Four capabilities, one platform,
cost optimised: visual intelligence
at broadcast scale.
A media library containing tens of thousands of video and image assets. A hard cost constraint. A four-capability visual search platform was built that standard tooling would have charged 10× more to run.
| Sector | Ad Tech / Media Intelligence |
| Service | Platform Design & Engineering |
| Scale | Tens of thousands of video & image assets |
| Cost outcome | 10× reduction |
| Processing time | Days to hours — distributed and scalable |
Key Highlights
The media library contained tens of thousands of video and image assets per client — and it grows constantly. A single campaign generates multiple versions of the same creative: different durations, crops for different placements, regional re-edits, localised audio. Finding, grouping, and retrieving related assets was slow, manual, and increasingly unworkable at scale.
The product requirement was clear: build a visual intelligence layer that lets clients search and discover assets intelligently — not just by filename or metadata, but by what the content actually is and looks like. Four capabilities were needed: frame-level retrieval, semantic video search, structural similarity across versions, and the same suite for images.
The engineering constraint was equally clear: the system had to be cheap to run. Media query loads are spiky — bursts of activity around campaign launches, then silence. Standard vector database solutions would have cost $350–$460/month in always-on compute alone, regardless of actual usage. That wasn't acceptable. The architecture had to cost almost nothing at idle and scale on demand.
The cost constraint wasn't
a limitation — it was the brief.
Design around the cost constraint from day one.
Rather than reaching for standard vector database tooling and optimising later, we designed the cost architecture before writing a line of application code. The goal: near-zero idle cost, with the ability to scale to thousands of queries on demand. That shaped every infrastructure decision that followed.
Benchmark the approach against real numbers.
Before committing, we validated the retrieval approach against real data and real costs. Storing ~70GB of vectors in AWS S3 vector buckets runs roughly $1–2/month, with 1,000 queries/month at $0.50–$2 — against OpenSearch Serverless ($350–$460/month) or Databricks Mosaic AI ($200–$900/month). The benchmark confirmed the order-of-magnitude saving was real, not theoretical, and set the architecture.
Build the storage and compute layers for scale.
With the approach proven, we built the production system: AWS S3 vector buckets with an optimised storage layout for retrieval without always-on compute, paired with distributed serverless inference that scales to zero at idle and to thousands of concurrent queries on demand.
Live in client dashboards, scaling with demand.
The four visual intelligence capabilities run live in ExtremeReach's client dashboards. Media workloads are spiky — campaign launches drive sudden bursts followed by silence — and the serverless design absorbs that pattern, scaling within seconds and costing nothing when idle, with no reserved capacity or manual oversight.
What changed.
| Before Ferrous Labs | After Ferrous Labs |
|---|---|
| Manual asset search — slow, error-prone, and unscalable | Four distinct visual intelligence capabilities — live in client dashboards |
| No way to find related versions of the same creative | Frame search, semantic search, structural similarity, and image equivalents — one platform |
| No semantic or visual retrieval across the library | Order-of-magnitude lower running cost than standard approaches |
| Days to process 100K+ videos | Zero cost at idle — scales to thousands of queries on demand. Days of processing → hours. |
The cost constraint wasn't a limitation — it was the brief. Standard tooling would have solved the problem and cost 10× more. Designing around the constraint forced better decisions at every layer of the stack.Ferrous Labs engineering note
Stack
Talk to a co-founder.
If you're delivering CV, vector retrieval, or cost-engineered ML at scale — we've delivered this before. Book a discovery call.