Route
How do we compose many models and providers behind one reliable interface?
What we will measure
Definitions are published before results. No measurement for this programme has been published yet.
- Routing regret
- Gap between the chosen route and the best feasible route after the fact
- Cost per request
- Monetary cost of a routed request, including overhead
- Latency overhead
- Added latency versus a direct provider call
- Policy-violation rate
- Share of requests that breach privacy, jurisdiction or other routing rules
- Time to onboard a provider
- Elapsed time to add a provider behind the same interface
Connected projects
| Project | Type | Programme | HOPn role | Status |
|---|---|---|---|---|
| AI-Pass Infrastructure layer for the other programmes. | Research project | Route | Developer | In progress |
| TEAOA Trust model for orchestration. | Research project | Route | Developer | In progress |
| Invoice automation Shared testbed for the Route, Ground and Assure programmes. | Research project | Route, Ground, Assure | Developer | In progress |
Planned work
Planned work for the next twelve months, counted from the start of the programme.
| months | Programme | Summary | Status |
|---|---|---|---|
| 0–2 | Route | AI-Pass submission | In progress |
| 6–12 | Route | Integrated pipeline paper | Planned |