Ask HN: How are you automating your coding work?

#1

Post by manthangupta109 » Wed, Jan 21, 2026, 7:13 PM UTC

With the increase of vibe coding I am interested in knowing some creative ways people are automating their coding work.

Re: Ask HN: How are you automating your coding work?

#2

Post by jackfranklyn » Wed, Jan 21, 2026, 7:22 PM UTC

[flagged]

Re: Ask HN: How are you automating your coding work?

#3

Post by mandeepj » Wed, Jan 21, 2026, 7:31 PM UTC

jackfranklyn wrote: post #2

[flagged]

> The moment you start rubber-stamping those, you end up with a codebase you don't understand.

Yeah, treat it like an intern or junior engineer who needs constant feedback and reviews.

Re: Ask HN: How are you automating your coding work?

#4

Post by hmokiguess » Wed, Jan 21, 2026, 7:40 PM UTC

Each project gets its own share of supervision depending on how critical human intervention is needed.

I have some complex large and strict compliance projects that the AI is a pair programmer but I make most of the decisions, and I have smaller projects that, despite great impact on the bottom line, can be entirely done unsupervised due to the low risk factor of "mistakes" and the easiness of correcting them after the fact they are caught by the AI as well.

Re: Ask HN: How are you automating your coding work?

#5

Post by denysvitali » Wed, Jan 21, 2026, 7:44 PM UTC

With Happy (https://blog.denv.it/posts/im-happy-engineer-now/)

Re: Ask HN: How are you automating your coding work?

#6

Post by lucabraccani » Wed, Jan 21, 2026, 7:46 PM UTC

jackfranklyn wrote: post #2

[flagged]

Which Claude Code model do you usually use? Any noticeable differences?

Re: Ask HN: How are you automating your coding work?

#7

Post by catigula » Wed, Jan 21, 2026, 7:47 PM UTC

jackfranklyn wrote: post #2

[flagged]

Having AI generate tests is technical debt unless what you're doing is extremely trivial and well-trodden in which case you can basically gen all of the code and not care at all.

Tests are where the moat still exists because prior to creating tests the outcomes are unverifiable.

Re: Ask HN: How are you automating your coding work?

#8

Post by langarus » Wed, Jan 21, 2026, 7:48 PM UTC

lucabraccani wrote: post #6

jackfranklyn wrote: post #2

[flagged]

Which Claude Code model do you usually use? Any noticeable differences?

I've began using Opus and I felt it was a class above all the rest. Used cursor and teste different models, but opus somehow was always much much better. Bought the max for 100$, totally worth it.

Re: Ask HN: How are you automating your coding work?

#9

Post by pbohun » Wed, Jan 21, 2026, 7:50 PM UTC

I'm not. I'm learning a little bit each day, making my brain better and myself more productive as I go.

Re: Ask HN: How are you automating your coding work?

#10

Post by bravura » Wed, Jan 21, 2026, 7:51 PM UTC

We use beads for everything. We label them as "human-spec" needed if they are not ready to implement. We label them as "qa-needed" if they cannot be verified through automatic tests.

I wrote beads-skills for Claude that I'll release soon to enforce this process.

2026 will be the year of agent orchestration for those of us who are frustrated having 10 different agents to check on constantly.

gastown is cool but too opinionated.

I'm excited about this promising new project: https://github.com/jzila/canopy

We're writing an internal tool to help with planning, which most people don't think is a problem but I think is a serious problem. Most plans are either too long and/or you end up repeating yourself.