I will believe agenetic commerce works when it can find best value option for UK rail tickets (which is surprisingly complex in terms of options), or can plan a cross border EU rail trip.
There are a number of dedicated rail travel websites in the UK who generally do OK in rail ticket discovery/purchase (for a fee; fee free from rail line operators but not always best value discovery). And the difference in fare between "dumb" booking and best value is very significant (literally £'00's on some routes).
The most heavily advertised site trainline.com; ($ and also white label as fee-free for some of the line operators without discovery features) is not perfect in best value discovery; and also struggles with European trips. Uber app train booking feature similar to trainline. Others that do better for discovery are trainsplit and trainpal. Seatfrog does last minute fares and upgrades (bit like priceline for flights/hotels)
All websites/apps call back into standard industry systems for ticket issue and reservations, and current/historical service data.
My expectation would be agenetic discovery from first principles consuming currently available open data sets for discovery of timetables and fares; handing off to the most appropriate line operator for fee free fulfilment. Props if they can do multimodal trips using open transit bus data, and coach bus timetables (NX, Flix, Flib, greenline); c.f. traveline.info/moovit
See Jon Worth's blogs about the absolute mess that currently exists for European rail ticketing especially cross border; agentic could help but only so far.
Thanks for the use case Miles - I think the reasoning models would do really well with this - the new OpenAI 'agent' is very powerful at this type of problem. I'd give it a shot, but not being from there I don't know a good challenging use case.
Four test cases; increasing difficulty (if anyone wants to have a go). I can hand-build all these (takes 5-20 mins each for best value or handling time constraints).
London to Edinburgh (and maybe Glasgow). Complexity: Multiple operators, coach alternatives (and air alternatives!). easy!
London to Liverpool
Complexity: multiple operators and likely best value would be split ticket/change of operator at Stafford or Crewe (slower but cheaper). The main operator on West coast (Avanti) has a reputation for pricey tickets. (West Coast also covers Manchester, Preston, Carlisle ends at Glasgow) should be easy, leveraging a hand off to e.g. trainsplit if not done natively (I expect genetic integration is in development)
Much harder:
London to Sheringham (or maybe Holt, Norfolk)
Complexity: may be quicker to change to local bus at Norwich (short walk from station) instead of branch train to Sheringham, especially if final destination is actually Holt (which needs local bus)
London to Sudbury Suffolk
Complexity: split ticket that even trainsplit/trainline does not find (express to Colchester, then backtrack to branch line change at Mark's Tey for final leg to Sudbury).
Native complexities (all trips)
Different flexibility of tickets on offer (plus some occasional line operator specials). Overall around 20 types of ticket available.
Multiple operators on some routes
Discount/concession opt-in cards of various eligibilities (disabled, veterans, senior, youth, regional, families; if you have bought the relevant railcard then you can get 20%-33% off some offpeak)
Credit if you have a season commuter ticket that covers part of the route.
Different ticket delivery types (eticket, rail smart card, collection on departure, post, corporate account).
The industry does have paid for API/datasets for route discovery and valid fare calculations. Brfares website gives free access to available valid fares for review (but not inventory).
I will believe agenetic commerce works when it can find best value option for UK rail tickets (which is surprisingly complex in terms of options), or can plan a cross border EU rail trip.
There are a number of dedicated rail travel websites in the UK who generally do OK in rail ticket discovery/purchase (for a fee; fee free from rail line operators but not always best value discovery). And the difference in fare between "dumb" booking and best value is very significant (literally £'00's on some routes).
The most heavily advertised site trainline.com; ($ and also white label as fee-free for some of the line operators without discovery features) is not perfect in best value discovery; and also struggles with European trips. Uber app train booking feature similar to trainline. Others that do better for discovery are trainsplit and trainpal. Seatfrog does last minute fares and upgrades (bit like priceline for flights/hotels)
All websites/apps call back into standard industry systems for ticket issue and reservations, and current/historical service data.
My expectation would be agenetic discovery from first principles consuming currently available open data sets for discovery of timetables and fares; handing off to the most appropriate line operator for fee free fulfilment. Props if they can do multimodal trips using open transit bus data, and coach bus timetables (NX, Flix, Flib, greenline); c.f. traveline.info/moovit
See Jon Worth's blogs about the absolute mess that currently exists for European rail ticketing especially cross border; agentic could help but only so far.
Thanks for the use case Miles - I think the reasoning models would do really well with this - the new OpenAI 'agent' is very powerful at this type of problem. I'd give it a shot, but not being from there I don't know a good challenging use case.
Four test cases; increasing difficulty (if anyone wants to have a go). I can hand-build all these (takes 5-20 mins each for best value or handling time constraints).
London to Edinburgh (and maybe Glasgow). Complexity: Multiple operators, coach alternatives (and air alternatives!). easy!
London to Liverpool
Complexity: multiple operators and likely best value would be split ticket/change of operator at Stafford or Crewe (slower but cheaper). The main operator on West coast (Avanti) has a reputation for pricey tickets. (West Coast also covers Manchester, Preston, Carlisle ends at Glasgow) should be easy, leveraging a hand off to e.g. trainsplit if not done natively (I expect genetic integration is in development)
Much harder:
London to Sheringham (or maybe Holt, Norfolk)
Complexity: may be quicker to change to local bus at Norwich (short walk from station) instead of branch train to Sheringham, especially if final destination is actually Holt (which needs local bus)
London to Sudbury Suffolk
Complexity: split ticket that even trainsplit/trainline does not find (express to Colchester, then backtrack to branch line change at Mark's Tey for final leg to Sudbury).
Native complexities (all trips)
Different flexibility of tickets on offer (plus some occasional line operator specials). Overall around 20 types of ticket available.
Multiple operators on some routes
Discount/concession opt-in cards of various eligibilities (disabled, veterans, senior, youth, regional, families; if you have bought the relevant railcard then you can get 20%-33% off some offpeak)
Credit if you have a season commuter ticket that covers part of the route.
Different ticket delivery types (eticket, rail smart card, collection on departure, post, corporate account).
The industry does have paid for API/datasets for route discovery and valid fare calculations. Brfares website gives free access to available valid fares for review (but not inventory).