Is access enough? Auth patterns for Claude Managed Agents
MCP tunnels let Claude Managed Agents reach and authenticate to real infrastructure, but access alone doesn't make an agent one you'd trust to run on-call.
Latest
Introducing Issues, one problem, one thread, start to finish.
On-call means re-triaging the same problem as diagnoses shift underneath you. Causely's new Issues give people and agents one stable thread instead.
Expanded Dynatrace Support: Better, Faster, Cheaper Agents
Causely turns Dynatrace entities, topology, and alerts into a causal model that names the root cause, making on-call agents better, faster, and cheaper.
Your on-call AI agent is wrong more than you think
Most frontier LLMs degrade badly by ~1,000 tokens of input, not the millions in their spec sheets. For on-call agents, that means accuracy drops exactly as an incident gets complex. The fix isn't a bigger model. It's not handing the LLM the raw data at all.
Auto-instrumenting Java with eBPF: No JVM changes required
Getting OpenTelemetry into Java enterprise applications without touching the JVM has been a persistent gap. OBI changes that, and for Causely customers, it unlocks the topology data needed to pinpoint root causes across complex Java microservice architectures.
Causely MCP Skills: stop prompt-engineering your reliability agent
Causely MCP Skills are live. One master router + six specialist workflows: alert triage, change impact, K8s investigation, postmortems & more. Describe your situation, Skills pick the right tools. No prompt engineering. No orchestration.
Semantics in Observability
Observability semantics fall into six layers, from entity inventory to constraints. Most tooling reaches layer two. This post defines all six precisely.
Why GenAI applications are hard to operate
Standard observability tools were built for deterministic systems. GenAI applications break that contract — token counts shift, tool call patterns change, completion rates drop — and none of it fires an alert. Here is what OTel GenAI instrumentation gives you today, and where the gaps remain.
The DNS blind spot hiding in your agentic pipelines
DNS lookup latency is invisible to standard OpenTelemetry instrumentation. eBPF-based tracing closes the gap, and it matters more as agents fan out calls across MCP servers.
A Cursor Plugin for AI Ops Agents You Can Trust in Production
Causely is now a Cursor plugin. Your coding agent gets causal context from your live environment and can move from emerging causes of reliability risk to code-level fixes in the IDE.
Your AI Ops Agent Is Guessing
Named root causes are what turn a guessing agent into one you can trust to act without manual review.
Why AI agents burn tokens on every reliability query
AI agents reconstruct environment state from raw telemetry on every reliability query. Causal context eliminates the reconstruction and cuts token use by 60%.
AI
Why Your AI SRE Agent Is Stuck on Read-Only
Most AI SRE agents are stuck on Read-Only — not because teams lack trust, but because raw telemetry offers no causal context to act on with confidence.
Blog
How Humm Group Delivered Flawlessly in a High-Stakes Product Launch
Launching a new fintech product required certainty across a complex microservices platform. With Causely modeling cause-and-effect relationships across services, Humm Group gained system-level understanding and confidence that critical dependencies behaved correctly during launch.
Reliability Is Managed In Services, But Felt In Transactions
Reliability is managed in services, but users experience outcomes. In complex, multi-service and AI-driven architectures, systems can look healthy in isolation while end-to-end workflows still fail. Product reliability needs visibility at the level of transactions and flows.
Causely product
Alerts Aren’t the Investigation: What Comes Next in Incident Response?
Alerts are signals, not explanations. By explicitly mapping alerts to symptoms and inferred root causes, Causely turns alert noise into a coherent explanation of what is actually happening in the system.
opentelemetry
How to Turn Slow Queries into Actionable Reliability Metrics with OpenTelemetry
Slow SQL queries degrade UX and reliability. This guide shows how to distill OpenTelemetry DB spans into actionable metrics: build span-derived slow-query dashboards, rank queries by traffic impact, and detect regressions with anomaly baselines, so you fix what matters first. Hands-on lab included.
Causely product
When Asynchronous Systems Fail Quietly, Reliability Teams Pay the Price
Causely’s causal model has been expanded for asynchronous messaging systems. Instead of treating queues as opaque buffers, Causely models messaging infrastructure as it operates in production, making asynchronous failures explicit and explainable.
Alerts Aren’t the Investigation
Alerts are supposed to start an investigation. Too often, they start translation: what is the system doing right now? That translation slows containment, splinters context, and stretches customer impact.
Queue Growth, Dead-Letter Queues, and Why Asynchronous Failures Are Easy to Misread
Asynchronous pipelines sit at the core of most modern systems. Message brokers accept traffic, consumers process it in the background, and downstream services depend on the results. When these systems fail, the failure rarely shows up where it starts.
Causality
Slight Reliability EP 113: AI Use-cases for SRE with Shmuel Kliger
Originally published to the Slight Reliability Podcast.
integration
Causely Expands Datadog Integration to Deliver Causal Intelligence Across Hybrid Environments
Causely’s expanded Datadog integration turns Datadog APM signals into system-level causal intelligence, helping teams understand how issues propagate across services and pinpoint true root cause.
DevOps & SRE
Thank You, FluxCD: How it helps us, and how you can use it too!
How Causely uses FluxCD and GitOps to ship weekly on Kubernetes, keep clusters in sync, and wire up OpenTelemetry and Causely in a hands-on lab you can copy.
Causely Named a Gartner Cool Vendor in AI for IT Operations 2025
Gartner recognized Causely for maintaining a live causality graph and using continuous inference to identify the underlying driver behind changes in golden signals as they emerge, even when failures cascade across multiple services.