Ben Lorica asked why old IT-ops logging doesn't already cover agents. Conikee says a single agent command can chain search, awk and network calls, while most observability tools record only 'bash tool executed', hiding what actually happened.
…or code into minutiae operations, whatever operations that it's executing within that particular single line. And we classify it as whether this is a file system operation, a network operation, and what is the sequence. That is our unique constraint. And that unlocked a lot of value for us inside.
So set aside the classification. So what you're asserting is that the existing tools don't even do the first step. Which is kind of weird, right? Because like I said, if you rewind before AI to the ITOS DevOps world, I thought that that was a given that you would capture those traces.
There is a difference between the old world and the new world. In the old world, right, anything ops like an IT, SecOps, DevOps, they either executed a single command or they created a bash or a DevOps tool like a HashiCOPS ecosystem, where you create a script to execute tool one, tool two, tool three. You're creating a sequence, right? But agents don't think like us, like us humans. Because of their pre-training, their environment is the bash. They have classic knowledge of how to be efficient in bash. And to save you and me tokens, they combine these commands together, which looks like a lumpy, large command.
Oh, I see. So if you were to explain this to someone who's not looking at these traces, the explanation will be your tool gives me really fine-grained records, whereas many of the existing tools just Give you kind of a high-level overview of what the agent did.
Exactly. And even if some tools do that, their approach is different. You know, some are using an LLM to break it down. They just feed the input and say, classify it, right? Now, when you use an LLM, it's stochastic, right? You just get a distribution and a choice is made. Or they use, you know…
It's like basically stuffing a log file, log files to an LLM and then making the LLM make sense of it, which, as you point out, LLMs are stochastic. So who knows? Exactly. Right.