PoolDeck

The Context is the Message

PoolDeck structures and connects visual data for teams and AI.

Book a Demo

Context Dies in Transit

5 billion images are created every day (.64% AI generated). Only .01% are visible to AI agents. Context like brand guidelines, approvals, and rights clearance remains invisible to AI that only sees pixels.

PoolDeck is the missing context layer for visual data.

PoolDeck tackles the entire visual workflow preceding DAMs: concepts, reviews, handoffs, and launches.

Approvals

Who approved the asset, when, for which use, and under what constraints.

Brand guidelines

How the asset maps to brand rules, visual identity, campaign standards, and permitted usage.

Provenance

Where the asset came from, who created it, source files, AI-generation status, edits, and authenticity signals.

Relationships

How the asset connects to campaigns, products, references, variants, source materials, teams, and downstream outputs.

Version history

What changed, when it changed, why it changed, and which version is approved for use.

Performance data

How the asset performed across channels, including engagement, conversion, retention, or sales impact.

How it works

Context in. Useful assets out.

PoolDeck takes assets from wherever they are, automates context, and delivers useful assets wherever you need them.

01

Ingest your visual data

Connect folders, campaigns, references, and working files from the tools your team already uses.

02

SPLaSH attaches context that travels

Our SPLaSH context engine reads each asset through your required context parameters, e.g. brand, audience, campaign, rights, and performance, then writes a versioned record of what it means.

03

Retrieve structured data

Teams search by meaning in the web app. Agents and pipelines retrieve the same context through the headless API, with a CLI and MCP 2 on the way.

04

Built to make your AI pipelines usable

Structured visual context gives emerging AI systems the meaning they need to understand, retrieve, and reuse media assets.

Proof

Agent ready. Compliance friendly.

Agent asks: Is this image compliant with both Heinz and Heineken brand requirements?

In testing, PoolDeck context lifted an agent's brand-compliance accuracy from 33% to 98%, at 100x lower cost on repeat calls.

Image only (VLM call)
Street photo sent to the model as pixels only
Accuracy: 33%

Did not correctly identify compliance. The model missed the required responsible drinking message and gave the wrong verdict.

Image + PoolDeck
The same photo paired with its PoolDeck JSON context record
Accuracy: 98%

Correctly identified compliance. The model found the image visually on-brand, but not paid-media compliant until responsible drinking copy is added.

PoolDeck JSON only
The PoolDeck JSON context record on its own, no image
Accuracy: 98%

Correctly identified compliance without reprocessing the image. With routing, the model only needs the relevant compliance fields.

Agent answers: Visually on-brand, but not paid-media compliant until responsible drinking copy is added.