LLM demos that crumble on the way to prod?
The demo-to-prod gap is a major problem; I'm sharing my playbook for closing it
⚙️ TDD for prompts
🧠 Debugging with thinking tokens
↔️ Knowing when to code vs. prompt
Stop chasing magic. Start engineering:
samsaccone.com/posts/shippi...
The demo-to-prod gap is a major problem; I'm sharing my playbook for closing it
⚙️ TDD for prompts
🧠 Debugging with thinking tokens
↔️ Knowing when to code vs. prompt
Stop chasing magic. Start engineering:
samsaccone.com/posts/shippi...
From Prototype to Product: An Engineer's Playbook for Shipping LLMs
samsaccone.com
August 1, 2025 at 11:08 PM
LLM demos that crumble on the way to prod?
The demo-to-prod gap is a major problem; I'm sharing my playbook for closing it
⚙️ TDD for prompts
🧠 Debugging with thinking tokens
↔️ Knowing when to code vs. prompt
Stop chasing magic. Start engineering:
samsaccone.com/posts/shippi...
The demo-to-prod gap is a major problem; I'm sharing my playbook for closing it
⚙️ TDD for prompts
🧠 Debugging with thinking tokens
↔️ Knowing when to code vs. prompt
Stop chasing magic. Start engineering:
samsaccone.com/posts/shippi...
LLM backed coding helpers suffer from the paradigm of speaking with a voice of an expert without the expertise of one.
Pattern matching on well written statements alone - which is a reasonable first level triage - now is a failure mode when you bring AI to code-review.
Pattern matching on well written statements alone - which is a reasonable first level triage - now is a failure mode when you bring AI to code-review.
December 6, 2024 at 12:46 AM
LLM backed coding helpers suffer from the paradigm of speaking with a voice of an expert without the expertise of one.
Pattern matching on well written statements alone - which is a reasonable first level triage - now is a failure mode when you bring AI to code-review.
Pattern matching on well written statements alone - which is a reasonable first level triage - now is a failure mode when you bring AI to code-review.
“Leaked system prompts” continue to matter less and less - as proven by more and more companies open sourcing their “secret recipe” github.com/stackblitz/b...
What matters is UX, interaction polish, and end-to-end value prop.
What matters is UX, interaction polish, and end-to-end value prop.
November 23, 2024 at 9:03 PM
“Leaked system prompts” continue to matter less and less - as proven by more and more companies open sourcing their “secret recipe” github.com/stackblitz/b...
What matters is UX, interaction polish, and end-to-end value prop.
What matters is UX, interaction polish, and end-to-end value prop.
After rolling out 6 large LLM projects for developer productivity across 10k+ engineers it's clear that while the hype of "just throw an LLM at it" continues... The reality under the hood is a pile of software and a pinch of LLM.
November 9, 2024 at 5:31 PM
After rolling out 6 large LLM projects for developer productivity across 10k+ engineers it's clear that while the hype of "just throw an LLM at it" continues... The reality under the hood is a pile of software and a pinch of LLM.