Runflow
Introducing Sentinel

Your AI pipeline shipsbad images.Sentinel stops that.

Automated quality evaluation built into every AI image and video workflow. Detect, score, and filter AI-generated images before they reach your users.

Built into every Solution API. Add it as a node in any Runflow workflow.

The Problem

You're generating at scale.Nobody's checking the output.

When AI pipelines run at volume, defects multiply. No team reviews 10,000 images a day. Without automated evaluation, broken images reach your users.

Invisible

You can't see what's broken

Face distortions, wrong backgrounds, skin tone issues, logo placement errors. At API scale, defects are invisible until a user complains.

Manual & slow

Human review doesn't scale

Manual QA works for dozens of images. Not for thousands. The moment you scale, quality control becomes the bottleneck, or disappears entirely.

Costly

Bad outputs cost real money

Every image that fails QA after delivery is a refund, a complaint, or a churn event. Defect cost doesn't show in COGS. It shows in your NRR.

How it works

Three modes.You choose how quality works.

Guard blocks bad images before delivery. Score evaluates asynchronously with zero latency. Pipeline Insights tracks quality trends over time. Use one, or all three.

01

Guard: block bad images

Sentinel evaluates every image before delivery. Bad outputs are discarded and re-generated automatically with the specific issues flagged. Your users only see quality results.

02

Score: zero-latency evaluation

03

Pipeline Insights: track quality over time

sentinel · evaluation result
guard mode · headshot_v2 · output_38291.jpg
Face fidelity
96
Likeness match
93
Background clean
88
Skin tone natural
84
Artifact detection
97
PASS · Score 94.2
Image cleared for delivery
img_3f2d · 58Face distortionRETRYING
Evaluation layers

Built for your use case,not the generic one.

Sentinel evaluates at three levels. From universal quality checks to custom business rules you define. Every layer is configurable.

Layer 01

Generic Quality

Universal checks that apply to any AI image generation. Runs automatically on every pipeline, zero configuration.

Prompt-to-image alignment
Artifact detection
Composition scoring
Sharpness & exposure
Most used
Layer 02

Use Case Specific

Pre-tuned criteria for Runflow's production pipelines. Headshots, fashion, on-model. Each with its own quality standard.

Face fidelity & likeness
Garment & logo accuracy
Background consistency
Expression & skin tone
Layer 03

Your Custom Rules

Define what matters to your business. Sentinel checks your edge cases on every single run, at any volume.

Custom quality schema
Business-specific criteria
Threshold configuration
Team-shareable templates
Case Study

How BetterPic Deploys Sentinel to DeliverQuality Headshots at Scale.

BetterPic generates AI headshots at 4x volume, then lets Sentinel score every output in real time. Only the highest-scoring images are delivered to users. The rest are suppressed automatically.

BetterPic.io

Generate 4x more candidates.Deliver only the best ones.

Users receive a tightly curated set of top headshots matching expression, likeness, background, and skin tone criteria. No human reviewer involved. Zero bad images shipped.

100K+ jobs per month. Zero manual QA.
📥
User uploads photos
Input: 8 reference photos
Runflow generates at 4x volume
e.g. 240 candidate images per user
🎯
Sentinel scores every image
Face, expression, background, skin tone
Top 60 delivered to user
Highest-scoring only, zero manual review
Developer-first

One call to add quality control to any pipeline.

Sentinel is built into every Solution API and can be added as a node in any Runflow workflow. Configure it for your use case. Never touch it again.

Instant integration

Already included in Solution APIs. For custom workflows, add the Sentinel node to your pipeline. One step, no rebuild.

🎯

Configurable thresholds

Set pass/fail scores per dimension. Sentinel adapts to your quality bar. Strict for luxury, lenient for drafts.

🔁

Actionable feedback

Sentinel tells you exactly what failed and why. Use the feedback to trigger a new generation with the specific issues flagged, or handle it in your own pipeline.

POST /v1/pipelines/headshot
{
  "use_case_name": "headshot generation",
  "use_case_description": "generating headshots for professional usage like LinkedIn",
  "evaluation_instructions": "skin need to look natural, and the generated face should look like the reference one, for example realistic skin texture and accurate facial similarity",
  "input_images": [
    {
      "image_url": "https://example.com/face_image.jpg",
      "image_label": "face_image"
    },
    {
      "image_url": "https://example.com/background_image.jpg",
      "image_label": "background_image"
    }
  ],
  "input_attributes": {
    "gender": "female",
    "hair_color": "gray"
  },
  "output_image": "https://example.com/output_image.jpg"
}
Get Started

Stop shipping bad images.Start with Sentinel.

Quality control is not optional at scale. It's what separates an AI product from a reliable AI product.

Solution APIs

Sentinel included

Using our Solution APIs? Sentinel is already built in. Quality evaluation on every image, zero setup.

  • Use case-specific evaluation presets
  • Score reporting per image
  • Actionable feedback per image
Get started
Custom Workflows

Add Sentinel as a node

Building your own workflow on Runflow? Add the Sentinel node for quality evaluation configured to your exact use case.

  • Custom evaluation schema
  • Your criteria, your thresholds
  • Shareable team templates
  • Dedicated onboarding call
Get started

See quality scoring in action

Try our free fashion product scorer. Upload a garment image and get an instant AI readiness score.

Score My Product