The alpha, twice a week
That was 4 min.
Get the best new moments in your inbox every Wednesday and Saturday. It's free.
Check your inbox
We sent a link to your address. Click it to finish signing up. Not there in a minute? Look in spam.
or
The Pragmatic Engineer · 4 min · Oct 7, 2026
Hedge AI vendor risk by being multi-model and using plain code
Sam Newman
Gergely OroszHost · Host, The Pragmatic Engineer
Spent four years at Uber heading mobile, web and backend teams; shipped part of its payments system.
About this segment
Sam points to the gap between AI revenue needs and the size of the software market. He recommends multi-vendor, multi-model setups and swapping agent steps for deterministic code.
From “Building resilient systems with Sam Newman”, Oct 7, 2026. Watch the full episode
Thanks. We'll look at and fix what's off.
“They need to be generating $2.6 trillion in revenue to justify their capex expenditure by 2030. The entire software market is $1.4 trillion.”
Takeaways
- Providers need about $2.6 trillion in revenue by 2030, in a $1.4 trillion software market.
- Use several vendors and models, and keep fallbacks for outages.
- Replace parts of an agent workflow with deterministic code where you can.
In this episode
Full episode- 1:21:33Fail open or fail closed depends on the business context4:39
- 1:08:19Make retries safe with idempotency keys, not just fingerprints4:48
- 1:26:21Robustness is only one of four parts of resilience1:58
- 1:01:59Decide how resilient you need to be before building resilience6:01
- 35:16Spec or code as source of truth depends on tacit knowledge5:17
- 1:44:55Run an AI software factory on one module, not the whole system4:47
- 1:16:04Thundering herds have different causes, so the fixes differ5:12
1:32:49Hedge AI vendor risk by being multi-model and using plain code3:39
Transcript
Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.
- 1:33:02
right well i mean or is it no it's not i mean firstly there's some stuff there's some ai stuff in there that can help um i i detail quite a few examples where around sort of correlation analysis and you know help support around posting there's some instant.io doing some amazing stuff in this area this is saying we can use tools to do a lot bits but really there's more fundamental kind of things here and the first thing is the macro and the micro the micro level there's some useful stuff we can do here um and i talk about that but the macro level is that that none of it stacks up financially right so if you're like taking a longer view about resilience if i'm building my products based on a market sector that is fundamentally flawed these companies don't have a viable path to sustainability when you say which companies are we talking about open ai and
- 1:33:49
anthropic and the hypervisors right conservative analysis by the economists are showing that they They need to be generating $2.6 trillion in revenue to justify their capex expenditure by 2030. The entire software market is $1.4 trillion. So macro level, I don't know how that gets sorted. I'm not smart enough. I also don't have any shares of those companies. But, you know, that's a separate conversation.
- 1:34:11
I can't solve that. What I can start thinking about is, okay, if that's what I'm operating in, how do I deal with that? I can't deal with all that. What I can do if I'm taking a view to resiliency is being very careful about how I use AI. For example, you know, if I'm thinking taking a longer view, being more flexible about model choices, that's going to help me because I've got the opportunity to use open-weight models from different vendors.
- 1:34:33
I mean, it's even just basic things like open AI and Anthropic are pretty terrible when it comes to availability of their core models from their services, which is why everyone I know also will use like, they'll use Google or Amazon or Microsoft as either their primary place they go to those models or their fallbacks, they have better uptimes and things. so there's all that stuff we've got to deal with at that level there's also the conversation about non-determinism and charity pulled me up on this a bit and i said the thing is that you know we're going from deterministic software to non-determinism you know that's a challenge for us we don't know how things work and then she said to me our distributed systems were never deterministic and now they're really not deterministic and of course she's right because when we take our
- 1:35:12
distributed system and we add the people in beyond the rabbits right and the fires and the people we always had a degree of non-determinism we're just amping that up a bit so I think that's a continuation so for me I think it's a confusing landscape it's not good or bad I think at the micro level there's some really great things that we can do when you say micro level that's the tactical things that we can do, right?
- 1:35:34
I think really what I mean by that is I'm taking the macroeconomic policy situation out of it I'm saying that as a developer there's things that we can make use of there's some good stuff in there that we can make use of but I also think there's some hedging we need to do longer term if you're building AI into your product there's some simple hedging things so being multi-vendor being multi-model for example breaking rather than having a single agent breaking that down into more workflow models therefore you can take bits of your workflow and realize actually this can now be swapped out for a bit of deterministic code that i write that could run more efficiently i think these are sensible things that you can do we can't fix this we can at least deal with our world and i think there's some sensible things that we can do in that space what are the things that we know that