[j45]

Big systems like Salesforce started as small things that more deeply learned about and more deeply understood unmet demand and customer needs, and then got to packaging it in a way to create something that grows.

Coding agents can help more with tasks and not quite big entire massive platforms on their own. Humans may be able to scale much further and bigger with their skills.

[dhorthy]

i like that angle...I also hear a lot that 'coding agents are great for prototypes, but we usually need a team to bring it to production'

[j45]

First congrats on the launch - I like it.

My feedback: what’s there looks inviting. Email interaction is handy, other ways would be too.

If there was a low code way to arrange the humanlayer primitives for folks at the edge of using it, I think human tasks could meet something like this even broader. Happy to chat offline.

Onto your comment: The coding for coding agents is still kinda prototype. It feels like some folks quietly have setup a very productive workflow themselves for quite sometime.

Still, there no doubt you could ship production code in some cases - except ai needs to handle all the things development explicitly and implicitly checks before doing so.

Getting to build some things that became more than few orders of magnitude larger than planned, one can learn a lot from the deep experiences of others… and I’m not sure where that is in AI. Speaking to someone with experience and insight can provide some profound insight, clarification and simplification.

Still, an axiom for me remains: clever architecture still tends to beat clever coding.

The best code often is the code that’s not written and not maintained and hopefully the functionality can be achieved through interacting with the architecture.

This approach is only one way, but it can take both domain knowledge and data knowledge, to put in enough a domain and data driven design relative to how well the developer may know the required and anticipated needs.

The high end of software development is many leagues beyond even what I just described. There’s a lot of talk about 10x engineers, I’d say there can be developers who definitely can be 10x as effective or reach 10x more of the solution, than average.

If a lot of the code AI is modelled on is based on the body of code in repos, most on a wide scale may be average to above average at most, perfectly serviceable and iteratively updated.

Sometimes we see those super elegant designs of fewer tables and code that does near everything, because it’s developments 5th or 6th version creating major overhauls. It could be refactored, or if the schema is not brittle, maybe a rewrite in full or part of the exact same team is present to do it.

Today’s AI could help shed a light in some of those directions, relative to the human using it. This again says in the hands of an expert developer AI can do a ton more for them, but the line to automation might be something else.

There is agentic ai and human in the loop to still figure itself out, as well as how to improve the existing processes. 2025 looks to be interesting.

[dhorthy]

I think a lot about the low code side and how we can make that work...at the end of the day that looks like a feature/integration into other platforms and that means a lot of matching opinions/interfaces.

I think K8s ecosystem did this well but it required big cross-enterprise working groups that produced things like CSI, SMI, OCI, and before that could happen, there was like 5+ years of storming and forming that had to happen before the dust settled enough for enteprises to step forward and embrace k8s/containers as the new compute paradigm

maybe i'm overthinking things.

onto the coding things -

> clever architecture still tends to beat clever coding

love this

> best code often is the code that’s not written and not maintained

it's too bad not-writing-code isn't as satisfying as deleting code

> it’s developments 5th or 6th version creating major overhauls

yeah the best agent orchestration architecture I'm aware is on interation 4 going on 5. I told him to open source it but he said "its .NET so if I open source it, nobody will care" XD

> There is agentic ai and human in the loop to still figure itself out, as well as how to improve the existing processes. 2025 looks to be interesting.

i'm stoked for it

[j45]

Maybe piggybacking on existing platforms is a way to go. You already have an API, maybe tying in a few major orchestration platforms like Zapier, n8n, make.com, and maybe even IFTTT, etc in one fell swoop would be a nice start to make it easier to tie in. Since you're into python, something like node-red might not be bad either.

There are lots of other process managers that could fit well with agents as well, python and not that could be reasonable bolt-ons or extensions.

I'd be very happy to check out the best agent orchestration architecture you're referring to, email is in my profile if easier :). 1

In terms of open sourcing, I don't think anyone would have an issue with .NET, I wouldn't. Many businesses have exposure to Microsoft 365 already and using Azure, kind of a massive built in audience.