Read the numbers off dashboards that have no API

Superlinked gives your agent one API to turn dashboards, pipeline views and admin tables into typed JSON it can check.

Get started

applications_deployed 1,094

health

Healthy: 753
Progressing: 23
Suspended: 0
Degraded: 28
Missing: 263
Unknown: 27

sync

Synced: 699
OutOfSync: 359
Unknown: 36

753 + 23 + 0 + 28 + 263 + 27 = 1,094

699 + 359 + 36 = 1,094

Health and sync each add up to the 1,094 deployed

Your agent gets 328 of 335 values exactly as the screen shows them

View evidence

Apache Superset

Slack Dashboard

Weekly Threads: 12 · +9.1% WoW
Weekly Messages: 217 · -7.3% WoW
New Members per Month: 124 · -26.6% MoM
Number of Members: nothing returned screen shows 2.51k
America/Los_Angeles: 410 screen shows 416
Asia/Kolkata: 354
Europe/Brussels: 79
America/Sao_Paulo: 49

Kubernetes Dashboard

Node detail

Node: kubernetes-dashboard-control-plane
CPU requests: 9.4% · 0.75 cores
Memory requests: 2.5% · 150 MiB
Pods: 6.4% · 7 pods
DiskPressure: False · KubeletHasNoDiskPressure
Ready: True · KubeletReady
kindnet-fmj8d: Running · 5 restarts

GitLab

CI/CD pipelines list

All tab count: 1,000+
Pipeline 1234145533: Warning · 02:24:47
Its branch: ruby_3_2 screen shows ruby3_2
Pipeline 1234128996: Failed · 00:35:06
Its merge request: !147325 screen shows 147325
Its commit: 0bd7ba8a

GitLab (Grafana dashboard)

GitLab CI pipelines health dashboard

Grafana dashboard of GitLab CI pipelines with a table of failed runs

Pipelines: 219
Failed pipelines: 18
Average pipeline duration: 2 hours
Failed run 1: v18.2.1 · 5 hours screen shows v19.2.1 · 5 hours
Failed run 6: v16.6.3 · 1 hour
Failed run 12: v13.5.0-rc1 · 43 minutes

Across all 12 recorded screens, 328 of 335 values matched the screen and 7 did not. The 4 here include every screen that missed anything.

Ask for one metric and get schema-valid JSON back

View on GitHub

from pathlib import Path
import json
from sie_sdk import SIEClient
client = SIEClient(
    api_key="API keysk-sie-…",
    base_url="https://api.superlinked.com",
)
schema = json.loads("""
{
  "type": "object",
  "properties": {
    "metric": {
      "type": "string"
    },
    "value": {
      "type": "string"
    },
    "change": {
      "type": "string"
    },
    "period": {
      "type": "string"
    }
  },
  "required": [
    "metric",
    "value",
    "change",
    "period"
  ],
  "additionalProperties": false
}
""")
image = {"data": Path(imagegitlab-dora-metrics.pngbrowse).read_bytes(), "format": "png"}
result = client.generate(
    "modelQwen/Qwen3.8-27B-FP8",
    "queryExtract Project-Alpha's deployment frequency: the metric, value, change, and reporting period.",
    max_new_tokens=512,
    images=[image],
    grammar={"json_schema": schema, "label": "dashboard_metric", "strict": True},
)
print(json.loads(result["text"]))

import { readFile } from 'node:fs/promises';
import { SIEClient } from '@superlinked/sie-sdk';

const client = new SIEClient('https://api.superlinked.com', {
  apiKey: 'sk-sie-…',
});

const schema = {
  "type": "object",
  "properties": {
    "metric": {
      "type": "string"
    },
    "value": {
      "type": "string"
    },
    "change": {
      "type": "string"
    },
    "period": {
      "type": "string"
    }
  },
  "required": [
    "metric",
    "value",
    "change",
    "period"
  ],
  "additionalProperties": false
};
const image = await readFile("gitlab-dora-metrics.png");
const result = await client.generate(
  'Qwen/Qwen3.8-27B-FP8',
  "Extract Project-Alpha's deployment frequency: the metric, value, change, and reporting period.",
  {
    maxNewTokens: 512,
    images: [image],
    grammar: {
      json_schema: schema,
      label: "dashboard_metric",
      strict: true,
    },
  },
);
console.log(JSON.parse(result.text));

image_bytes=$(base64 < 'gitlab-dora-metrics.png' | tr -d '\n')
curl https://api.superlinked.com/v1/generate/Qwen__Qwen3.8-27B-FP8 \
  -H "Authorization: Bearer sk-sie-…" \
  -H "Content-Type: application/json" \
  -d "{\"prompt\":\"Extract Project-Alpha's deployment frequency: the metric, value, change, and reporting period.\",\"max_new_tokens\":512,\"images\":[{\"data\":\"$image_bytes\",\"format\":\"png\"}],\"grammar\":{\"json_schema\":{\"type\":\"object\",\"properties\":{\"metric\":{\"type\":\"string\"},\"value\":{\"type\":\"string\"},\"change\":{\"type\":\"string\"},\"period\":{\"type\":\"string\"}},\"required\":[\"metric\",\"value\",\"change\",\"period\"],\"additionalProperties\":false},\"label\":\"dashboard_metric\",\"strict\":true}}"

Build the "Screenshot mining" capability into my app using the Superlinked Inference Engine (SIE).

Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: Qwen/Qwen3.8-27B-FP8 (SIE primitive: /generate). Keep the model id configurable.

Task
- Input: an uploaded app screenshot plus the fields to extract.
- Behaviour: describe the screenshot, then return its primary metric as schema-valid JSON
- Call the selected SIE primitive once per request and map the response into your domain type.

Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.

Run

Output

Source gitlab-dora-metrics.png — source · gitlab-dora-metrics.png

metricDeployment frequency

value25.4/d

change-6.7%

periodLast full calendar month

PRICE

$ / 1k images $ / 1M input tokens $ / 1M output tokens ↓

$0.309 SIE Grounding DINO

AWS Rekognition $1

Google Vision Labels $1.5

SIE Qwen3.6 27B $0.72

OpenAI GPT-5.4 mini $0.75

Anthropic Claude Haiku 4.5 $1

$0.72 SIE Qwen3.6 27B

OpenAI GPT-5.4 mini $4.5

Anthropic Claude Haiku 4.5 $5

QUALITY

Field accuracy ↑

SIE Qwen3.6 27B 0.86

0.84

0.83

SIE Grounding DINO 0.74

0.72

0.71

LATENCY

p50 s ↓

0.8s SIE Grounding DINO

0.9s

SIE Qwen3.6 27B 1.5s

1.6s

1.8s

Deploy your way

Managed Cloud

Full compute toolkit for your agents with zero ops.

No idle GPUs, pay for what you use
Fits your stack: SDK, API, CLI, MCP
Zero lock-in, self-host the same stack
SOC 2 Type 2, US or EU data residency

$50 Example credit balance

1.3B tokens embedded

120k pages parsed

27M tokens generated (1:1 in:out)

Get started

no credit card required

Self-host with K8s

Easy & scalable deployment in your own cloud.

Terraform to your cloud in minutes
Apache-2.0, same engine as Cloud
Scales to zero, no bill between jobs
Per-tenant pools, no noisy neighbors

Agent prompt

Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our GCP project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our Azure AKS cluster via helm install. Requirements: superlinked.com/docs/deployment

Deploy guide

Run locally

Run the same models on your own machine.

Runs on NVIDIA GPU or Apple Silicon
One command, no Docker or cluster
All 100+ Cloud models, fully offline
Same SDK and IDs, no code changes

pip install "sie-server[local]" && sie-server servepip install "sie-server[local]" && sie-server serve --device cuda

Quickstart

Your agent gets 328 of 335 values exactly as the screen shows them

Ask for one metric and get schema-valid JSON back

Screenshot extraction quality and latency

Deploy your way