On the more general side, it's a bit hard to describe, just like it is hard to describe when someone "Googles bad".
They ask self serving questions, underspecify their requests, omit crucial context that the agent is blatantly not going to have access to, or subtly misdirect the agent. They expect the agent to figure out everything: you'll never catch them write a prompt longer than one or two sentences. They never steer the agent or look at the CoT traces.
My boss being a particularly poor case: he apparently has the habit of arguing with the agent, as if it was a person, as if there was any merit to that. Starts being a dickhead with it, shouts at it, what have you. Was flabbergasted we don't.
On the more practical side, they have zero mental model of the harness they're using (Copilot Chat in VS Code). They're surprised when the cheap-ass Auto model, which is almost always some beyond-demented version of GPT, does stupid things. They have no concept of skills, zero understanding of what an MCP server is, haven't heard of lifecycle hooks, agent memory, the various fs scopes (session, workspace, user). No concept of how to have the agent inspect its own debug logs for higher accuracy action provenance.
This also snowballs. Having to give them a stock config is one thing, but even beyond that, you won't see them experimenting. The MCP you're using doesn't support some action? They'll never interrogate whether the underlying scoped OAuth token or bearer token does support it, and they'll never ask their agent to patch the functionality in. They'll not consider the various user flows it can perform on their behalf. They'll not string them together into end-to-end automated workflows unless you explain it to them this is possible, and even after that, they'll just kind of ignore it. They'll never build tooling, extend the harnessing, etc.
Whether this has more to do with age or just disinterest-induced lackluster adoption, up for opinion.
I think this is less an age thing and more of a combined curiosity and systems understanding and thinking thing.
I've noticed the same effect, but the lines it always seems to fall on are if the person fails one (or heaven forbid both) of these:
1) are you curious about how your tools work and how to get better using them?
2) can you hold the mental map of both what you are solving and how your tools work in your head, and explain how information flows.
There is also a dash of:
3) are you willing to try something, even if it has a bit of a screwup risk, just to see what happens?
You mean why not work myself instead of the agent? That'd be because for me it's been working great, and so it does make sense. In the scenarios it doesn't, I do indeed just fall back to manual work. A lot of those scenarios are obvious too, so not too many wasted runs to speak of either.
I did give up on cheaper models, they required constant babysitting, and in those cases yes, the benefits indeed evaporated. The expensive models have been genuinely working wonders though, and were still able to justify themselves economically plenty, at least by my own measurements.
I think there's also one underappreciated and indirect way agents help with productivity: they counteract the attention span collapse of the past years. By being addictive themselves, they keep you engaged, and being engaged means being productive. Not even asking an agent to check something out feels too rich, and once you've asked, you're already one foot into the flow.
There's also definitely been some honeymoon effect going on for me, where I dived into more work more readily, just to see if the agent can figure things out on its own.
On the more general side, it's a bit hard to describe, just like it is hard to describe when someone "Googles bad".
They ask self serving questions, underspecify their requests, omit crucial context that the agent is blatantly not going to have access to, or subtly misdirect the agent. They expect the agent to figure out everything: you'll never catch them write a prompt longer than one or two sentences. They never steer the agent or look at the CoT traces.
My boss being a particularly poor case: he apparently has the habit of arguing with the agent, as if it was a person, as if there was any merit to that. Starts being a dickhead with it, shouts at it, what have you. Was flabbergasted we don't.
On the more practical side, they have zero mental model of the harness they're using (Copilot Chat in VS Code). They're surprised when the cheap-ass Auto model, which is almost always some beyond-demented version of GPT, does stupid things. They have no concept of skills, zero understanding of what an MCP server is, haven't heard of lifecycle hooks, agent memory, the various fs scopes (session, workspace, user). No concept of how to have the agent inspect its own debug logs for higher accuracy action provenance.
This also snowballs. Having to give them a stock config is one thing, but even beyond that, you won't see them experimenting. The MCP you're using doesn't support some action? They'll never interrogate whether the underlying scoped OAuth token or bearer token does support it, and they'll never ask their agent to patch the functionality in. They'll not consider the various user flows it can perform on their behalf. They'll not string them together into end-to-end automated workflows unless you explain it to them this is possible, and even after that, they'll just kind of ignore it. They'll never build tooling, extend the harnessing, etc.
Whether this has more to do with age or just disinterest-induced lackluster adoption, up for opinion.
I think this is less an age thing and more of a combined curiosity and systems understanding and thinking thing.
I've noticed the same effect, but the lines it always seems to fall on are if the person fails one (or heaven forbid both) of these: 1) are you curious about how your tools work and how to get better using them? 2) can you hold the mental map of both what you are solving and how your tools work in your head, and explain how information flows.
There is also a dash of: 3) are you willing to try something, even if it has a bit of a screwup risk, just to see what happens?
Having done all that (what you’re doing) - it often just ends up wasted effort, with poor quality at the end.
Why not just actually do the thing, instead?
You mean why not work myself instead of the agent? That'd be because for me it's been working great, and so it does make sense. In the scenarios it doesn't, I do indeed just fall back to manual work. A lot of those scenarios are obvious too, so not too many wasted runs to speak of either.
I did give up on cheaper models, they required constant babysitting, and in those cases yes, the benefits indeed evaporated. The expensive models have been genuinely working wonders though, and were still able to justify themselves economically plenty, at least by my own measurements.
I think there's also one underappreciated and indirect way agents help with productivity: they counteract the attention span collapse of the past years. By being addictive themselves, they keep you engaged, and being engaged means being productive. Not even asking an agent to check something out feels too rich, and once you've asked, you're already one foot into the flow.
There's also definitely been some honeymoon effect going on for me, where I dived into more work more readily, just to see if the agent can figure things out on its own.
4 replies →