Rendered at 07:31:48 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
nevon 2 hours ago [-]
I feel like this is a bit of a "draw the rest of the owl" problem. With a couple of terabytes of logs per day, god knows how many metric timeseries, thousands of cloud environments, thousands of repositories, hundreds of thousands of build pipelines running every day, it's not something you can just point an agent at and call it a day. Segmenting and correlating the data is _hard_. Even something as seemingly simple as "p95 latency of this endpoint has increased - what repo contains the responsible code" is difficult to do, even if you are willing to give an agent read access to everything.
jeffbee 2 hours ago [-]
Yeah something about this whole concept is way, way off. The energy, and therefore cost, of an LLM analyzing every data point of every time series is many orders of magnitude too high, unless your operations are trivial.
jubilee33 1 hours ago [-]
I encounter this problem a lot in my work. Agents being run on a cron for instance, where the task is not dynamic and a simple script can be more than sufficient. As agentic use increases i think it will get worse, as scripting is hard to do elegantly, even if the agent is writing the script.
But having an agentic call for every single detail is just so inefficient.
antupis 12 minutes ago [-]
I think there running both will be winning combination scripts/classical ML do large scale crunching and when they find some anomaly or some threshold creates alert. Agents will create initial report and maybe create first pr for developer.
ibraryunus 21 minutes ago [-]
[flagged]
yegle 2 hours ago [-]
I have been doing something similar but much smaller scale: having a daily scheduled task from Antigravity to ADB connect to my phone and dump all logs and do analysis to let me know if there's any app behaving weirdly (e.g. repeated crashes).
The adb connection is intentionally over Tailscale so in the morning after I connect to some random WiFi (Android remote debugging is only enabled w/ WiFi connection) I can start reading the report, then quote and ask Gemini to fix some issues.
We have been doing this recently after some security incidents. Constant monitoring of all security related events, and being able spot anomalys which our normal system isn’t able to catch. The active part is just emailing us right now, but I am considering adding some light lock down actions.
kelseydh 2 hours ago [-]
It feels like the real value here will be from monitoring services like DataDog adding this functionality to their own internal products, rather than companies rolling their own agentic monitoring. Datadog's Bits AI is already quite helpful in scanning monitoring data for insights.
theshrike79 2 hours ago [-]
Without even knowing what it is, I'm kinda guessing Datadog's AI also has a nice hefty price tag attached to it?
And if not today, it will have one soon.
renegade-otter 40 minutes ago [-]
This is like tokenmaxxing for observability?
8 hours ago [-]
2bird3 8 hours ago [-]
Feels like the author hits the nail on the head but leaves out higher cardinality data. Would love to know how Anthropic goes about ingesting and analyzing their logs, of which they presumably have many.
appplication 7 hours ago [-]
Ingesting? Presumably Kafka. Analyzing? Presumably a fairly large analytics org.
esafak 8 hours ago [-]
How are you setting the alerts? Are you using anomaly detection? If so, what kind?
The adb connection is intentionally over Tailscale so in the morning after I connect to some random WiFi (Android remote debugging is only enabled w/ WiFi connection) I can start reading the report, then quote and ask Gemini to fix some issues.
(Disclosure: Not mine, but a friend's.)
And if not today, it will have one soon.