Operations | Monitoring | ITSM | DevOps | Cloud

We build agents to take work off engineers’ plates. Then we give those engineers a new manual job: reading failed runs and babysitting prompts. Agents will improve themselves automatically. We’re not there yet, but this is the future I’m betting on. We’ve been working on this ourselves at Komodor over the past year. We know how hard it is to turn a failure into an improvement that holds up beyond a few examples.

If your app pins openai in requirements or a lockfile, read this before you bump the version, not after something breaks.

An LLM inference provider hosts open-weight models like Llama, DeepSeek, and Qwen behind a pay-per-token API, handling GPUs, scaling, and serving for you. The same Llama 3.3 70B model ranges from $0.10 to $1.04 per million input tokens depending on who serves it, so provider choice is a pricing decision. Top picks as of September 2026: Groq and Cerebras for speed, DeepInfra for price, Together and Fireworks for breadth, Baseten for custom models.

Observability investigations rarely follow a straight line. A latency question might cause an AI agent to start with a metric, pivot into traces, compare a deployment window, and finish by reducing thousands of logs to a few patterns. Each individual query is easy, but propagating context throughout an entire investigation can be tricky and expensive.

Collecting high-quality user feedback on agents, like from thumbs-up or thumbs-down buttons, is an important part of agent development. User feedback is needed for everything from basic gut checks on whether your agents are behaving well to planning and creating robust eval sets. It’s a critical part of Datadog’s Agent Observability, which provides explicit end-user feedback features for collecting and analyzing it.

AI agent observability means tracing tool calls, reasoning steps, and handoffs, not just tokens and latency. Here's what to instrument and why. Sejal Pandey works on content and growth at Last9, writing about observability, reliability, and SRE practices.

AI adoption is accelerating across enterprises, but governance isn't necessarily keeping pace. As AI becomes part of everyday business workflows and applications, organizations need to understand where it is being used, what data it can access, and who is responsible for managing the risks. ManageEngine's shadow AI researchhighlights this challenge.

Build when the problem is narrow (one provider, one team, simple attribution) and the tooling is strategically yours to own. Buy when AI spend spans providers, arrives untagged, and needs unit costs finance will trust, because that build is a multi-quarter platform project with a permanent maintenance tail. Price both paths in engineer-years before deciding. CloudZero sells the “buy” side.

Perplexity pricing runs $0 for Free, $20 a month for Pro, and $200 a month for Max, with enterprise seats listed from $40 per user. Pro fits most people who search for work daily. Max exists for heavy automation. The prices are verified against Perplexity's live plans page as of September 2026. When Perplexity published a customer quote on its own pricing page, it chose an unusual one.