Add blogpost about lessons learned from ai-workflows #1065
Conversation
|
Build succeeded. ✔️ pre-commit SUCCESS in 1m 20s |
|
|
||
| ## From code to service | ||
|
|
||
| Once you move from building a prototype to building a production system, you also need to think about the infrastructure and other components, not just agents and code around them. Here are just a few examples of what we plumbed that keeps AI agents running reliably: |
There was a problem hiding this comment.
gemini suggested these:
Integrated: This is a strong choice as it suggests a more deliberate and seamless connection between different systems.
Wove together: This offers a more metaphorical and descriptive alternative, implying a complex and intertwined network.
Incorporated: This is a good, formal option that means to include something as part of a whole.
Architected: This emphasizes the intentional design and planning that went into connecting the systems.
Implemented: This is a very common and direct word for putting a plan into effect, and it fits well.
I picked architected
|
|
||
| ## Takeaways | ||
|
|
||
| After roughly 3.5 months of development, our system is currently running for a selected set of components - and it's being heavily developed. But by following these principles, we've seen a huge difference in reliability and maintainability. More importantly, we're now much clearer about what's actually possible to do with AI and what isn't. |
There was a problem hiding this comment.
More importantly, we're now much clearer about what's actually possible to do with AI and what isn't.
I know what you're trying to say, but it doesn't feel right and at the same time I don't have a better suggestion for this :/
I'll think about it a bit…
lbarcziova
force-pushed
the
lessons-learned-ai
branch
from
c13ca10 to
2ace003
Compare
|
Build succeeded. ✔️ pre-commit SUCCESS in 1m 20s |
TomasTomecek
left a comment
TomasTomecek
left a comment
There was a problem hiding this comment.
I'll leave grammar improvements to Mato.
I can see you improved a lot of sections that are now much more readable and expertly written, LGTM.
|
|
||
| After roughly 3.5 months of development, our system is currently running for a selected set of components - and it's being heavily developed. But by following these principles, we've seen a huge difference in reliability and maintainability. More importantly, we're now much clearer about what's actually possible to do with AI and what isn't. | ||
|
|
||
| Ask me again in 3 months, and I'll probably have another set of valuable lessons learned. But that's the nature of this rapidly evolving field. |
There was a problem hiding this comment.
so you actually left this part here, nice!
|
Build succeeded. ✔️ pre-commit SUCCESS in 1m 24s |
|
Build succeeded. ✔️ pre-commit SUCCESS in 1m 20s |
Co-authored-by: Matej Focko <[email protected]> Signed-off-by: Tomas Tomecek <[email protected]>
TomasTomecek
force-pushed
the
lessons-learned-ai
branch
from
5a97221 to
3f678bd
Compare
|
Build succeeded. ✔️ pre-commit SUCCESS in 1m 18s |
|
My plan is to merge this tomorrow and publish so we can have the blog post up rather sooner than later. |
3 participants
Fixes packit/jotnar#200