Essay says agent frameworks lack logs needed for real-time oversight
A review of four widely used frameworks found missing persistent agent IDs and records of which humans approved tasks.
2
Stories per day · 30 days
Relatedopentelemetry4ai-agents3splunk3hallucinations2solarwinds2access-control1agent-security1agent-traces1annotation1broken-authorization1cert-advisory1cisco1clickhouse1cloudflare1compression1data-pipeline1grafana1honeycomb1
25 stories, newest first · one card per story
Stories tagged #observability
Splunk and SolarWinds patch code execution and access flaws
Fixes cover 16 product CVEs in Splunk Enterprise, 15 in SOAR, plus Observability and Patch Manager bugs.
1
Splunk survey: AI agent observability lags hallucination detection
Of 2,050 respondents in ten countries, 85% want hallucination detection but only 58% say they can catch it.
1
SolarWinds Observability Self-Hosted before 2026.4 has broken authorization
Canada’s Cyber Centre points administrators to CVE-2026-28328 and says to apply SolarWinds updates when available.
Grafana Cloud adds Knowledge Graph for agents and incident response
Custom entities and agent runtime context are generally available; several monitoring features remain in preview.
1
Paper proposes Semantic Observability for automated root-cause analysis
The paper is architectural and defers measured results on LogHub and Train-Ticket to a companion study.
Splunk survey: AI agent rollout is outrunning monitoring and ownership
Of 2050 respondents, 38% lack clear ownership for monitoring AI and only 58% can effectively watch for hallucinations.
2
Engineer argues teams should run their own LLM proxy
The post says vendor dashboards lack engineer-grade token time series, while a self-hosted proxy can log keys, models, clients, and status.
1
Annotrace: A Workbench for Step-Level Annotation of Agent Traces
Annotrace labels agent traces at step level and reports 91% model agreement on 235 units.
Rewinding the exponential: How we keep hardware usage down
Cloudflare details pipeline changes that deferred about 2.5 years of hardware growth.
4
Filter, reshape, and redact logs before export with Transformers
Cloudflare Logpush Transformers, now generally available, filter, redact, and reshape logs with SQL before export.
5
New Relic adds terminal-based investigation and recovery checks with Ground Truth CLI
New Relic released Ground Truth CLI so developers and AI agents can investigate incidents from the terminal.
2
Introducing Cloudflare Traces: follow requests through our entire platform
Cloudflare Traces open beta follows requests across security, cache, routing, Workers, and origin with OpenTelemetry export.
5
8 major updates to Cloudflare Observability
Cloudflare combined logs, traces, SQL queries, alerts, and dashboards into one observability platform with new pricing.
10
Detect and send production issues straight to your agent
Cloudflare Workers Issues, now in open beta, groups production errors and sends them to coding agents.
5
An OpenAI Agent Hacked Australia's Health Service. Their Government Found Out Months Later.
SolarWinds has patched two RCE vulnerabilities in Observability Self-Hosted, affecting all versions up to 2026.2.3.
2
Closing the observability gap for the AI-ready enterprise
Sponsored NETSCOUT piece argues MELT telemetry leaves dangerous gaps for AI-driven enterprise operations.
1
SolarWinds Observability Flaws Let Unauthenticated Attackers Execute Remote Code
SolarWinds patched two unauthenticated RCE flaws in Observability Self-Hosted 2026.2.3; CVE-2026-28324 scores CVSS 9.8, CVE-2026-28325 scores 8.8, no exploitation reported.
2
Salesforce Agentforce: Bridging the Enterprise AI Gap from ‘Vibe Coding’ to Battle-Tested Orchestration
Salesforce pitches Agentforce as an enterprise agent platform with testing, observability, and deterministic gating; Southwest Airlines reports $6M annual savings and 45% autonomous resolution.
10
The fix for rogue AI agents could be more AI
Startups and labs are deploying AI monitors like Apollo's Watcher and Goodfire's Silico to oversee rogue agents, though skeptics warn agents can deceive monitors.
Airrived adds Agentic Observability to track AI agent actions and risks
Airrived launches Agentic Observability to give enterprises end-to-end visibility into AI agent actions, permissions, data flows, and costs.
2
Involving before Evolving: A Vision for Trustworthy Enterprise Digital Twin Engineering
Vision paper proposes 'involving before evolving' staged approach for trustworthy enterprise digital twins, validated via an ongoing Michelin prototype.
numbat - AI agent observability, (Fri, Sep 4th)
SANS reviews Perplexity's open source numbat, a Go-based tool giving security teams observability, detection rules, and enforcement for AI agents like Claude and Gemini.
Grafana security advisory (AV26-860)
Canada's Cyber Centre warned that Grafana Alloy versions through 1.18.1 are affected by CVE-2026-19516 and urged users to apply available updates.