Drive the data-profiling agent from your own code
Everything this app does goes through the SkillSafe App API — plain JSON over HTTPS with optional streaming. Send a CSV or TSV export (header row plus data rows) and get back a data profile with judgement: a verdict on analyzability, the table's grain, quality issues ranked by severity and tied to actual values, the dimensions and metrics worth using, patterns to check and the analyses to run first. Examples in cURL, Python, JavaScript, Go, Java, Ruby, PHP and C#.
Basics
Base URL: https://api.skillsafe.ai/v1/app-api. 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. Runs execute the app's agent (model gpt-terra) and are billed in
SkillSafe credits to the calling token, with a worst-case hold up front and the actual cost
settled when the job finishes.
| Status | Meaning |
|---|---|
401 | Missing or expired token — create a new session. |
402 | Not enough credits — top up at skillsafe.ai/account/billing. |
403 | The token isn't allowed to do this. |
404 | Unknown job or record id. |
5xx | Transient 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. The free quick profiler on the app's page (shape, types, nulls, distincts) is browser-side computation with no endpoint behind it; the API surface is the agent run documented below.
Step 0 — A tiny client
Every step below is one or two HTTP calls, so start with a small helper that adds the auth
header, sends JSON and unwraps the data envelope. The later steps reuse this
helper.
export API="https://api.skillsafe.ai/v1/app-api"
export SKILLSAFE_TOKEN="YOUR_TOKEN" # see step 1
# every call looks like:
# curl -s "$API/…" -H "Authorization: Bearer $SKILLSAFE_TOKEN" [-d '{json}']
# jq is used below to pull fields out of the {"data": …} envelope
import json, os, requests
API = "https://api.skillsafe.ai/v1/app-api"
TOKEN = os.environ["SKILLSAFE_TOKEN"] # see step 1
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 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 $payload["data"];
}
// .NET 8+
using System.Net.Http.Json;
using System.Text.Json;
static class SkillSafe
{
const string Api = "https://api.skillsafe.ai/v1/app-api";
static readonly HttpClient Http = new();
static SkillSafe() =>
Http.DefaultRequestHeaders.Authorization =
new("Bearer", Environment.GetEnvironmentVariable("SKILLSAFE_TOKEN")); // see step 1
public static async Task<JsonElement> ApiAsync(HttpMethod method, string path, object? body = null)
{
var req = new HttpRequestMessage(method, Api + path);
if (body != null) req.Content = JsonContent.Create(body);
var res = await Http.SendAsync(req);
var json = await res.Content.ReadFromJsonAsync<JsonElement>();
if (!res.IsSuccessStatusCode)
throw new Exception(json.GetProperty("error").GetProperty("message").GetString());
return json.GetProperty("data");
}
}
Step 1 — Get a token
For scripted use, the simplest reliable path is your personal token: open the
token page, sign in, and hit
"Copy shell export" — it puts export SKILLSAFE_TOKEN="…" on your
clipboard, which every example below reads. Treat the token like a password — it can
spend your credits. For fully headless scripts, POST /guest (below) mints a
guest token with no browser involved; guests can always call /me and
/estimate, but whether a guest can afford an actual run depends on the app's
daily sponsorship budget, so don't build on it.
curl -s -X POST "$API/guest" \
-H "Content-Type: application/json" \
-d '{"slug":"data-scout"}' | jq -r '.data.token'
token = api("POST", "/guest", {"slug": "data-scout"})["token"]
const { token } = await api("POST", "/guest", { slug: "data-scout" });
var guest struct{ Token string `json:"token"` }
err := call("POST", "/guest", map[string]string{"slug": "data-scout"}, &guest)
String envelope = api("POST", "/guest", """
{"slug":"data-scout"}""");
// token is at data.token in the returned JSON
token = api("POST", "/guest", { slug: "data-scout" })["token"]
$token = api("POST", "/guest", ["slug" => "data-scout"])["token"];
var guest = await SkillSafe.ApiAsync(HttpMethod.Post, "/guest",
new { slug = "data-scout" });
var token = guest.GetProperty("token").GetString();
Step 2 — Check who you are and your balance
Returns subject_type ("user" or "guest"),
subject_id and your credits balance. Check this before an
expensive run.
curl -s "$API/me" -H "Authorization: Bearer $SKILLSAFE_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
Send the same input you would send to a run; the response's hold_credits is
the worst-case cost and min_credits the floor. Nothing is charged and no job
is created. The response also reports the resolved model and whether
sponsorship is active. The app itself refuses to start a run when
hold_credits exceeds the caller's balance — a sensible check for your
scripts too.
curl -s -X POST "$API/estimate" \
-H "Authorization: Bearer $SKILLSAFE_TOKEN" -H "Content-Type: application/json" \
-d '{"data":"order_id,region,amount\n1001,EMEA,49.90\n…","notes":"one row per order"}' | jq '.data'
est = api("POST", "/estimate", {"data": data, "notes": notes})
print("worst case:", est["hold_credits"], "credits on", est["model"])
const est = await api("POST", "/estimate", { data, notes });
console.log("worst case:", est.hold_credits, "credits on", est.model);
var est struct {
HoldCredits int64 `json:"hold_credits"`
Model string `json:"model"`
}
err := call("POST", "/estimate", map[string]string{
"data": data, "notes": notes,
}, &est)
String envelope = api("POST", "/estimate", """
{"data": %s, "notes": %s}
""".formatted(toJsonString(data), toJsonString(notes)));
// worst-case cost is at data.hold_credits
est = api("POST", "/estimate", { data: data, notes: notes })
puts "worst case: #{est["hold_credits"]} credits on #{est["model"]}"
$est = api("POST", "/estimate", [
"data" => $data,
"notes" => $notes,
]);
echo "worst case: {$est['hold_credits']} credits on {$est['model']}\n";
var est = await SkillSafe.ApiAsync(HttpMethod.Post, "/estimate", new {
data, notes });
Console.WriteLine($"worst case: {est.GetProperty("hold_credits")} credits");
Step 4 — Run it and wait
/run places a credit hold and returns a job_id; poll
/jobs/{job_id} every 1–2 seconds until status is
succeeded or failed. Always send an Idempotency-Key
header so a network retry can't start a second, double-charged run. The agent replies with
plain text in a fixed shape (see "The report's shape" below), delivered at
output.output.
| Input field | Type | Notes |
|---|---|---|
data | string, required | The dataset as delimiter-separated text (comma, tab, semicolon or pipe), header row first. Keep whole rows — never cut a record mid-line. If you sample a big table, keep the header plus leading and trailing rows and add a marker row such as [... 9000 of 10000 rows omitted - data truncated ...]; the web app does exactly that at ~60k chars. |
notes | string, optional | Context: what the table is supposed to be, its intended grain, what you want to use it for, columns you already distrust. |
focus | string, optional | One of Auto detect (default), Quality audit, Dimensions and metrics, Trends over time, Segmentation, Keys and joins. |
profile | string, optional | A mechanical profile of the table (row/column counts, per-column types, nulls, distincts, ranges). The web app generates one in the browser; scripts can simply omit it — the agent reads the data itself either way. |
retry_note | string, optional | Feedback about a previous malformed reply; the agent obeys it exactly. |
$model | string, optional | Per-run model override (allowlisted models only). |
# input.json: {"data":"order_id,region,amount\n1001,EMEA,49.90\n…","focus":"Quality audit"}
JOB_ID=$(curl -s -X POST "$API/run" \
-H "Authorization: Bearer $SKILLSAFE_TOKEN" -H "Content-Type: application/json" \
-H "Idempotency-Key: scout-$(date +%s)" \
-d @input.json | jq -r '.data.job_id')
while :; do
JOB=$(curl -s "$API/jobs/$JOB_ID" -H "Authorization: Bearer $SKILLSAFE_TOKEN")
STATUS=$(echo "$JOB" | jq -r '.data.status')
[ "$STATUS" = "succeeded" ] || [ "$STATUS" = "failed" ] && break
sleep 2
done
# the report is plain text at data.output.output
echo "$JOB" | jq -r '.data.output.output'
import time
job_id = api("POST", "/run", {
"data": data,
"notes": notes,
"focus": "Quality audit",
}, **{"Idempotency-Key": "scout-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"]
report = raw["output"] if isinstance(raw, dict) else raw # plain text, not JSON
print(report.splitlines()[0]) # e.g. "VERDICT: Usable with caveats"
const { job_id } = await api("POST", "/run", {
data,
notes,
focus: "Quality audit",
}, { "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 report = job.output?.output ?? job.output; // plain text, not JSON
console.log(report.split("\n")[0]); // e.g. "VERDICT: Usable with caveats"
var started struct{ JobID string `json:"job_id"` }
err := call("POST", "/run", map[string]string{
"data": data, "notes": notes, "focus": "Quality audit",
}, &started)
if err != nil {
log.Fatal(err)
}
var job struct {
Status string `json:"status"`
Error string `json:"error"`
Output struct {
Output string `json:"output"`
} `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)
}
report := job.Output.Output // plain text, not JSON
fmt.Println(strings.SplitN(report, "\n", 2)[0])
String envelope = api("POST", "/run", """
{"data": %s, "notes": %s, "focus": "Quality audit"}
""".formatted(toJsonString(data), toJsonString(notes)));
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 report is the plain-text STRING at data.output.output — no second
// JSON parse needed, just read the string field
started = api("POST", "/run", { data: data, notes: notes,
focus: "Quality audit" })
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"]
report = raw.is_a?(Hash) ? raw["output"] : raw # plain text, not JSON
puts report.lines.first # e.g. "VERDICT: Usable with caveats"
$started = api("POST", "/run", [
"data" => $data,
"notes" => $notes,
"focus" => "Quality audit",
]);
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 = $job["output"];
$report = is_array($raw) ? ($raw["output"] ?? "") : $raw; // plain text, not JSON
echo strtok($report, "\n") . "\n"; // e.g. "VERDICT: Usable with caveats"
var started = await SkillSafe.ApiAsync(HttpMethod.Post, "/run", new {
data, notes, focus = "Quality audit" });
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 report = job.GetProperty("output").GetProperty("output").GetString()!;
Console.WriteLine(report.Split('\n')[0]); // e.g. "VERDICT: Usable with caveats"
The report's shape
The reply is plain text (markdown bullets, no code fence around the whole thing) in exactly this frame — stable enough to parse with a few string splits:
VERDICT: Ready for analysis | Usable with caveats | Needs cleaning first | Not analyzable
GRAIN: <one row per what, in a few words - or Unknown>
CONFIDENCE: <integer 0-100>
SUMMARY: <2-4 sentences, ends at the first blank line>
## Dataset reading
- <plain bullets: rows and columns seen, the grain and how it was inferred, key candidates>
## Quality issues
- <issue> | <High|Medium|Low> | <evidence: the column and the offending value> | <the concrete fix>
## Dimensions and metrics
- <plain bullets: what to slice by, which numerics are real metrics vs ids-in-disguise>
## Patterns to check
- <plain bullets: arithmetic that should reconcile, hierarchies, correlations worth testing>
## Recommended analyses
- <plain bullets: 3-5 analyses, each naming the metric, the slice and the payoff>
## Open questions
- <plain bullets; an empty section is the single bullet "- None.">
- All six
##headings always appear, in that order. - Every
## Quality issuesbullet has exactly four|-separated fields; split on" | ". Issues are ordered High first. Ready for analysisguarantees noHighissue;Needs cleaning firstguarantees at least one;Not analyzableguarantees recommended analyses are- None.and at least one open question.- Column names and quoted values arrive wrapped in backticks (
`region`,`999999`).
If a reply ever fails to match the frame, retry once with the same input plus a
retry_note field describing the problem — the agent is instructed to
obey it. That's exactly what the app itself does (and the retry is a second billed run).
Step 5 — The same run, streamed
Identical input to /run, but the response is
text/event-stream, so you can show the report as it generates (the app's live
output panel is this endpoint). Events:
| Event | Data |
|---|---|
job | {job_id} — the run was accepted. |
delta | {text} — the next chunk of agent output. |
done / pending | Final payload: {job_id, status, charged_credits, output}. Authoritative — deltas can drop the tail, so always read the final report from here. |
error | {code, message, job_id}. |
curl -sN -X POST "$API/run-stream" \
-H "Authorization: Bearer $SKILLSAFE_TOKEN" -H "Content-Type: application/json" \
-d @input.json
# event: job data: {"job_id":"job_…"}
# event: delta data: {"text":"VERDICT: Usable with caveats\nGRAIN:"}
# …
# event: done data: {"job_id":"…","status":"succeeded","charged_credits":412,
# "output":{"output":"…the full report text…"}}
res = requests.post(API + "/run-stream", json=payload, stream=True,
headers={"Authorization": f"Bearer {TOKEN}"})
event, done = None, None
for line in res.iter_lines(decode_unicode=True):
if line.startswith("event:"):
event = line[6:].strip()
elif line.startswith("data:"):
data = json.loads(line[5:])
if event == "delta":
print(data.get("text", ""), end="", flush=True)
elif event in ("done", "pending"):
done = data
elif event == "error":
raise RuntimeError(data.get("message"))
report = done["output"]["output"] # authoritative full text
const res = await fetch(API + "/run-stream", {
method: "POST",
headers: { Authorization: `Bearer ${TOKEN}`, "Content-Type": "application/json" },
body: JSON.stringify(payload),
});
const reader = res.body.getReader();
const decoder = new TextDecoder();
let buf = "", event = "message", done, out = "";
for (;;) {
const chunk = await reader.read();
if (chunk.done) break;
buf += decoder.decode(chunk.value, { stream: true });
let i;
while ((i = buf.indexOf("\n")) >= 0) {
const line = buf.slice(0, i); buf = buf.slice(i + 1);
if (line.startsWith("event:")) event = line.slice(6).trim();
else if (line.startsWith("data:")) {
const data = JSON.parse(line.slice(5));
if (event === "delta") out += data.text ?? "";
else if (event === "done" || event === "pending") done = data;
else if (event === "error") throw new Error(data.message);
}
}
}
const report = done.output.output; // authoritative full text
req, _ := http.NewRequest("POST", API+"/run-stream", bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("Content-Type", "application/json")
res, err := http.DefaultClient.Do(req)
if err != nil {
log.Fatal(err)
}
defer res.Body.Close()
sc := bufio.NewScanner(res.Body)
sc.Buffer(make([]byte, 0, 1<<20), 1<<20)
event, done := "", []byte(nil)
for sc.Scan() {
line := sc.Text()
if strings.HasPrefix(line, "event:") {
event = strings.TrimSpace(line[6:])
} else if strings.HasPrefix(line, "data:") {
data := strings.TrimSpace(line[5:])
if event == "delta" {
// unmarshal {"text": …} and append
} else if event == "done" || event == "pending" {
done = []byte(data)
}
}
}
// unmarshal done → .output.output (the full plain-text report)
var req = HttpRequest.newBuilder(URI.create(API + "/run-stream"))
.header("Authorization", "Bearer " + TOKEN)
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(payloadJson))
.build();
var lines = HTTP.send(req, HttpResponse.BodyHandlers.ofLines()).body();
final String[] event = {""};
StringBuilder doneData = new StringBuilder();
lines.forEach(line -> {
if (line.startsWith("event:")) event[0] = line.substring(6).trim();
else if (line.startsWith("data:")) {
if (event[0].equals("delta")) { /* parse {"text"} and append */ }
else if (event[0].equals("done")) doneData.append(line.substring(5).trim());
}
});
// parse doneData → output.output (the full plain-text report)
uri = URI(API + "/run-stream")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer #{TOKEN}"
req["Content-Type"] = "application/json"
req.body = payload.to_json
event, done, buf = nil, nil, ""
Net::HTTP.start(uri.host, uri.port, use_ssl: true) do |http|
http.request(req) do |res|
res.read_body do |chunk|
buf << chunk
while (i = buf.index("\n"))
line = buf.slice!(0..i).chomp
if line.start_with?("event:") then event = line[6..].strip
elsif line.start_with?("data:")
data = JSON.parse(line[5..])
print data["text"] if event == "delta"
done = data if %w[done pending].include?(event)
end
end
end
end
end
report = done["output"]["output"] # authoritative full text
$event = ""; $done = null; $buf = "";
$ch = curl_init(API . "/run-stream");
curl_setopt_array($ch, [
CURLOPT_POST => true,
CURLOPT_HTTPHEADER => ["Authorization: Bearer $TOKEN", "Content-Type: application/json"],
CURLOPT_POSTFIELDS => json_encode($payload),
CURLOPT_WRITEFUNCTION => function ($ch, $chunk) use (&$event, &$done, &$buf) {
$buf .= $chunk;
while (($i = strpos($buf, "\n")) !== false) {
$line = rtrim(substr($buf, 0, $i)); $buf = substr($buf, $i + 1);
if (str_starts_with($line, "event:")) $event = trim(substr($line, 6));
elseif (str_starts_with($line, "data:")) {
$data = json_decode(substr($line, 5), true);
if ($event === "delta") echo $data["text"] ?? "";
if ($event === "done" || $event === "pending") $done = $data;
}
}
return strlen($chunk);
},
]);
curl_exec($ch);
curl_close($ch);
$report = $done["output"]["output"]; // authoritative full text
var req = new HttpRequestMessage(HttpMethod.Post, Api + "/run-stream")
{ Content = JsonContent.Create(payload) };
var res = await Http.SendAsync(req, HttpCompletionOption.ResponseHeadersRead);
using var reader = new StreamReader(await res.Content.ReadAsStreamAsync());
string? line; string ev = ""; JsonElement doneEl = default;
while ((line = await reader.ReadLineAsync()) != null)
{
if (line.StartsWith("event:")) ev = line[6..].Trim();
else if (line.StartsWith("data:"))
{
var data = JsonDocument.Parse(line[5..]).RootElement.Clone();
if (ev == "delta") Console.Write(
data.TryGetProperty("text", out var t) ? t.GetString() : "");
else if (ev is "done" or "pending") doneEl = data;
}
}
var report = doneEl.GetProperty("output").GetProperty("output").GetString()!;
The grounding contract is instructed on every run: every finding names its column and quotes the offending value from your data, uniqueness and completeness claims are hedged to the rows actually seen, and what the sample does not settle lands under ## Open questions instead of being invented. If you sample a large table, keep whole rows and say so with a marker row - the report will then scope its counts to the sample. Note that this is a contract the prompt imposes on the model, not a server-side guarantee: the web app additionally checks every quoted column and value back against the submitted data and marks what it cannot find, and an API client that cares about grounding should do the same on the fields it consumes.