Case study 006
Talk to film. Twenty sources, one honest score.
BetaIn beta, launching October 2026.
- Sources
- 20+review sources aggregated into one blended score
- Corpus
- 20ktitles resolved, indexed and scored, built from scratch
- Delivery
- 8 mobuild after three years of groundwork
01Context
Three years of groundwork and a broken discovery experience
The Fi1m team had spent three years on the problem: review scores that disagree, aggregators that flatten them, and recommendation engines that optimise for whatever a platform wants you to stream. Discovery had become a chore.
The frontier report tracked two things arriving at once: models good enough to read and reconcile criticism at scale, and MCP as the way agents would consume services. Fi1m was the concept that used both.
02What we built
A corpus from nothing, a blended score, a critic of its own, and a conversation
There was no dataset to license, so the first thing built was the corpus: twenty thousand titles, each resolved to one canonical record across remakes, re-releases, regional titles and the twenty-plus review sources that all spell them differently.
On top of it, reviews aggregated and weighted into a blended score that shows its working, with Fi1m's own reviews alongside, so the platform has a voice rather than just an average. Then a discovery interface you talk to, which keeps lists of what you've seen and what you'd like to see, and an MCP server exposing the same catalogue to agents, so “find us something for tonight” works from whatever assistant you already use.
03How
Training and indexing came first. The product sat on top.
Most of the eight months went into the corpus, because everything else depends on it. Ingestion pipelines pulled metadata, cast, crew and criticism from more than twenty sources, and entity resolution collapsed them into one record per title, with every claim carrying its source.
Models were then trained on that material rather than the open web: readers fine-tuned to extract a verdict and its reasons from each critic's house style, calibration so a three-star review and a 7/10 land on the same scale, and a review model that writes in Fi1m's own voice. The catalogue is indexed for meaning as well as metadata, so “something like Heat but quieter” resolves. The blending stays deterministic and explainable, and the MCP server and the web interface share one API, so agents and people get identical answers. It all runs on Edge, with training and indexing on Edge Compute.
04What changed
From four tabs to one question
Twenty thousand films indexed and scored in beta, built from an empty database at the start of an eight-month build. For Fi1m, three years of thinking became a product with two front doors, one for people and one for their agents, and a corpus underneath that is now an asset in its own right.
Before
Four tabs, and trusting none of them.
Now
20kfilms indexedOne sentence, and a list that finally remembers what you meant to watch.
05What's next
Where to watch, and who to watch with
On the roadmap after launch:
- 01Availability across streaming services, folded into the answer
- 02Shared lists and group decisions for households that can never agree
- 03Television
Handed to Edge Expert Services to run. Labs stays on as R&D partner.
Engagement
Built for people and their agents.
Fi1m is the first Labs product designed from day one to be used over MCP as much as through a browser. It's also the largest corpus Labs has built from nothing. That's the pattern we expect most consumer products to follow, and why the frontier report keeps coming back to it.
Fi1m 006
Beta- Client
- Fi1m, film.one
- Sector
- Media & entertainment. Discovery platform and MCP.
- Status
- Beta, launching October 2026.
- Build
- Three years of groundwork, eight-month build.
- Labs' role
- Report
- Concept and spec
- Build
- Expert Services
- Now run by
- Edge Expert Services
- Stack
- 20+ source ingestion and entity resolutionFine-tuned review readersScore calibrationSemantic catalogue indexExplainable blended scoringMCP serverEdge ComputeEdge StorageEdge CDN
- Related
- film.one
More work
All seven buildsGive your product a second front door
Your customers' agents are about to start using your service on their behalf. If you'd like that to work well, it's a Labs conversation.
Or write to labs@edge.network