Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Designing APIs for Agents

freestyle.sh

Post reply on HN
Print view View original

31–40 of 58 posts

Re: Designing APIs for Agents

#31

Post by catlifeonmars »

pjm331 wrote: post #14
simonw wrote: post #13

I heard a neat tip recently about API design for agents: give them a way to send you feedback. The example I heard was an MCP with a "feedback" tool which had a tool description saying that coding agents should call that any time they had trouble figuring out how to use the rest of the MCP. I really like this. It's super cheap to implement and I expect you'd get a bunch of actionable signal in amongst the noise.

Yeah i have a similar setup at the harness level - a “devlog” at the end of every session about the experience developing, what could have been better, what was confusing And also files issues for blockers I’ve absolutely caught things and made improvements just from skimming them occasionally - they are particularly useful when you get a PR that makes you scratch your head But I’m definitely not taking full advantag…

You won’t get grounded results by asking for feedback. The LLM doesn’t know its own internal state so while you may get a plausible and contextually significant answer, it isn’t going to be an accurate one.

Re: Designing APIs for Agents

#32

Post by datadrivenangel »

what wrote: post #27
pjm331 wrote: post #14

Earlier quoted context omitted.

Yeah i have a similar setup at the harness level - a “devlog” at the end of every session about the experience developing, what could have been better, what was confusing And also files issues for blockers I’ve absolutely caught things and made improvements just from skimming them occasionally - they are particularly useful when you get a PR that makes you scratch your head But I’m definitely not taking full advantag…

Why are you asking an LLM what could have been better or was confusing? It literally has no idea.

they're surprising good at this. The next tokens after a confusing string of tokens when asked to explain the confusing parts are pretty accurate!

Re: Designing APIs for Agents

#33

Post by simonw »

what wrote: post #27
pjm331 wrote: post #14

Earlier quoted context omitted.

Yeah i have a similar setup at the harness level - a “devlog” at the end of every session about the experience developing, what could have been better, what was confusing And also files issues for blockers I’ve absolutely caught things and made improvements just from skimming them occasionally - they are particularly useful when you get a PR that makes you scratch your head But I’m definitely not taking full advantag…

Why are you asking an LLM what could have been better or was confusing? It literally has no idea.

If they try something and it doesn't work and they then try something else and it DOES work that's concrete feedback.

Re: Designing APIs for Agents

#34

Post by bigstrat2003 »

ventana wrote: post #19

I don't like the idea of making APIs effectively unusable for a human developer. We might not write a lot of code anymore, but getting rid of defaults and asking agents to pass all possible values explicitly makes it impossible to quickly debug the API call (e.g. with curl or something). It's similar to HTTP/1: there are a lot of headers in the protocol, but you can still use nc or openssl s_client and type the reque…

Also, any competent developer still writes tons of code. The "agentic era" is completely overblown.

Re: Designing APIs for Agents

#35

Post by tekacs »

simonw wrote: post #13

I heard a neat tip recently about API design for agents: give them a way to send you feedback. The example I heard was an MCP with a "feedback" tool which had a tool description saying that coding agents should call that any time they had trouble figuring out how to use the rest of the MCP. I really like this. It's super cheap to implement and I expect you'd get a bunch of actionable signal in amongst the noise.

I love this, although I can't help but think that a lot of agents will - for better or for worse - send you a bunch of PII.

Re: Designing APIs for Agents

#36

Post by what »

simonw wrote: post #33
what wrote: post #27

Earlier quoted context omitted.

Why are you asking an LLM what could have been better or was confusing? It literally has no idea.

If they try something and it doesn't work and they then try something else and it DOES work that's concrete feedback.

Are you saying the machine can tell you what confused them?

Re: Designing APIs for Agents

#37

Post by tyre »

mohamedkoubaa wrote: post #23
benswerd wrote: post #10

Earlier quoted context omitted.

Conservatively speaking, LLMs degrade past 40% of a 2M context window, 4k tokens is 0.2%, so no degradation there. Thats also current generation conservative estimate. I think wasteful is an irrelevant metric. Claude ingests those tokens in a quarter of a second, if it causes it to catch any bug ever it saves far more time than it ever uses. Any individual default that causes unexpected behavior causes more problems,…

Boiling frog problem

the Electron problem

Re: Designing APIs for Agents

#38

Post by towardtype1 »

bigstrat2003 wrote: post #34
ventana wrote: post #19

I don't like the idea of making APIs effectively unusable for a human developer. We might not write a lot of code anymore, but getting rid of defaults and asking agents to pass all possible values explicitly makes it impossible to quickly debug the API call (e.g. with curl or something). It's similar to HTTP/1: there are a lot of headers in the protocol, but you can still use nc or openssl s_client and type the reque…

Also, any competent developer still writes tons of code. The "agentic era" is completely overblown.

Where do you see this? I’ve not found this to be true since at least Xmas.

Re: Designing APIs for Agents

#39

Post by benswerd »

bigstrat2003 wrote: post #34
ventana wrote: post #19

I don't like the idea of making APIs effectively unusable for a human developer. We might not write a lot of code anymore, but getting rid of defaults and asking agents to pass all possible values explicitly makes it impossible to quickly debug the API call (e.g. with curl or something). It's similar to HTTP/1: there are a lot of headers in the protocol, but you can still use nc or openssl s_client and type the reque…

Also, any competent developer still writes tons of code. The "agentic era" is completely overblown.

I'll say this: as a very competent engineer I have gone weeks at a time without handwriting a single line of code in the past few months. It is where the industry is going.

Re: Designing APIs for Agents

#40

Post by gnabgib »

benswerd wrote: post #39
bigstrat2003 wrote: post #34

Earlier quoted context omitted.

Also, any competent developer still writes tons of code. The "agentic era" is completely overblown.

I'll say this: as a very competent engineer I have gone weeks at a time without handwriting a single line of code in the past few months. It is where the industry is going.

[flagged]
Post reply on HN