Arch Desk — API

Paste the brief, get a structured backend-architect review.

API tokens Open the app

Review your system brief from your own scripts

Send a system brief — plain prose describing what you are building — and get back one JSON object: a readiness posture, the component plan with each component's data ownership and role, prioritized findings across boundaries, API design, data, scalability, resilience, security, operability, cost and simplicity, each with a concrete design fix, quick wins, and the focus areas to work through first. Everything this app does goes through the SkillSafe App API — plain JSON over HTTPS — so you can hang a review off a design-doc pull request, an RFC about to be circulated, or a project kickoff checklist. Every code step below is shown in cURL, Python, JavaScript, Go, Java, Ruby, PHP and C#; pick a language once and the whole page follows.

Basics

Base URL: https://api.skillsafe.ai/v1/app-api, app slug arch-desk. Every request sends Authorization: Bearer <token> and JSON bodies with Content-Type: application/json. Responses are wrapped in an envelope: {"data": …} on success, {"error": {"code", "message"}} on failure. The review itself is produced by the gpt-terra model. Estimates are free; runs are metered against your credit balance. There is a single run task — one bundle of one brief in, one review out, no follow-up calls and no session state to carry.

StatusMeaning
401Missing or expired token — create a new session.
402Not enough credits — top up at skillsafe.ai/account/credits.
403The token isn't allowed to do this (e.g. a guest reviewing a very large bundle).
404Unknown job or record id.
5xxTransient platform error — retry with backoff.

Browsers enforce CORS for this API, so run these examples from a server, script or terminal — not from another website's frontend.

Step 0 — A tiny client

Every task below is a single HTTP call, so start with a short helper that adds the auth header, sends JSON and unwraps the data envelope. The later steps reuse it.

export API="https://api.skillsafe.ai/v1/app-api"
export TOKEN="YOUR_TOKEN"      # see step 1

# every call looks like:
#   curl -s "$API/..." -H "Authorization: Bearer $TOKEN" [-d '{json}']
# jq is used below to pull fields out of the {"data": ...} envelope
import json, requests

API = "https://api.skillsafe.ai/v1/app-api"
TOKEN = "YOUR_TOKEN"  # see step 1 — read it from your shell environment in real code

def api(method, path, body=None, **headers):
    res = requests.request(method, API + path, json=body,
                           headers={"Authorization": f"Bearer {TOKEN}", **headers})
    payload = res.json()
    if not res.ok:
        raise RuntimeError(payload.get("error", {}).get("message", res.reason))
    return payload["data"]
// Node 18+ (built-in fetch)
const API = "https://api.skillsafe.ai/v1/app-api";
const TOKEN = "YOUR_TOKEN"; // see step 1 — read it from your shell environment in real code

async function api(method, path, body, extraHeaders = {}) {
  const res = await fetch(API + path, {
    method,
    headers: { Authorization: `Bearer ${TOKEN}`, "Content-Type": "application/json", ...extraHeaders },
    body: body === undefined ? undefined : JSON.stringify(body),
  });
  const json = await res.json();
  if (!res.ok) throw new Error(json.error?.message ?? res.statusText);
  return json.data;
}
package main

import (
	"bytes"
	"encoding/json"
	"fmt"
	"net/http"
	"os"
)

const API = "https://api.skillsafe.ai/v1/app-api"

var token = os.Getenv("SKILLSAFE_TOKEN") // see step 1

func call(method, path string, body, out any) error {
	var buf bytes.Buffer
	if body != nil {
		json.NewEncoder(&buf).Encode(body)
	}
	req, _ := http.NewRequest(method, API+path, &buf)
	req.Header.Set("Authorization", "Bearer "+token)
	req.Header.Set("Content-Type", "application/json")
	res, err := http.DefaultClient.Do(req)
	if err != nil {
		return err
	}
	defer res.Body.Close()
	var env struct {
		Data  json.RawMessage `json:"data"`
		Error *struct{ Message string `json:"message"` } `json:"error"`
	}
	json.NewDecoder(res.Body).Decode(&env)
	if res.StatusCode >= 400 {
		return fmt.Errorf("api %s %s: %s", method, path, env.Error.Message)
	}
	if out == nil {
		return nil
	}
	return json.Unmarshal(env.Data, out)
}
// Java 17+, no dependencies. Pair with your JSON library (Jackson, Gson…)
// to read fields out of the returned envelope.
import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class SkillSafe {
    static final String API = "https://api.skillsafe.ai/v1/app-api";
    static final String TOKEN = System.getenv("SKILLSAFE_TOKEN"); // see step 1
    static final HttpClient HTTP = HttpClient.newHttpClient();

    static String api(String method, String path, String jsonBody) throws Exception {
        var req = HttpRequest.newBuilder(URI.create(API + path))
            .header("Authorization", "Bearer " + TOKEN)
            .header("Content-Type", "application/json")
            .method(method, jsonBody == null
                ? HttpRequest.BodyPublishers.noBody()
                : HttpRequest.BodyPublishers.ofString(jsonBody))
            .build();
        var res = HTTP.send(req, HttpResponse.BodyHandlers.ofString());
        if (res.statusCode() >= 400) throw new RuntimeException(res.body());
        return res.body(); // envelope: {"data": …}
    }
}
require "net/http"
require "json"

API = "https://api.skillsafe.ai/v1/app-api"
TOKEN = ENV.fetch("SKILLSAFE_TOKEN") # see step 1

def api(method, path, body = nil)
  uri = URI(API + path)
  req = Net::HTTP.const_get(method.capitalize).new(uri)
  req["Authorization"] = "Bearer #{TOKEN}"
  req["Content-Type"] = "application/json"
  req.body = body.to_json if body
  res = Net::HTTP.start(uri.host, uri.port, use_ssl: true) { |h| h.request(req) }
  payload = JSON.parse(res.body)
  raise (payload.dig("error", "message") || res.message) unless res.is_a?(Net::HTTPSuccess)
  payload["data"]
end
<?php
const API = "https://api.skillsafe.ai/v1/app-api";
$TOKEN = getenv("SKILLSAFE_TOKEN"); // see step 1

function api(string $method, string $path, ?array $body = null): mixed {
    global $TOKEN;
    $ch = curl_init(API . $path);
    curl_setopt_array($ch, [
        CURLOPT_CUSTOMREQUEST  => $method,
        CURLOPT_RETURNTRANSFER => true,
        CURLOPT_HTTPHEADER     => [
            "Authorization: Bearer $TOKEN",
            "Content-Type: application/json",
        ],
        CURLOPT_POSTFIELDS     => $body === null ? null : json_encode($body),
    ]);
    $payload = json_decode(curl_exec($ch), true);
    $status  = curl_getinfo($ch, CURLINFO_RESPONSE_CODE);
    curl_close($ch);
    if ($status >= 400) {
        throw new Exception($payload["error"]["message"] ?? "HTTP $status");
    }
    return $payload["data"];
}
// .NET 8+
using System.Net.Http.Json;
using System.Text.Json;

static class SkillSafe
{
    const string Api = "https://api.skillsafe.ai/v1/app-api";
    static readonly HttpClient Http = new();

    static SkillSafe() =>
        Http.DefaultRequestHeaders.Authorization =
            new("Bearer", Environment.GetEnvironmentVariable("SKILLSAFE_TOKEN")); // see step 1

    public static async Task<JsonElement> ApiAsync(HttpMethod method, string path, object? body = null)
    {
        var req = new HttpRequestMessage(method, Api + path);
        if (body != null) req.Content = JsonContent.Create(body);
        var res = await Http.SendAsync(req);
        var json = await res.Content.ReadFromJsonAsync<JsonElement>();
        if (!res.IsSuccessStatusCode)
            throw new Exception(json.GetProperty("error").GetProperty("message").GetString());
        return json.GetProperty("data");
    }
}

Step 1 — Get a token

POST /guest

A guest token lets you check balances and estimate costs for free. For metered review runs billed to your own account, use your personal token: open the token page, sign in with SkillSafe, and press Copy shell export — it puts export SKILLSAFE_TOKEN="…" on your clipboard, which every example below reads. Treat the token like a password: it can spend your credits. For fully headless scripts, POST /guest mints a guest token with no browser involved.

curl -s -X POST "$API/guest" \
  -H "Content-Type: application/json" \
  -d '{"slug":"arch-desk"}' | jq -r '.data.token'
token = api("POST", "/guest", {"slug": "arch-desk"})["token"]
const { token } = await api("POST", "/guest", { slug: "arch-desk" });
var guest struct{ Token string `json:"token"` }
err := call("POST", "/guest", map[string]string{"slug": "arch-desk"}, &guest)
String envelope = api("POST", "/guest", """
    {"slug":"arch-desk"}""");
// token is at data.token in the returned JSON
token = api("POST", "/guest", { slug: "arch-desk" })["token"]
$token = api("POST", "/guest", ["slug" => "arch-desk"])["token"];
var guest = await SkillSafe.ApiAsync(HttpMethod.Post, "/guest",
    new { slug = "arch-desk" });
var token = guest.GetProperty("token").GetString();

The app stores this browser's token under the localStorage key skillsafe_app_token:arch-desk, on the app's own origin. The token page reads and manages it for you — you never need to open developer tools.

Step 2 — Check who you are and your balance

GET /me

Returns subject_type ("user" or "guest"), subject_id and your credits balance. Check this before reviewing a large bundle.

curl -s "$API/me" -H "Authorization: Bearer $TOKEN" | jq '.data'
me = api("GET", "/me")
print(me["subject_type"], me["credits"])
const me = await api("GET", "/me");
console.log(me.subject_type, me.credits);
var me struct {
	SubjectType string `json:"subject_type"`
	Credits     int64  `json:"credits"`
}
err := call("GET", "/me", nil, &me)
String envelope = api("GET", "/me", null);
// data.subject_type, data.credits
me = api("GET", "/me")
puts "#{me["subject_type"]}: #{me["credits"]} credits"
$me = api("GET", "/me");
echo "{$me['subject_type']}: {$me['credits']} credits\n";
var me = await SkillSafe.ApiAsync(HttpMethod.Get, "/me");
Console.WriteLine($"{me.GetProperty("subject_type")}: {me.GetProperty("credits")} credits");

Step 3 — Estimate the cost

POST /estimate

Send exactly the input you would send to /run; the response's hold_credits is the worst-case cost. Nothing is charged and no job is created, so estimating is free — useful when you are piping a whole kustomize build in and want a ceiling before spending credits.

Input fieldTypeNotes
briefstring, requiredThe system brief, in plain prose: what the product does, who uses it, the expected load (rough numbers beat none), the data, the stack you run or have in mind, and any hard constraints. A proposed design you want challenged is welcome too. This is the model's only evidence — nothing is read from a live system. Briefs longer than 60,000 characters are clipped middle-out, with a [... clipped ...] line showing where. At least 80 characters are needed for a review.
stagestringgreenfield | prototype-live | scaling | legacy-rework | unknown — where the system is in its life. It sets the review's center of gravity: greenfield weighs buildability, scaling weighs the bottleneck math, legacy-rework weighs migration paths. If the brief clearly contradicts it, the brief wins.
concernstringgeneral | scalability | resilience | data | api-design | security — the review emphasis. It weights the findings and the summary, but it is emphasis and not exclusivity: a high-severity finding from another category is never suppressed.
contextstring, optionalExtra context: team size and experience, budget, deadline, compliance constraints, technology decisions already locked in and not up for debate, and risks you have already chosen to accept. Clipped at 20,000 characters.
prescan_factsobject, optionalWhat a client-side scanner mechanically matched in the brief: {"signals": [], "flags": []}. Each entry is {id, label}. Signal ids look like sig:postgres or sig:num-40-requests-second (technologies and load numbers the brief names); flag ids are gap checks — no-scale, no-latency, no-storage, no-auth, no-failure, no-consistency, sensitive-unprotected, no-team. Every flag id you send comes back in coverage_check. The web UI fills this from its own scan; API callers may omit the field or send the two empty arrays.
retry_notestring, optionalOnly set by the app's automatic reformat retry when a first reply was not valid JSON. Leave it out.
cat > brief.txt <<'TXT'
SnapCrate is a photo-delivery app for wedding photographers.
About 3k photographers, 60k galleries a year, peak 40 requests/second.
Plan: one Node API, Postgres, S3 for originals, workers for zip exports.
Pro accounts pay by card monthly. Two engineers, launch in eight weeks.
TXT

jq -n --rawfile brief brief.txt \
  '{brief: $brief,
    stage: "greenfield",
    concern: "general",
    context: "Two engineers, comfortable with Node and Postgres; $500/month infra budget.",
    prescan_facts: {signals: [], flags: []}}' > input.json

curl -s -X POST "$API/estimate" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -d @input.json | jq '.data.hold_credits'
BRIEF = """SnapCrate is a photo-delivery app for wedding photographers.
About 3k photographers, 60k galleries a year, peak 40 requests/second.
Plan: one Node API, Postgres, S3 for originals, workers for zip exports.
Pro accounts pay by card monthly. Two engineers, launch in eight weeks.
"""

payload = {
    "brief": BRIEF,
    "stage": "greenfield",
    "concern": "general",
    "context": "Two engineers, comfortable with Node and Postgres; $500/month infra budget.",
    "prescan_facts": {"signals": [], "flags": []},
}

est = api("POST", "/estimate", payload)
print("worst case:", est.get("hold_credits", est.get("credits")), "credits")
const brief = `SnapCrate is a photo-delivery app for wedding photographers.
About 3k photographers, 60k galleries a year, peak 40 requests/second.
Plan: one Node API, Postgres, S3 for originals, workers for zip exports.
Pro accounts pay by card monthly. Two engineers, launch in eight weeks.
`;

const payload = {
  brief,
  stage: "greenfield",
  concern: "general",
  context: "Two engineers, comfortable with Node and Postgres; $500/month infra budget.",
  prescan_facts: { signals: [], flags: [] },
};

const est = await api("POST", "/estimate", payload);
console.log("worst case:", est.hold_credits ?? est.credits, "credits");
const brief = `SnapCrate is a photo-delivery app for wedding photographers.
About 3k photographers, 60k galleries a year, peak 40 requests/second.
Plan: one Node API, Postgres, S3 for originals, workers for zip exports.
Pro accounts pay by card monthly. Two engineers, launch in eight weeks.
`

payload := map[string]any{
	"brief":   brief,
	"stage":   "greenfield",
	"concern": "general",
	"context": "Two engineers, comfortable with Node and Postgres; $500/month infra budget.",
	"prescan_facts": map[string]any{
		"signals": []any{}, "flags": []any{},
	},
}

var est struct{ HoldCredits int64 `json:"hold_credits"` }
err := call("POST", "/estimate", payload, &est)
String brief = """
    SnapCrate is a photo-delivery app for wedding photographers.
    About 3k photographers, 60k galleries a year, peak 40 requests/second.
    Plan: one Node API, Postgres, S3 for originals, workers for zip exports.
    Pro accounts pay by card monthly. Two engineers, launch in eight weeks.
    """;

String jsonPayload = """
    {"brief": %s,
     "stage": "greenfield",
     "concern": "general",
     "context": "Two engineers, comfortable with Node and Postgres; $500/month infra budget.",
     "prescan_facts": {"signals": [], "flags": []}}
    """.formatted(toJsonString(brief));

String envelope = api("POST", "/estimate", jsonPayload);
// worst-case cost is at data.hold_credits
BRIEF = <<~TXT
  SnapCrate is a photo-delivery app for wedding photographers.
  About 3k photographers, 60k galleries a year, peak 40 requests/second.
  Plan: one Node API, Postgres, S3 for originals, workers for zip exports.
  Pro accounts pay by card monthly. Two engineers, launch in eight weeks.
TXT

payload = { brief: BRIEF,
            stage: "greenfield",
            concern: "general",
            context: "Two engineers, comfortable with Node and Postgres; $500/month infra budget.",
            prescan_facts: { signals: [], flags: [] } }

est = api("POST", "/estimate", payload)
puts "worst case: #{est["hold_credits"] || est["credits"]} credits"
$brief = <<<'TXT'
SnapCrate is a photo-delivery app for wedding photographers.
About 3k photographers, 60k galleries a year, peak 40 requests/second.
Plan: one Node API, Postgres, S3 for originals, workers for zip exports.
Pro accounts pay by card monthly. Two engineers, launch in eight weeks.
TXT;

$payload = [
    "brief"         => $brief,
    "stage"         => "greenfield",
    "concern"       => "general",
    "context"       => "Two engineers, comfortable with Node and Postgres; $500/month infra budget.",
    "prescan_facts" => ["signals" => [], "flags" => []],
];

$est = api("POST", "/estimate", $payload);
echo "worst case: " . ($est["hold_credits"] ?? $est["credits"]) . " credits\n";
var brief = """
    SnapCrate is a photo-delivery app for wedding photographers.
    About 3k photographers, 60k galleries a year, peak 40 requests/second.
    Plan: one Node API, Postgres, S3 for originals, workers for zip exports.
    Pro accounts pay by card monthly. Two engineers, launch in eight weeks.
    """;

var payload = new {
    brief,
    stage = "greenfield",
    concern = "general",
    context = "Two engineers, comfortable with Node and Postgres; $500/month infra budget.",
    prescan_facts = new {
        signals = Array.Empty<object>(), flags = Array.Empty<object>(),
    },
};

var est = await SkillSafe.ApiAsync(HttpMethod.Post, "/estimate", payload);
Console.WriteLine($"worst case: {est.GetProperty("hold_credits")} credits");

prescan_facts.flags is how you make the review answer for gaps you already know about. Send {"signals": [{"id": "sig:postgres", "label": "postgres"}], "flags": [{"id": "no-latency", "label": "no latency target stated"}]} and every flag id comes back in coverage_check — addressed by a finding or an open question, or set aside with the reason. Nothing you flag is silently dropped, which makes it the field to assert on in an automated check.

Step 4 — Run the review and wait for the result

POST /run
GET /jobs/{job_id}

/run takes the same input as /estimate, places a credit hold and returns a job_id. Poll /jobs/{job_id} every 1–2 seconds until status is succeeded or failed (a run typically takes 30–90 s, since every finding carries a concrete design fix). Always send an Idempotency-Key header so a network retry can't start a second, double-charged run. The review is in output — usually nested as output.output, and as a JSON string, so parse defensively. The samples below print the posture, the component plan, the prioritized findings and the focus areas, then save the whole object to review.json.

JOB_ID=$(curl -s -X POST "$API/run" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -H "Idempotency-Key: ad-$(date +%s)" \
  -d @input.json | jq -r '.data.job_id')

while :; do
  JOB=$(curl -s "$API/jobs/$JOB_ID" -H "Authorization: Bearer $TOKEN")
  STATUS=$(echo "$JOB" | jq -r '.data.status')
  [ "$STATUS" = "succeeded" ] || [ "$STATUS" = "failed" ] && break
  sleep 2
done

# unwrap the review once, then read it
echo "$JOB" | jq -r '.data.output.output' > review.json

jq -r '
  "\(.review_name) [\(.posture)]: \(.verdict)",
  "",
  "COMPONENTS",
  (.components[] | "  \(.type)/\(.name) owns \(.owns) - \(.role)"),
  "",
  "FINDINGS",
  (.findings[] | "  [\(.priority)] \(.id) \(.category) \(.component): \(.problem)"),
  "",
  "QUICK WINS",
  (.quick_wins[] | "  - \(.)"),
  "",
  "FOCUS AREAS",
  (.focus_areas[] | "  \(.area) - \(.why)"),
  "",
  "COVERAGE",
  (.coverage_check[] | "  \(.id): \(if .addressed then "ok" else "SET ASIDE" end) - \(.note)")' \
  review.json

# fail the pipeline on anything critical
jq -e '[.findings[] | select(.priority == "critical")] | length == 0' review.json > /dev/null \
  || { echo "critical findings present"; exit 1; }
import time

job_id = api("POST", "/run", payload,
             **{"Idempotency-Key": "ad-001"})["job_id"]

while True:
    job = api("GET", f"/jobs/{job_id}")
    if job["status"] in ("succeeded", "failed"):
        break
    time.sleep(1.5)

if job["status"] == "failed":
    raise RuntimeError(job.get("error", "run failed"))

raw = job["output"]
if isinstance(raw, dict) and "output" in raw:
    raw = raw["output"]
review = json.loads(raw) if isinstance(raw, str) else raw

print(f'{review["review_name"]} [{review["posture"]}]: {review["verdict"]}')
for r in review["components"]:
    print(f'  {r["type"]}/{r["name"]:<20} owns={r["owns"]:<28} {r["role"]}')
for f in review["findings"]:
    print(f'  [{f["priority"]:>8}] {f["id"]} {f["category"]} {f["component"]}')
    print(f'      L:{f["likelihood"]}/S:{f["severity"]} {f["problem"]}')
    print(f'      fix: {f["fix"]}')
    if f["snippet"]:
        print("      snippet:", f["snippet"].splitlines()[0], "...")
for w in review["quick_wins"]:
    print("  win:", w)
for a in review["focus_areas"]:
    print(f'  focus {a["area"]} {a["finding_ids"]} - {a["why"]}')
for c in review["coverage_check"]:
    print(f'  {c["id"]}: {"ok" if c["addressed"] else "SET ASIDE"} - {c["note"]}')

with open("review.json", "w", encoding="utf-8") as fh:
    json.dump(review, fh, indent=2)

critical = [f for f in review["findings"] if f["priority"] == "critical"]
if critical:
    raise SystemExit(f"{len(critical)} critical finding(s)")
import { writeFileSync } from "node:fs";

const { job_id } = await api("POST", "/run", payload,
  { "Idempotency-Key": crypto.randomUUID() });

let job;
do {
  await new Promise((r) => setTimeout(r, 1500));
  job = await api("GET", `/jobs/${job_id}`);
} while (job.status !== "succeeded" && job.status !== "failed");

if (job.status === "failed") throw new Error(job.error ?? "run failed");

const raw = job.output?.output ?? job.output;
const review = typeof raw === "string" ? JSON.parse(raw) : raw;

console.log(`${review.review_name} [${review.posture}]: ${review.verdict}`);
for (const r of review.components) {
  console.log(`  ${r.type}/${r.name} (owns ${r.owns}): ${r.role}`);
}
for (const f of review.findings) {
  console.log(`  [${f.priority}] ${f.id} ${f.category} ${f.component}`);
  console.log(`      L:${f.likelihood}/S:${f.severity} - ${f.fix}`);
}
for (const w of review.quick_wins) console.log(`  win: ${w}`);
for (const a of review.focus_areas) {
  console.log(`  focus ${a.area} (${a.finding_ids.join(", ")}): ${a.why}`);
}
for (const c of review.coverage_check) {
  console.log(`  ${c.id}: ${c.addressed ? "ok" : "SET ASIDE"} - ${c.note}`);
}

writeFileSync("review.json", JSON.stringify(review, null, 2));

const critical = review.findings.filter((f) => f.priority === "critical");
if (critical.length) process.exitCode = 1;
var started struct{ JobID string `json:"job_id"` }
if err := call("POST", "/run", payload, &started); err != nil {
	log.Fatal(err)
}

var job struct {
	Status string          `json:"status"`
	Error  string          `json:"error"`
	Output json.RawMessage `json:"output"`
}
for {
	if err := call("GET", "/jobs/"+started.JobID, nil, &job); err != nil {
		log.Fatal(err)
	}
	if job.Status == "succeeded" || job.Status == "failed" {
		break
	}
	time.Sleep(1500 * time.Millisecond)
}

// job.Output is {"output": "<json string>"} — unwrap, then unmarshal:
type Review struct {
	ReviewName string `json:"review_name"`
	Posture    string `json:"posture"`
	Verdict    string `json:"verdict"`
	ExecSummary string `json:"exec_summary"`
	Assumptions   []string `json:"assumptions"`
	OpenQuestions []string `json:"open_questions"`
	Components []struct {
		Type, Name, Owns, Role string
	} `json:"components"`
	Findings []struct {
		ID, Category, Severity, Likelihood, Priority string
		Component, Problem, Impact, Fix, Snippet     string
	} `json:"findings"`
	CoverageCheck []struct {
		ID, Note  string
		Addressed bool
	} `json:"coverage_check"`
	QuickWins  []string `json:"quick_wins"`
	FocusAreas []struct {
		Area, Why  string
		FindingIDs []string `json:"finding_ids"`
	} `json:"focus_areas"`
	Summary string `json:"summary"`
}
var wrapper struct{ Output string `json:"output"` }
json.Unmarshal(job.Output, &wrapper)
var review Review
json.Unmarshal([]byte(wrapper.Output), &review)

fmt.Printf("%s [%s]: %s\n", review.ReviewName, review.Posture, review.Verdict)
for _, r := range review.Components {
	fmt.Printf("  %s/%s (owns %s): %s\n", r.Type, r.Name, r.Owns, r.Role)
}
for _, f := range review.Findings {
	fmt.Printf("  [%s] %s %s %s: %s\n", f.Priority, f.ID, f.Category, f.Component, f.Problem)
}
for _, a := range review.FocusAreas {
	fmt.Printf("  focus %s %v: %s\n", a.Area, a.FindingIDs, a.Why)
}
os.WriteFile("review.json", []byte(wrapper.Output), 0o644)
String envelope = api("POST", "/run", jsonPayload);
String jobId = /* data.job_id via your JSON library */;

while (true) {
    String job = api("GET", "/jobs/" + jobId, null);
    String status = /* data.status */;
    if (status.equals("succeeded") || status.equals("failed")) break;
    Thread.sleep(1500);
}
// The review is at data.output.output as a JSON string — parse it again, then read
// review_name, posture, verdict, exec_summary, assumptions[], open_questions[],
// components[] (type/name/owns/role),
// findings[] (id/category/severity/likelihood/priority/component/problem/impact/fix/snippet),
// coverage_check[] (id/addressed/note), quick_wins[],
// focus_areas[] (area/why/finding_ids[]) and summary.
// Finally keep the review on disk:
//   Files.writeString(Path.of("review.json"), reviewJson);
started = api("POST", "/run", payload)

job = nil
loop do
  job = api("GET", "/jobs/#{started["job_id"]}")
  break if %w[succeeded failed].include?(job["status"])
  sleep 1.5
end
raise (job["error"] || "run failed") if job["status"] == "failed"

raw = job["output"].is_a?(Hash) ? job["output"].fetch("output", job["output"]) : job["output"]
review = raw.is_a?(String) ? JSON.parse(raw) : raw

puts "#{review["review_name"]} [#{review["posture"]}]: #{review["verdict"]}"
review["components"].each { |r| puts "  #{r["type"]}/#{r["name"]} (owns #{r["owns"]}): #{r["role"]}" }
review["findings"].each do |f|
  puts "  [#{f["priority"]}] #{f["id"]} #{f["category"]} #{f["component"]}"
  puts "      L:#{f["likelihood"]}/S:#{f["severity"]} - #{f["fix"]}"
end
review["quick_wins"].each { |w| puts "  win: #{w}" }
review["focus_areas"].each { |a| puts "  focus #{a["area"]} #{a["finding_ids"].join(", ")}" }
review["coverage_check"].each { |c| puts "  #{c["id"]}: #{c["addressed"] ? "ok" : "SET ASIDE"}" }

File.write("review.json", JSON.pretty_generate(review))
exit 1 if review["findings"].any? { |f| f["priority"] == "critical" }
$started = api("POST", "/run", $payload);

do {
    sleep(2);
    $job = api("GET", "/jobs/" . $started["job_id"]);
} while (!in_array($job["status"], ["succeeded", "failed"]));

if ($job["status"] === "failed") {
    throw new Exception($job["error"] ?? "run failed");
}

$raw = is_array($job["output"]) ? ($job["output"]["output"] ?? $job["output"]) : $job["output"];
$review = is_string($raw) ? json_decode($raw, true) : $raw;

echo "{$review['review_name']} [{$review['posture']}]: {$review['verdict']}\n";
foreach ($review["components"] as $r) {
    echo "  {$r['type']}/{$r['name']} (owns {$r['owns']}): {$r['role']}\n";
}
foreach ($review["findings"] as $f) {
    echo "  [{$f['priority']}] {$f['id']} {$f['category']} {$f['component']}\n";
    echo "      L:{$f['likelihood']}/S:{$f['severity']} - {$f['fix']}\n";
}
foreach ($review["quick_wins"] as $w) {
    echo "  win: $w\n";
}
foreach ($review["focus_areas"] as $a) {
    echo "  focus {$a['area']}: " . implode(", ", $a["finding_ids"]) . "\n";
}
foreach ($review["coverage_check"] as $c) {
    echo "  {$c['id']}: " . ($c["addressed"] ? "ok" : "SET ASIDE") . "\n";
}

file_put_contents("review.json", json_encode($review, JSON_PRETTY_PRINT));
var started = await SkillSafe.ApiAsync(HttpMethod.Post, "/run", payload);
var jobId = started.GetProperty("job_id").GetString();

JsonElement job;
while (true)
{
    job = await SkillSafe.ApiAsync(HttpMethod.Get, $"/jobs/{jobId}");
    var status = job.GetProperty("status").GetString();
    if (status is "succeeded" or "failed") break;
    await Task.Delay(1500);
}

var rawText = job.GetProperty("output").GetProperty("output").GetString();
using var doc = JsonDocument.Parse(rawText!);
var review = doc.RootElement;

Console.WriteLine($"{review.GetProperty("review_name")} " +
                  $"[{review.GetProperty("posture")}]: {review.GetProperty("verdict")}");
foreach (var r in review.GetProperty("components").EnumerateArray())
{
    Console.WriteLine($"  {r.GetProperty("type")}/{r.GetProperty("name")}: {r.GetProperty("role")}");
}
foreach (var f in review.GetProperty("findings").EnumerateArray())
{
    Console.WriteLine($"  [{f.GetProperty("priority")}] {f.GetProperty("id")} " +
                      $"{f.GetProperty("category")} {f.GetProperty("component")} " +
                      $"(L:{f.GetProperty("likelihood")}/S:{f.GetProperty("severity")})");
}
foreach (var a in review.GetProperty("focus_areas").EnumerateArray())
{
    Console.WriteLine($"  focus {a.GetProperty("area")}: {a.GetProperty("why")}");
}

await File.WriteAllTextAsync("review.json", rawText!);

The model is asked for one JSON object and nothing else, but a stray code fence or preamble is always possible. Strip a leading ```json fence, take the text between the first { and the last }, and only then parse — that is what the app does before it falls back to a retry_note reformat run.

The review object — output schema

One JSON object, always the same shape. Every array is present, and the review is grounded in the pasted brief alone: findings cite either something the brief actually says (a stated choice, number or constraint) or something material it leaves out, reported against (not specified in the brief). Proposed components are marked proposed: in their role rather than presented as if the brief mentioned them. Where the brief is silent on something that changes the verdict you get an entry in assumptions and, if it would change the ranking, in open_questions. Expect five to twelve findings on a typical brief — a well-thought-out one may honestly yield two or three, and findings is never empty.

FieldTypeMeaning
review_namestringA short title naming the system, taken from the brief's own naming — e.g. order marketplace — architecture review.
posturestringready-to-build | refine-first | needs-discovery. See the table below.
verdictstringOne sentence justifying the posture and naming the single most important change.
exec_summarystringTwo or three paragraphs, separated by blank lines, on the dominant themes across the set.
assumptionsstring[]Explicit assumptions filling gaps the brief left open. Read these first — a wrong assumption invalidates the findings built on it.
open_questionsstring[]Questions whose answers would change the ranking.
componentsarray{type, name, owns, role} — the component plan the reviewed design needs. type is one of service, datastore, queue, cache, gateway, job, external, client; owns names the data or responsibility that component owns; components the brief does not already have carry a proposed: prefix in role. At most ~15 rows.
findingsarrayThe prioritized findings table — ids AD-001, AD-002, … in sequence, at least one entry. Columns are listed below.
coverage_checkarray{id, addressed, note} — one entry per prescan_facts.flags id you sent, each appearing exactly once. See the semantics below.
quick_winsstring[]One-line changes worth doing immediately, ahead of any planning. May be empty when nothing here is a one-liner.
focus_areasarray{area, why, finding_ids} — what to work through first, one sentence tied to the review, and the finding ids that motivate it. Every id in finding_ids exists in findings.
summarystringClosing paragraph: what to fix first, and what risk remains after that.

The three posture values:

postureWhat it means
ready-to-buildThe design holds up as described: the topology matches the team and the load, data ownership is clear, the consistency and failure stories are stated. Findings still exist, but they are decisions to make next, not blockers. A genuinely sound brief lands here rather than having severity manufactured for it.
refine-firstThe direction is workable but named design decisions should change before more code is written — an overbuilt topology for the team, a missing consistency story on a money flow, a datastore choice the read pattern contradicts.
needs-discoveryThe brief does not yet contain enough system to review — no load, no data shape, no constraints — or it contains a contradiction that must be resolved first. The findings say what to find out, not what to build.

Each entry in findings:

ColumnMeaning
idSequential AD-001, AD-002, … — the stable handle referenced from focus_areas[].finding_ids.
categoryboundaries | api-design | data | scalability | resilience | security | operability | cost | simplicity. Weighted by the concern you sent, but never restricted to it.
severitylow | medium | high — how bad it is when it bites.
likelihoodlow | medium | high — how likely it is to bite.
prioritycritical | high | medium | low — severity by likelihood. critical is reserved for something that loses data, loses money, breaks tenant isolation or makes the system unbuildable by the stated team, so sort on this field and work top-down. This is also the field to gate an automated check on.
componentWhat this finding is about — e.g. orders datastore or checkout flow — always grounded in the brief, or the literal (not specified in the brief) when the finding is about a gap.
problemWhat is wrong or missing, in this brief specifically.
impactWhat happens in production (or during the build) because of it.
fixThe concrete design change or decision to make — not "think about scaling".
snippetA small design artifact you can lift: an API contract sketch, a table or queue definition, a call sequence. Plain text. Empty string when a snippet would add nothing.

coverage_check semantics:

CaseWhat you get
Every flag id you sentEach prescan_facts.flags id appears in coverage_check exactly once. Nothing you flagged is silently dropped, which makes this the field to assert on in an automated check. Ids in prescan_facts.signals are not reconciled here — they ground the component plan and the capacity math instead.
addressed: trueThe flag is covered by the review; note names the finding id that covers it.
addressed: falseThe flag was deliberately set aside; note gives the reason — a check that fired but is not a real gap for this brief (no latency target on a nightly batch job, no team constraints because the context field already gave them).
Nothing sentOmit prescan_facts, or send the two empty arrays, and coverage_check comes back empty. The rest of the review is unaffected.

A small, realistic result for the SnapCrate brief above, trimmed for length:

{
  "review_name": "SnapCrate photo delivery — architecture review",
  "posture": "ready-to-build",
  "verdict": "One API, Postgres and S3 fits the stated load and team; the main change is making
              the zip-export workers a real queue with idempotent, resumable jobs.",
  "exec_summary": "The proposed shape — one Node API, Postgres, S3, background workers — matches
                   40 requests/second and a two-person team well. Nothing here needs a second
                   service.\n\nThe risks are concentrated in the export pipeline and the payment
                   flow: exports are long-running and retry-prone, and monthly card charges need
                   an idempotency story before launch, not after.",
  "assumptions": [
    "Peak 40 rps is mostly gallery reads; writes are a small fraction.",
    "Card charging is delegated to a payment provider — raw card data never touches the API."
  ],
  "open_questions": [
    "How large is a typical gallery (affects zip-export memory and S3 multipart strategy)?",
    "Is there a delivery deadline promise to photographers (affects export queue sizing)?"
  ],
  "components": [
    { "type": "service", "name": "api", "owns": "accounts, galleries, orders",
      "role": "the single Node API from the brief" },
    { "type": "datastore", "name": "postgres", "owns": "all relational state",
      "role": "system of record, as briefed" },
    { "type": "external", "name": "object storage", "owns": "originals and export zips",
      "role": "S3, as briefed" },
    { "type": "queue", "name": "export-queue", "owns": "zip-export job state",
      "role": "proposed: a Postgres-backed job queue so exports survive worker restarts" }
  ],
  "findings": [
    { "id": "AD-001", "category": "resilience",
      "severity": "high", "likelihood": "high", "priority": "high",
      "component": "zip-export workers",
      "problem": "The brief has workers but no job queue: nothing says what happens when an
                  export dies halfway through a 40 GB gallery.",
      "impact": "Failed exports restart from zero or vanish; photographers re-trigger them and
                 double the load exactly when the system is struggling.",
      "fix": "Back the workers with a durable job table (Postgres SKIP LOCKED is enough at this
              scale), make jobs idempotent per gallery-version, and upload via S3 multipart so
              a resume never re-sends finished parts.",
      "snippet": "jobs(id, gallery_id, version, state, attempts, locked_by, locked_at)\nworker loop: SELECT ... FOR UPDATE SKIP LOCKED; multipart upload; mark done" },
    { "id": "AD-002", "category": "data",
      "severity": "high", "likelihood": "medium", "priority": "high",
      "component": "monthly billing",
      "problem": "Pro accounts pay by card monthly, but the brief has no idempotency or retry
                  story for charges.",
      "impact": "A retried charge job double-bills a customer; a missed one silently lapses a
                 subscription.",
      "fix": "Use the payment provider's subscription objects rather than home-grown monthly
              charge jobs, and key any charge call with an idempotency key.",
      "snippet": "" }
  ],
  "coverage_check": [
    { "id": "no-latency", "addressed": false,
      "note": "Set aside: gallery delivery is not latency-sensitive beyond ordinary page loads,
               and exports are explicitly asynchronous." }
  ],
  "quick_wins": [
    "Adopt the provider's native subscriptions — deletes the billing cron entirely."
  ],
  "focus_areas": [
    { "area": "Export pipeline durability",
      "why": "It is the only long-running, failure-prone flow in the system.",
      "finding_ids": ["AD-001"] }
  ],
  "summary": "Build it as briefed, with a durable export queue and provider-native billing. …"
}

This is AI-generated review from brief text, not a production sign-off: it sees only what you sent, never the running system, its metrics or its code. Check assumptions and open_questions before you act on the rankings, sanity-check the capacity math against your own numbers, and keep a human architect in the loop.

Step 5 — Stream the review as it is written

POST /run-stream

/run-stream takes exactly the same body as /run but answers with server-sent events, so you can show progress instead of a spinner — useful here because a full findings table with design artifacts makes for a long reply. This app's own progress panel is this endpoint. Events are separated by a blank line; each has an event: line and a data: line carrying JSON.

EventPayloadMeaning
job{job_id, status}Sent once, when the job is accepted — show "starting".
delta{text}A chunk of the reply, in order. Append it; the accumulated length is your only progress signal (the total is not known in advance). The app advances its step list by watching for the "review_name", "components", "findings", "coverage_check" and "focus_areas" keys as they arrive.
done{job_id, status, charged_credits, output}The final, authoritative result — read the review from output.output rather than trusting concatenated deltas, and the settled price from charged_credits.
error{code, message}Replaces done when the run fails.
# -N disables buffering so events print as they arrive
curl -N -s -X POST "$API/run-stream" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -H "Idempotency-Key: ad-$(date +%s)" \
  -d @input.json

# event: job
# data: {"job_id":"job_...","status":"running"}
#
# event: delta
# data: {"text":"{\"review_name\":\"SnapCrate photo"}
# ...
# event: done
# data: {"job_id":"job_...","status":"succeeded","charged_credits":612,"output":{"output":"{...}"}}
import json, requests

result = None
with requests.post(
    API + "/run-stream",
    headers={"Authorization": f"Bearer {TOKEN}",
             "Idempotency-Key": "ad-001"},
    json=payload,
    stream=True,
) as r:
    r.raise_for_status()
    event = None
    for line in r.iter_lines(decode_unicode=True):
        if not line:
            continue
        if line.startswith("event:"):
            event = line[len("event:"):].strip()
        elif line.startswith("data:"):
            data = json.loads(line[len("data:"):].strip())
            if event == "delta":
                print(".", end="", flush=True)          # live progress
            elif event == "done":
                result = data
            elif event == "error":
                raise RuntimeError(data.get("message", "run failed"))

review = json.loads(result["output"]["output"])          # authoritative
print("charged:", result["charged_credits"], "-", review["review_name"])
print("posture:", review["posture"])
for f in review["findings"]:
    print(f'  [{f["priority"]}] {f["id"]} {f["resource"]}: {f["problem"]}')
with open("review.json", "w", encoding="utf-8") as fh:
    json.dump(review, fh, indent=2)
const res = await fetch(API + "/run-stream", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${TOKEN}`,
    "Content-Type": "application/json",
    "Idempotency-Key": crypto.randomUUID(),
  },
  body: JSON.stringify(payload),
});

const reader = res.body.getReader();
const decoder = new TextDecoder();
let buf = "", done = null;

for (;;) {
  const chunk = await reader.read();
  if (chunk.done) break;
  buf += decoder.decode(chunk.value, { stream: true });
  const frames = buf.split("\n\n");
  buf = frames.pop();
  for (const frame of frames) {
    const name = /^event:\s*(.+)$/m.exec(frame)?.[1];
    const body = /^data:\s*(.+)$/m.exec(frame)?.[1];
    if (!name || !body) continue;
    const data = JSON.parse(body);
    if (name === "delta") process.stdout.write(".");   // live progress
    if (name === "done") done = data;
    if (name === "error") throw new Error(data.message ?? "run failed");
  }
}

const review = JSON.parse(done.output.output);
console.log(`\n${done.charged_credits} credits - ${review.review_name} [${review.posture}]`);
for (const f of review.findings) console.log(`  [${f.priority}] ${f.id} ${f.resource}`);
writeFileSync("review.json", JSON.stringify(review, null, 2));
body, _ := json.Marshal(payload)
req, _ := http.NewRequest("POST", API+"/run-stream", bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Idempotency-Key", "tc-001")

res, err := http.DefaultClient.Do(req)
if err != nil {
	log.Fatal(err)
}
defer res.Body.Close()

var event string
var final map[string]any
sc := bufio.NewScanner(res.Body)
sc.Buffer(make([]byte, 0, 64*1024), 4*1024*1024)
for sc.Scan() {
	line := sc.Text()
	switch {
	case strings.HasPrefix(line, "event:"):
		event = strings.TrimSpace(strings.TrimPrefix(line, "event:"))
	case strings.HasPrefix(line, "data:"):
		var data map[string]any
		json.Unmarshal([]byte(strings.TrimPrefix(line, "data:")), &data)
		switch event {
		case "delta":
			fmt.Print(".") // live progress
		case "done":
			final = data
		case "error":
			log.Fatal(data["message"])
		}
	}
}
// final["output"].(map[string]any)["output"].(string) is the review JSON —
// unmarshal it into the Review struct from step 4, then write it to review.json.
// Java 17+ — read the stream line by line instead of buffering the body.
var req = HttpRequest.newBuilder(URI.create(API + "/run-stream"))
    .header("Authorization", "Bearer " + TOKEN)
    .header("Content-Type", "application/json")
    .header("Idempotency-Key", "tc-001")
    .POST(HttpRequest.BodyPublishers.ofString(jsonPayload))
    .build();

var res = HTTP.send(req, HttpResponse.BodyHandlers.ofLines());
String event = null, done = null;
for (String line : (Iterable<String>) res.body()::iterator) {
    if (line.startsWith("event:")) {
        event = line.substring(6).trim();
    } else if (line.startsWith("data:")) {
        String data = line.substring(5).trim();
        if ("delta".equals(event)) System.out.print(".");   // live progress
        else if ("done".equals(event)) done = data;
        else if ("error".equals(event)) throw new RuntimeException(data);
    }
}
// parse `done`, then parse data.output.output again — it is a JSON string holding
// review_name, posture, verdict, inventory[], findings[], coverage_check[],
// quick_wins[], focus_areas[] and the rest.
require "net/http"
require "json"

uri = URI(API + "/run-stream")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer #{TOKEN}"
req["Content-Type"] = "application/json"
req["Idempotency-Key"] = "kc-001"
req.body = payload.to_json

event = nil
done = nil
Net::HTTP.start(uri.host, uri.port, use_ssl: true) do |http|
  http.request(req) do |res|
    res.read_body do |chunk|
      chunk.each_line do |line|
        line = line.strip
        if line.start_with?("event:")
          event = line.delete_prefix("event:").strip
        elsif line.start_with?("data:")
          data = JSON.parse(line.delete_prefix("data:").strip)
          case event
          when "delta" then print "."           # live progress
          when "done"  then done = data
          when "error" then raise (data["message"] || "run failed")
          end
        end
      end
    end
  end
end

review = JSON.parse(done["output"]["output"])
puts "\n#{done["charged_credits"]} credits - #{review["review_name"]} [#{review["posture"]}]"
review["findings"].each { |f| puts "  [#{f["priority"]}] #{f["id"]} #{f["resource"]}" }
File.write("review.json", JSON.pretty_generate(review))
$event = null;
$done  = null;

$ch = curl_init(API . "/run-stream");
curl_setopt_array($ch, [
    CURLOPT_POST       => true,
    CURLOPT_HTTPHEADER => [
        "Authorization: Bearer $TOKEN",
        "Content-Type: application/json",
        "Idempotency-Key: kc-001",
    ],
    CURLOPT_POSTFIELDS => json_encode($payload),
    CURLOPT_WRITEFUNCTION => function ($ch, $chunk) use (&$event, &$done) {
        foreach (explode("\n", $chunk) as $line) {
            $line = trim($line);
            if (str_starts_with($line, "event:")) {
                $event = trim(substr($line, 6));
            } elseif (str_starts_with($line, "data:")) {
                $data = json_decode(trim(substr($line, 5)), true);
                if ($event === "delta") { echo "."; }        // live progress
                elseif ($event === "done") { $done = $data; }
                elseif ($event === "error") { throw new Exception($data["message"] ?? "run failed"); }
            }
        }
        return strlen($chunk);
    },
]);
curl_exec($ch);
curl_close($ch);

$review = json_decode($done["output"]["output"], true);
echo "\n{$done['charged_credits']} credits - {$review['review_name']} [{$review['posture']}]\n";
foreach ($review["findings"] as $f) {
    echo "  [{$f['priority']}] {$f['id']} {$f['resource']}\n";
}
file_put_contents("review.json", json_encode($review, JSON_PRETTY_PRINT));
var req = new HttpRequestMessage(HttpMethod.Post, Api + "/run-stream") {
    Content = JsonContent.Create(payload),
};
req.Headers.Add("Idempotency-Key", "tc-001");

using var res = await Http.SendAsync(req, HttpCompletionOption.ResponseHeadersRead);
using var reader = new StreamReader(await res.Content.ReadAsStreamAsync());

string? evt = null, done = null;
while (await reader.ReadLineAsync() is { } line)
{
    if (line.StartsWith("event:")) evt = line[6..].Trim();
    else if (line.StartsWith("data:"))
    {
        var data = line[5..].Trim();
        if (evt == "delta") Console.Write(".");            // live progress
        else if (evt == "done") done = data;
        else if (evt == "error") throw new Exception(data);
    }
}

using var final = JsonDocument.Parse(done!);
var text = final.RootElement.GetProperty("output").GetProperty("output").GetString();
using var reviewDoc = JsonDocument.Parse(text!);
var review = reviewDoc.RootElement;
Console.WriteLine($"{review.GetProperty("review_name")} [{review.GetProperty("posture")}]");
foreach (var f in review.GetProperty("findings").EnumerateArray())
    Console.WriteLine($"  [{f.GetProperty("priority")}] {f.GetProperty("id")} {f.GetProperty("resource")}");
await File.WriteAllTextAsync("review.json", text!);

In a browser, the native EventSource only speaks GET, and this endpoint is a POST — read the fetch response body incrementally, as the JavaScript sample above does. On an idempotent replay the server may answer with a plain JSON envelope instead of an event stream; check the Content-Type before you start parsing frames.