Man, I just got into a killer flow with it, minimal guardrails, having it doing lots of independent work all the way to task completion, and my company dropped our prem token allowance to 60%. I was hitting 2k+%. So I just got hamstringed. Corporate pulled a complete 180 on us.
Would love to hear if other are in this situation.
I would describe the flow-state challenge as: Needing a way to make the agentic coding process continuous rather than intermittent. It used to be that I could let a semi-visual map of the code build in my head, then work based on that map (continuously) for a few days. Now I have to basically load a whole new map into my brain for one task, write a detailed prompt, hit enter, then dump all that "context" to go work on a prompt for some other part of the code. I have been experimenting with tools and processes that let me reduce the amount of context switching between each task so I can keep more of my mind at a higher "architectural" level, which feels more continuous.
A helpful middle ground I’ve found is to build out the architecture you want, but stub out the tedious function implementations you don’t want to do yourself.
And by stub out I mean write the function signature yourself, including parameters it’ll accept and return types. Add a comment if necessary about what it will do.
This is actually a great idea. I build a whole thing into my agent management platform that basically treats tickets (kinda like Jira, but not) as a store of shared context, then lets me launch prompts into the terminal with all the ticket history as context (all the file changes and prompt history, etc). I find that just having that context improves consistency quite a bit without pulling in a whole chat.
I think using skills like grill_me is supposed to make the experience a lot more user-involved and fun, rather than just being an accept_permissions driven process and the feeling like an observer.
Share your POV about the flow state. I lost that too, but found myself a few days ago sitting in front of Claude prompting until 5am in the morning. The flow is different, less satisfactory for sure than writing code yourself.
Main reason I am sticking to using AI is convenience, speed and the perception that the job market expects you to.
I don’t think the problem is AI, the problem is the way we use AI and what we ask it to do. Flow comes from having a clear mental model, making decisions. If the LLMs model is making most of the decisions, I’m left trying to reconstruct someone else’s thinking after the fact.
I think that’s the key. Don’t hand over the thinking, use it as part of the loop. The more I use it, the better I get at knowing what to ask for, what to ignore, and when to take back control.
think simple. you are human, ai is a car. you can walk but if you ride a car you can arrive fast. you don't need to forget how to walk while you riding a car.
another side i think for myself; if you are developer you are somewhat right. if you are maker, no problem you can use ai as much as possible. bcz i know i can write completely if the ai is turned off.
If you ride a car, you can arrive fast. Maybe. If you don't wreck the car. Or get hit by a bus. Or have your tire go flat. And your engine doesn't blow. And you don't get pulled over by the cops. And there is no construction on the roads. No accidents. No bridges washed out.
So yeah, your analogy works. Better than you intended.
Man, I just got into a killer flow with it, minimal guardrails, having it doing lots of independent work all the way to task completion, and my company dropped our prem token allowance to 60%. I was hitting 2k+%. So I just got hamstringed. Corporate pulled a complete 180 on us.
Would love to hear if other are in this situation.
I would describe the flow-state challenge as: Needing a way to make the agentic coding process continuous rather than intermittent. It used to be that I could let a semi-visual map of the code build in my head, then work based on that map (continuously) for a few days. Now I have to basically load a whole new map into my brain for one task, write a detailed prompt, hit enter, then dump all that "context" to go work on a prompt for some other part of the code. I have been experimenting with tools and processes that let me reduce the amount of context switching between each task so I can keep more of my mind at a higher "architectural" level, which feels more continuous.
Curious what others are doing to solve this.
A helpful middle ground I’ve found is to build out the architecture you want, but stub out the tedious function implementations you don’t want to do yourself.
And by stub out I mean write the function signature yourself, including parameters it’ll accept and return types. Add a comment if necessary about what it will do.
You should probably adjust how you work and find a workflow that feels ok to you instead of abandoning it completely.
AI works amazingly well for me in fields I don't know much about. In fields where I actually have experience, it's hit or miss.
Could this mean it doesn’t actually work amazingly well in fields you don’t know much about, just that you can’t tell when it’s a miss?
lol
Same here. I built a small tool to keep them straight: it just lists past sessions per project and one click reopens the right one.
This is actually a great idea. I build a whole thing into my agent management platform that basically treats tickets (kinda like Jira, but not) as a store of shared context, then lets me launch prompts into the terminal with all the ticket history as context (all the file changes and prompt history, etc). I find that just having that context improves consistency quite a bit without pulling in a whole chat.
I think using skills like grill_me is supposed to make the experience a lot more user-involved and fun, rather than just being an accept_permissions driven process and the feeling like an observer.
https://github.com/mattpocock/skills/blob/main/skills/produc...
Share your POV about the flow state. I lost that too, but found myself a few days ago sitting in front of Claude prompting until 5am in the morning. The flow is different, less satisfactory for sure than writing code yourself.
Main reason I am sticking to using AI is convenience, speed and the perception that the job market expects you to.
I experience LLM a lot recently, but I am feeling, if you do not have design in mind, it will messy everything.
The frustration makes sense. Its easy to lose your rhythm when the tool starts doing more thinking than you.
AI works for me magically..better than magic...
I don’t think the problem is AI, the problem is the way we use AI and what we ask it to do. Flow comes from having a clear mental model, making decisions. If the LLMs model is making most of the decisions, I’m left trying to reconstruct someone else’s thinking after the fact.
I think that’s the key. Don’t hand over the thinking, use it as part of the loop. The more I use it, the better I get at knowing what to ask for, what to ignore, and when to take back control.
think simple. you are human, ai is a car. you can walk but if you ride a car you can arrive fast. you don't need to forget how to walk while you riding a car.
another side i think for myself; if you are developer you are somewhat right. if you are maker, no problem you can use ai as much as possible. bcz i know i can write completely if the ai is turned off.
If you ride a car, you can arrive fast. Maybe. If you don't wreck the car. Or get hit by a bus. Or have your tire go flat. And your engine doesn't blow. And you don't get pulled over by the cops. And there is no construction on the roads. No accidents. No bridges washed out.
So yeah, your analogy works. Better than you intended.
but why, can you give more details
Okay, thank you.