text. Your conversation is saved too — log in from any device and the thread is still there.

One Wang, every channel

Connect a Telegram or Slack bot in the dashboard's Channels tab — paste your bot token and your team can message Wang from the chat app they already live in. Wang answers there grounded in the same instructions and knowledge base it uses everywhere, so a teammate asking in Slack gets the same answer as one asking in the dashboard. Engineers drive that same Wang and the same Wok over MCP (Cursor, Claude Code) or the REST API.

Confirmation & guardrails

Wang handles safe, undoable work on its own, but asks first before anything risky — deleting data, buying a domain, sending email, spending money. And it can only ever touch your team's own Wok — never another team's, even if someone tries to trick it into it.

Portable by default (shipped)

A Wok is yours to take. Its entire definition — schema, policies, functions, env, storage config, scheduled jobs, and infra shape — exports to Terraform HCL in one call:

export.sh

curl https://tellwang.com/v1/woks/$WOK/terraform \
  -H "Authorization: Bearer $TELLWANG_KEY" > wok.tf

terraform init && terraform apply
# → redeploys this Wok on a different cloud, your own account, or self-hosted.

No lock-in: TellWang earns its keep by running your Wok well, not by trapping it.

Proven in practice

We built a full point-of-sale system this way first, and building on the live system beat writing code and deploying it separately every time. TellWang is that, packaged for your team.