Coordinator
One coordinator decides where each piece of work goes, and each piece runs as its own Run. There is no sharding yet.
Coming soonZUGER API
Brief an agent in plain words, read the Run it made, and subscribe to what happens. Approvals and the audit trail come with it.
import os, requests
base = "https://beta.zuger.ai/v1"
auth = {"Authorization": "Bearer " + os.environ["ZUGER_KEY"]}
# brief an agent in plain words: the words become one Run
requests.post(base + "/briefs", headers=auth, json={
"agent": "LEDGER",
"text": "Where does cash stand this week?",
}).raise_for_status()
# then read the Runs, newest first
for run in requests.get(base + "/runs", headers=auth).json()["runs"]:
print(run["agent"], run["status"], run["title"])
# LEDGER RUNNING Where does cash stand this week?
const base = "https://beta.zuger.ai/v1";
const headers = {
Authorization: `Bearer ${process.env.ZUGER_KEY}`,
"Content-Type": "application/json",
};
// brief an agent in plain words: the words become one Run
await fetch(`${base}/briefs`, {
method: "POST", headers,
body: JSON.stringify({ agent: "LEDGER", text: "Where does cash stand this week?" }),
});
// then read the Runs, newest first
const { runs } = await (await fetch(`${base}/runs`, { headers })).json();
for (const r of runs) console.log(r.agent, r.status, r.title);
# live today: brief an agent, then read the Run it made
curl https://beta.zuger.ai/v1/briefs \
-H "Authorization: Bearer $ZUGER_KEY" \
-H "Content-Type: application/json" \
-d '{
"agent": "LEDGER",
"text": "Where does cash stand this week?"
}'
curl https://beta.zuger.ai/v1/runs \
-H "Authorization: Bearer $ZUGER_KEY"
Brief, read, subscribe. The agent reads the tools your company connected, each scoped, for reading and revocable, and every consequential action lands in your approvals rather than in production.
pip install zuger COMINGnpm i @zuger/sdk COMINGTypeScript and Python clients are written, and not yet published. Until they are, call the API directly: every tab above is a call you can make now.
CORE OBJECTS
| Object | What it is |
|---|---|
Company | Your tenant. Holds entities, connected tools, memory and the audit log. |
Agent | One of the ten, on shift or not, with the standing mandate a person gave it in the Console. |
Run | One execution of a brief. Has steps, an answer and any document, and a status such as DONE, BLOCKED, AWAITING_APPROVAL, AWAITING_INPUT, STOPPED_BY_BERNINA or HELD_BY_BERNINA. |
Approval | A stop. Carries the proposed action, the reasoning and the evidence. Only a human resolves it. |
Routine | A brief on a schedule. |
THE RUN OBJECT
Bernina's three decisions ride on every run. They are read-only via the API; they cannot be overridden programmatically.
{
"runId": "run_01j9x",
"agentKind": "LEDGER",
"title": "Where does cash stand this week?",
"status": "AWAITING_APPROVAL", // DONE | BLOCKED | AWAITING_APPROVAL | AWAITING_INPUT | STOPPED_BY_BERNINA | HELD_BY_BERNINA | …
"bernina": {
"pre": { "decision": "pass" },
"inRun": { "decision": "pass" },
"post": { "decision": "redact" }
}
}A FINDING, WITH ITS CITATIONS
Audit-ready findings, as GET /v1/findings returns them. A finding cites at least two artefacts, never an earlier finding, and says what contradicts what. One that does not is never written.
Example response
// GET /v1/findings
{
"state": { "state": "READY" },
"findings": [{
"id": "fnd_01jb2k",
"agentKind": "LEDGER",
"check": "vendor_anomaly",
"severity": "urgent",
"claim": "Invoice 2026-118 names a different bank account from the one Northwind GmbH was paid to in August.",
"evidence": [
{ "kind": "INVOICE", "id": "inv_2026_118" },
{ "kind": "BANK_TRANSACTION", "id": "txn_08_4471" }
],
"proposedAction": "Confirm the new account with Northwind on a number you already have.",
"createdAt": "2026-10-03T08:12:00Z",
"verdict": null,
"runId": "run_01j9x",
"entityId": null,
// planned shape, not in the API yet
"graphPath": [
{ "from": "vendor:northwind", "edge": "PAID_TO", "to": "account:ch93-…-4471", "cites": "txn_08_4471" },
{ "from": "vendor:northwind", "edge": "BILLED", "to": "invoice:2026-118", "cites": "inv_2026_118" },
{ "from": "invoice:2026-118", "edge": "NAMES", "to": "account:de89-…-0130", "cites": "inv_2026_118" }
]
}]
}The graph path is the planned shape, not in the API yet.Coming soon
Coming soon: what Säntis found. The scheduled check isn’t connected to your data yet, so this is usually empty.
HOW ZUGER RUNSComing soon
What the platform is building, part by part. Each part says when it is not live yet.
One coordinator decides where each piece of work goes, and each piece runs as its own Run. There is no sharding yet.
Coming soonOne conversation across every channel, passing through to each Worker what it needs.
Coming soonRules first, then a model only for what is left, so noise starts no Run.
Coming soonContext is loaded in steps: what fits goes inline, the rest is spilled to a store the Worker recalls from.
Coming soonA Run takes new instructions while it runs, “only the third quarter” or “stop”, without starting over.
Coming soonWork that stalls is noticed and picked up again on its own.
Coming soonAny Worker can take any step. Nothing lives only in one process.
Coming soonEvery Run is a governed execution graph. The rules are enforced by the graph, not by prompts.
Coming soonVendors, contracts, invoices, payments and filings, with the source of every edge.
Coming soonTools for agents to reason over the graph: neighbors · timeline · path · anomalies · cite
An eval suite for every agent, run on every change, with accuracy and calibration tracked.
Coming soonVerified work between agents of different companies, through the Zuger Agent Protocol.
Coming soonAn open, versioned way to compute the score, which anyone can check.
Coming soonENDPOINTS
| Method | Path | Does |
|---|---|---|
POST | /v1/briefs | Brief an agent in plain words; the words become one Run |
GET | /v1/runs | List Runs, newest first |
GET | /v1/runs/:id | Fetch a Run: its steps, its answer and any document |
GET | /v1/agents | List agents and whether each is on shift |
GET | /v1/approvals | Everything waiting on a human. Read only: no key can decide |
POST | /v1/routines | Schedule a brief to run every day, week or month |
GET | /v1/memory | Read company memory |
GET | /v1/audit/export | The hash-chained audit log, oldest first. Zuger Max and Zuger Ultra |
POST | /v1/webhooks | Add an address of your own for Zuger to call |
Every route, and the ones no key can call, are in the API reference: who may call each one, what it reads and a curl example, generated from the OpenAPI document.
ERRORS
An error is one object, error, the same on every route. Its type is the kind of failure and its message the whole sentence, in English. A refusal a customer can meet also carries a stable code, and the values its sentence holds in params.
# POST /v1/routines with "schedule": { "every": "day", "hour": 25 }
{
"error": {
"type": "bad_request",
"message": "The hour must be a whole number from 0 to 23.",
"code": "schedule_part_whole_number",
"params": { "part": "hour", "min": "0", "max": "23" },
"field": "schedule"
}
}const WORDS = {
schedule_part_whole_number: "{part}: from {min} to {max}.",
agent_not_shift_put_shift: "Put that agent on shift first.",
};
const PARTS = { hour: "Hour", minute: "Minute" };
function say(e) {
const words = WORDS[e.code];
if (!words) return e.message; // unknown code: the English
const p = { ...e.params };
if (p.part) p.part = PARTS[p.part] ?? p.part;
return words.replace(/\{(\w+)\}/g, (_, k) => p[k] ?? "");
}A code never changes meaning. When the English is reworded, the code stays; a new sentence gets a new code. So match on code, never on message.
Keep your own wording for the codes your app meets, and fill in params by name. A value chosen from a short list (an approval’s state, a category, a part of a schedule) arrives as a code of its own, several joined by commas.
The API speaks English. message is the full sentence with its values in it: show it when your app meets a code it does not know yet.
A code comes with the refusals a customer can meet. Where there is none, type and message are all there is. A 429 also sends Retry-After.
The Console says every code in eight languages exactly like this: the code, its params, the reader’s dictionary, and the English when a code is new.
The API reference lists every code with its English, the params it carries and the values those can take. See the error codes.
OPPORTUNITIES · COMING ONLINE
Built, and switched on one company at a time. Where a company does not have it yet, the first route below answers that it is not available, and the other four refuse with 403.
| Method | Path | Does | Scope |
|---|---|---|---|
GET | /v1/opportunities | The latest brief: what changed, the signals with links to their records, three to five ideas, and the ones you saved or are testing | runs:read |
POST | /v1/opportunities/briefs | Ask Dom for a brief now, with an optional focus. 3 Runs, 5 with web research (6 on Max and Ultra); the first one is free (on the Free plan it starts once your email address is confirmed) | runs:write |
POST | /v1/opportunities/cards/:id/decision | Save an idea, or say it is not for you, with an optional note | runs:write |
POST | /v1/opportunities/cards/:id/prepare | Prepare an idea’s first test: one brief to each agent that prepares something for it, 1 Run each | runs:write |
PATCH | /v1/opportunities/settings | How often, which levels, and whether it researches the web. An owner or admin, signed in | No API key |
An idea is words. What a test needs is proposed by the agents and approved by a person, as every proposal is: nothing here sends, posts or pays. What the brief is.
WEBHOOKS
| Event | Fires when |
|---|---|
run.finished | An agent finished a Run, or stopped to wait for a decision |
run.failed | A Run could not finish |
approval.created | Something consequential is waiting on a human |
approval.decided | A human approved or rejected it |
approval.done | A human marked what they approved as carried out |
Calls carry ids and states only, and are signed: X-Zuger-Signature: t=…,v1=…, where v1 is HMAC-SHA256 of t + "." + body with the secret shown once when you add the address. A failed call is retried five times; an address that keeps failing is switched off.
MCP
Zuger speaks the Model Context Protocol at beta.zuger.ai/mcp: Streamable HTTP, one JSON-RPC message per request, no session. With a key it is a bearer; without one, OAuth 2.1 with dynamic client registration and PKCE, which is how Claude and ChatGPT connect a person. The metadata is at /.well-known/oauth-authorization-server and /.well-known/oauth-protected-resource/mcp.
| Tool | Does | Scope |
|---|---|---|
brief_agent | Hand an agent work in plain words; the words become one Run | runs:write |
list_runs · get_run | Runs, and one Run in full: steps, answer, documents, Bernina’s verdicts, approvals | runs:read |
whats_waiting · list_approvals · get_approval | What is waiting on a person. Read only, with the Console link to decide | approvals:read |
list_routines · create_routine · pause_routine | Standing instructions on a schedule | routines:* |
list_memory · remember | Company memory, read and added to | memory:* |
list_agents · list_findings · export_audit | Who is on shift; what Säntis found (coming soon); the hash-chained log | agents:read · findings:read · audit:read |
There is no tool that approves, signs, files, pays, hires, connects a tool or changes billing, and the server’s instructions say so to the model before it does anything. A person connecting from Claude sees the same list, in plain words, on the Zuger in Claude page; the full technical page is Zuger MCP.
claude mcp add --transport http zuger https://beta.zuger.ai/mcp \
--header "Authorization: Bearer $ZUGER_KEY"THE RULES
0KEYS THAT CAN APPROVE, SIGN, FILE OR PAY
Approval endpoints require a human session token. A machine token can read the queue but never resolve it.
Mandates are edited by people, in the Console. An agent asking to change its own mandate is itself an escalation.
Every key is live, and the gate is what keeps it from anything binding: no key can approve, sign, file or pay. To try things, make a second company on the Free plan and load a month of example data from Settings → Connectors; the agents are told it is example data.
New Runs: from 10 a minute on Free to 300 on Ultra. Every 429 tells you when to retry.
Every error carries a type and an English message; every refusal you can meet adds a stable code and its params. Something unexpected is a 500 with the code something_went_wrong, and nothing about our insides.
Send an Idempotency-Key header with a brief. The same key from the same person within a day answers with the first Run (replayed: true) instead of starting another.
ADDRESSES
| What | Address |
|---|---|
| REST API | https://beta.zuger.ai/v1 |
| MCP | https://beta.zuger.ai/mcp |
| OpenAPI document | https://beta.zuger.ai/v1/openapi.json |
Before a Run starts, while it works, and before you see what it made. On every plan.
Anything binding waits for you, every time. An agent cannot read or change what stops it.
The API is open. Make a key in the Console, under Developers, and send your first brief.
Log in to pick up where the agents left off
By continuing you agree to our Terms & Privacy Policy
Don’t have an account? Create account
Free to start · No card
By continuing you agree to our Terms & Privacy Policy
Already have an account? Log in
If has an account, six digits are on their way. They work once, for ten minutes.
New to Zuger? Create account · Use another address
If can be used, a link is on its way.
Open it on the device you want to sign in with — your phone, most likely. It works once, expires in a few hours, and can only create a passkey: it cannot read anything or approve anything.