This website uses cookies
Read our Privacy policy and Terms of use for more information.
Everyone demos the reasoning. Nobody demos what the agent does to your data layer, or what happens when it hits the rate limit mid-incident.
Aug 23, 2026
•
5 min read
Two observability acquisitions in six days. Here is what that means for who owns your telemetry.
Aug 21, 2026
3 min read
The demo shows you the tower. It never shows you the year underground.
Aug 9, 2026
2 min read
Continuous profiling is becoming observability's fourth signal. What it is, what it does well, and the honest cost of always-on.
Jul 30, 2026
A governance model for agent actions that fits in your head: decide by blast radius, not confidence.
Jul 26, 2026
Not 'is the model up', but 'why did the agent do that'. Seeing an autonomous agent's model calls, tool calls and reasoning as one trace.
Jul 23, 2026
Two very different kinds of AI in operations. One is fluent, one reasons about cause. Which you trust for a root cause decides whether you fix the incident or a coincidence.
Jul 22, 2026
4 min read
When a real pattern does not exist, a vendor best practice is just their product with a halo on it. Keep a human on the decision until the pattern earns its place.
Jul 19, 2026
Not a chatbot and not a script. An AI system that is given a goal and takes the actions to reach it.
Jul 14, 2026
An industry now exists to shave the observability invoice. That is financial engineering. The real fix is deciding what each signal is for.
Jul 12, 2026
Good tools answer the question for you, until the one they can't. Keep your curiosity muscle warm on purpose.
The moment an AI agent acts, someone owns the outcome. Most teams have not said who.
Jul 5, 2026
Strip away the vendor gloss and the message from the floor was steady, honest, and unglamorous.
Jul 3, 2026
Vendors sell autonomous operations. The Bank of England found that 2% of AI use cases run fully autonomously. That gap is correct, and here is how to climb it.
Jun 7, 2026
9 min read
$3.35bn says security and observability are one market. A survey of 506 leaders says the teams aren't. The gap is where this goes wrong.
Jun 3, 2026
Reliability numbers never climb in a straight line. One bad month is not a failed strategy.
May 25, 2026
Auto-remediation is replacing the 3 AM scramble. But toil is rising, MTTR is worsening, and the remaining 20% of incidents just got harder.
Feb 15, 2026
11 min read
