# observability ai agents

A software observability concept concerning telemetry for generative AI agent operations.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## 200 OK is dead as an AI agent health signal. Here's what comes next.

DevFeed: [200 OK is dead as an AI agent health signal. Here's what comes next.](<https://devfeed.tech/articles/200-ok-is-dead-as-an-ai-agent-health-signal-here-s-what-comes-next-140899.md>)

Original publisher: [Read original article](<https://thenewstack.io/silent-ai-agent-failures/>)

Author: Boris Chabeda

Published: 2026-11-18T16:00:00Z

Content type: article

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [health check](<https://devfeed.tech/topics/health-check.md>), [Monitoring & Alerting](<https://devfeed.tech/topics/monitoring-alerting.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [Logging and metrics](<https://devfeed.tech/topics/logging-and-metrics.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-architecture](<https://devfeed.tech/tags/agent-architecture.md>), [agent-orchestration](<https://devfeed.tech/tags/agent-orchestration.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [andela](<https://devfeed.tech/tags/andela.md>), [apm](<https://devfeed.tech/tags/apm.md>), [audit](<https://devfeed.tech/tags/audit.md>), [automated](<https://devfeed.tech/tags/automated.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [billing](<https://devfeed.tech/tags/billing.md>), [blast-radius](<https://devfeed.tech/tags/blast-radius.md>), [bottleneck](<https://devfeed.tech/tags/bottleneck.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [budget](<https://devfeed.tech/tags/budget.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classification-accuracy](<https://devfeed.tech/tags/classification-accuracy.md>), [health](<https://devfeed.tech/tags/health.md>), [observability](<https://devfeed.tech/tags/observability.md>), [post-contributed](<https://devfeed.tech/tags/post-contributed.md>), [signal](<https://devfeed.tech/tags/signal.md>), [sponsor-andela](<https://devfeed.tech/tags/sponsor-andela.md>), [sponsored-post-contributed](<https://devfeed.tech/tags/sponsored-post-contributed.md>)

### AI overview

The article argues that `200 OK` and conventional APM metrics can hide AI agents that silently reject valid requests. In a 100-trace audit, 27% of sampled decisions were false-positive `OUT_OF_SCOPE` blocks; the authors propose inline schema validation and a local RoBERTa-base NLI cross-encoder to compare intent decisions and hand off schema failures or disagreements to an operator. On a co-hosted c7i.xlarge, the evaluator used about 1.5 GB RAM and one CPU core, with reported p50/p95 latency of 42/88 ms and no added infrastructure cost. The authors report that it caught a prompt regression misclassifying shoe-size exchanges, enabling rollback within 2m 36s. They describe DeBERTa-v3-base as a higher-accuracy option for longer queries, with heavier CPU demands. Limitations include correlated judge errors, 30 unguarded requests after prompt changes, and dependence on available operators.

### Source excerpt

A customer asks whether they can swap unworn boots for a size 10. The agent replies, in under a second, The post 200 OK is dead as an AI agent health signal. Here's what comes next. appeared first on The New Stack.

## Best Tools for AI Agent Observability in Banking

DevFeed: [Best Tools for AI Agent Observability in Banking](<https://devfeed.tech/articles/best-tools-for-ai-agent-observability-in-banking-131241.md>)

Original publisher: [Read original article](<https://www.lyzr.ai/blog/ai-agent-observability-tools-for-banks/>)

Author: Lyzr Team

Published: 2026-11-12T10:05:55Z

Content type: comparison

Language: en

Sources: [Lyzr.ai](<https://devfeed.tech/sources/lyzr-ai.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [tracing](<https://devfeed.tech/topics/tracing.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Grafana Cloud](<https://devfeed.tech/topics/grafana-cloud.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [llamaindex](<https://devfeed.tech/topics/llamaindex.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-observability](<https://devfeed.tech/tags/agent-observability.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-observability](<https://devfeed.tech/tags/ai-agent-observability.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [banking](<https://devfeed.tech/tags/banking.md>), [best](<https://devfeed.tech/tags/best.md>), [observability](<https://devfeed.tech/tags/observability.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

The comparison separates three banking needs: tracing agent runs, controlling agent actions, and preserving an examiner-ready governance record. Fiddler, Arthur, Arize Phoenix, Grafana Cloud and OpenObserve describe run observability; Opencontroller authorizes tool calls, records activity and can quarantine agents; Madison links rules, obligations, policies, controls, tests and evidence to a named approver but does not trace runs. The vendors differ in deployment and enforcement: Phoenix and OpenObserve describe self-hosted options, Grafana Cloud is described as cloud-based, Fiddler claims inline allow/block/redact, while Arthur returns a verdict for the application to enforce. The guide recommends inventorying agents, deciding what trace content may be captured, choosing deployment and enforcement models, and rehearsing a real run back to its governing rule. OpenTelemetry GenAI conventions provide a common trace structure, but remain under active development; prompt and response content is off by default.

### Source excerpt

AI agent observability in banking means being able to answer "what did the agent do, and why?" with a record that survives an examination: the...

## Port vs Guild: AI Agent Governance for Your Software Factory

DevFeed: [Port vs Guild: AI Agent Governance for Your Software Factory](<https://devfeed.tech/articles/port-vs-guild-ai-agent-governance-for-your-software-factory-124879.md>)

Original publisher: [Read original article](<https://www.port.io/blog/porxt-vs-guild>)

Author: John Crowley

Published: 2026-11-09T18:54:32Z

Content type: comparison

Language: en

Sources: [Port](<https://devfeed.tech/sources/developer-experience-platform-engineering-blog-port.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [control-plane](<https://devfeed.tech/topics/control-plane.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [versioning](<https://devfeed.tech/topics/versioning.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-control](<https://devfeed.tech/tags/agent-control.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-governance](<https://devfeed.tech/tags/ai-agent-governance.md>), [ai-software-factory](<https://devfeed.tech/tags/ai-software-factory.md>), [compare](<https://devfeed.tech/tags/compare.md>), [control](<https://devfeed.tech/tags/control.md>), [control-plane](<https://devfeed.tech/tags/control-plane.md>), [factory](<https://devfeed.tech/tags/factory.md>), [governance](<https://devfeed.tech/tags/governance.md>), [guild](<https://devfeed.tech/tags/guild.md>), [port](<https://devfeed.tech/tags/port.md>), [sdlc](<https://devfeed.tech/tags/sdlc.md>), [software](<https://devfeed.tech/tags/software.md>), [software-factory](<https://devfeed.tech/tags/software-factory.md>), [vs](<https://devfeed.tech/tags/vs.md>)

### AI overview

Guild provides an agent control plane: it assigns agents identities, scopes and injects credentials at runtime, logs actions, and tracks agent costs. Its Software Factory handles bounded coding issues through checks and review to a pull request. The article distinguishes this from a software factory platform, which maps services, owners, dependencies, and standards, applies policies to both agent and human changes, and can include deterministic steps such as deployments and ServiceNow tickets. It presents Guild and Port as complementary: Guild governs agents and their runs; Port governs the estate and work around them. The article suggests evaluating whether changes can be tied to services, owners, and standards; whether policies cover human work; and whether the platform handles non-agent steps and tracks estate outcomes such as change failure rate. Guild's reported factory metrics are its own claims, and the dLocal example is presented as a customer account.

### Source excerpt

Compare Port vs Guild for AI agent governance: what an agent control plane does and what a software factory adds across the SDLC.

## See How Your Genie Agent Got to the Answer

DevFeed: [See How Your Genie Agent Got to the Answer](<https://devfeed.tech/articles/see-how-your-genie-agent-got-to-the-answer-112987.md>)

Original publisher: [Read original article](<https://montecarlo.ai/blog-see-how-your-genie-agent-got-to-the-answer>)

Author: Virna Sekuj

Published: 2026-11-02T17:11:35Z

Content type: release

Language: en

Sources: [Monte Carlo](<https://devfeed.tech/sources/monte-carlo.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [observability](<https://devfeed.tech/topics/observability.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-observability](<https://devfeed.tech/tags/agent-observability.md>), [agent-trust](<https://devfeed.tech/tags/agent-trust.md>), [agent-trust-ai-observability](<https://devfeed.tech/tags/agent-trust-ai-observability.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-observability](<https://devfeed.tech/tags/ai-observability.md>), [bi](<https://devfeed.tech/tags/bi.md>), [business](<https://devfeed.tech/tags/business.md>), [can](<https://devfeed.tech/tags/can.md>), [data](<https://devfeed.tech/tags/data.md>), [databricks](<https://devfeed.tech/tags/databricks.md>), [databricks-ai](<https://devfeed.tech/tags/databricks-ai.md>), [english](<https://devfeed.tech/tags/english.md>), [enterprises](<https://devfeed.tech/tags/enterprises.md>), [genie](<https://devfeed.tech/tags/genie.md>), [monte-carlo](<https://devfeed.tech/tags/monte-carlo.md>), [observability](<https://devfeed.tech/tags/observability.md>), [question](<https://devfeed.tech/tags/question.md>), [research](<https://devfeed.tech/tags/research.md>), [show](<https://devfeed.tech/tags/show.md>), [sql](<https://devfeed.tech/tags/sql.md>), [traces](<https://devfeed.tech/tags/traces.md>), [users](<https://devfeed.tech/tags/users.md>)

### AI overview

Monte Carlo's updated Genie traces expose the research trail behind each answer, making it easier to locate where an agent went off course. In agent mode, each research step appears as a node in the trace tree with its SQL queries nested beneath it; spans identify the turn mode, and turns show the agent's restated intent, plan, and narration. Standard-mode turns also surface selected tables, applied instructions, and matched example questions with confidence scores. Existing traces gain the new research-step structure automatically, while standard-mode traces remain unchanged. Monte Carlo-hosted Agent Observability can also ingest traces from Databricks MLflow SDK agents, Knowledge Assistants, and Genie: workspace traces are exported on a schedule, converted to OpenTelemetry, and stored for viewing without a live warehouse query. Hosted ingestion is enabled per account.

### Source excerpt

Genie traces now show every research step behind an answer, and Databricks agent traces can be ingested into Monte Carlo-hosted Agent Observability. Databricks AI/BI Genie has become the front door to data for many enterprises. Business users ask a question in plain English, and Genie writes the SQL, runs it, and hands back an answer. ...

## Soei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering

DevFeed: [Soei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering](<https://devfeed.tech/articles/soei-structured-observability-of-evidence-and-intent-for-multi-agent-ai-software-engineering-107395.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.39468>)

Author: Mohammed Nayeem Khan, K S Sarun Kumar

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [observability](<https://devfeed.tech/topics/observability.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-software](<https://devfeed.tech/tags/ai-software.md>), [ai-software-engineering](<https://devfeed.tech/tags/ai-software-engineering.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [commit](<https://devfeed.tech/tags/commit.md>), [completion](<https://devfeed.tech/tags/completion.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [multi-agent-ai](<https://devfeed.tech/tags/multi-agent-ai.md>), [observability](<https://devfeed.tech/tags/observability.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [structured](<https://devfeed.tech/tags/structured.md>)

### AI overview

The study finds that coding-agent activity logs can fail to show whether work was actually verified: in 45 sessions, an estimated 23.4% of code-editing episodes had no independent check after the last edit, and 57.8% of agent-marked completed to-dos lacked intervening proof. It also reports long sessions, replay limits that omit substantial transcript data, and credential-like strings in some records. The authors propose Soei, combining an acknowledgement-aware event schema, hash-chained local ledger, provenance graph, calibrated attribution and lineage, and a verification layer that separates completion claims from evidence. On this corpus, the ledger was 20% of raw data size, contained no content or credentials, and supported tamper detection and deterministic replay. The abstract also reports an unauthenticated local mutation surface in Agenttrail's Map service.

### Source excerpt

arXiv:2610.39468v1 Announce Type: new Abstract: AI coding agents now do long, multi-step and multi-session software work with little supervision. When a developer comes back to that work, the useful question is not what the model said but what was actually done, by whom, and whether it is finished. We study this in three parts. First, we verify Agenttrail, an open-source local observability tool for coding agents, against its source at commit e4ba2da: nine documented constants and mechanisms hold at file-and-line level, two event pipelines are never unified, and its Map service has an unauthenticated local mutation surface. Second, we run a prototype of our system on 45 real coding-agent sessions (102,233 records, 20,577 tool executions, 2,336 human-to-agent episodes). With a blind-audited classifier (precision 83.3% and 96.7%) we estimate that 23.4% (95% CI 17.1 to 35.7) of code-editing episodes end with no independent check after the last edit, and that 57.8% of to-dos the agent marked complete after editing had no proof in between. A 10-minute timing heuristic for session hand-offs recovers 6 of the 24 session pairs that content lineage links. 42% of sessions run longer than 24 hours, 48.1% of transcript bytes lie past a 2 MiB replay bound, and 1,326 records in 16 sessions contain credential-like strings. Third, we propose Soei (Structured Observability of Evidence and Intent): an acknowledgement-aware event schema, a hash-chained local ledger, a W3C PROV-aligned graph, calibrated inference for attribution and lineage, and a verification layer that keeps a claim of completion apart from proof. On the same corpus the ledger is 20% of raw size, holds no content or credentials, verifies at about 126k events/s, detects tampering and replays deterministically. We position the work against concurrent 2026 proposals and define autonomy levels with evidence gates and harness metrics baselined on our data.

## AI Agent Observability vs Traditional APM: What Changes

DevFeed: [AI Agent Observability vs Traditional APM: What Changes](<https://devfeed.tech/articles/ai-agent-observability-vs-traditional-apm-what-changes-106157.md>)

Original publisher: [Read original article](<https://www.lyzr.ai/blog/ai-agent-observability-vs-traditional-apm/>)

Author: Lyzr Team

Published: 2026-10-29T07:36:11Z

Content type: article

Language: en

Sources: [Lyzr.ai](<https://devfeed.tech/sources/lyzr-ai.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [tracing](<https://devfeed.tech/topics/tracing.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [observability](<https://devfeed.tech/topics/observability.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-observability](<https://devfeed.tech/tags/agent-observability.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-observability](<https://devfeed.tech/tags/ai-agent-observability.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [apm](<https://devfeed.tech/tags/apm.md>), [observability](<https://devfeed.tech/tags/observability.md>), [vs](<https://devfeed.tech/tags/vs.md>)

### AI overview

Traditional APM can show a healthy request even when an AI agent makes a harmful decision: a 200 response, normal latency and no exception do not establish correctness. The article recommends keeping APM for infrastructure and adding agent-run traces for model calls, tool use, retrieval and handoffs, joined to service traces with shared trace context. Because agent traces may contain customer data, set capture and redaction rules; define correctness with policy checks, evals and sampled human review; and calibrate automated judges. Adjust sampling and alerts to catch low eval scores, high per-run cost, unusual tool-call counts, guardrail triggers and new prompt or model versions, then turn failures into regression tests. OpenTelemetry GenAI spans are identified as an instrumentation option, but their status is marked "Development," so the article advises pinning versions. Observability records and evaluates behavior; it cannot itself block a call, and uninstrumented agents remain outside its view.

### Source excerpt

TL;DR You run platform engineering at a fintech, and your APM is good: golden-signal dashboards, clear SLOs, a pager rotation that works. Then on Monday,...

## AI agent observability is struggling to keep up with hallucinations

DevFeed: [AI agent observability is struggling to keep up with hallucinations](<https://devfeed.tech/articles/ai-agent-observability-is-struggling-to-keep-up-with-hallucinations-95022.md>)

Original publisher: [Read original article](<https://www.helpnetsecurity.com/2026/10/22/ai-agent-observability-report/>)

Author: Anamarija Pogorelec

Published: 2026-10-22T04:00:14Z

Content type: news

Language: en

Sources: [Help Net Security](<https://devfeed.tech/sources/help-net-security.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [AI agent hallucinations](<https://devfeed.tech/topics/ai-agent-hallucinations.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Hallucination detection](<https://devfeed.tech/topics/hallucination-detection.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-observability](<https://devfeed.tech/tags/agent-observability.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-observability](<https://devfeed.tech/tags/ai-agent-observability.md>), [alerts](<https://devfeed.tech/tags/alerts.md>), [api](<https://devfeed.tech/tags/api.md>), [code](<https://devfeed.tech/tags/code.md>), [costs](<https://devfeed.tech/tags/costs.md>), [diagnose](<https://devfeed.tech/tags/diagnose.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [guides](<https://devfeed.tech/tags/guides.md>), [hallucinations](<https://devfeed.tech/tags/hallucinations.md>), [it](<https://devfeed.tech/tags/it.md>), [news](<https://devfeed.tech/tags/news.md>), [observability](<https://devfeed.tech/tags/observability.md>), [observe-ai](<https://devfeed.tech/tags/observe-ai.md>), [report](<https://devfeed.tech/tags/report.md>), [security](<https://devfeed.tech/tags/security.md>), [splunk](<https://devfeed.tech/tags/splunk.md>), [survey](<https://devfeed.tech/tags/survey.md>), [systems](<https://devfeed.tech/tags/systems.md>), [teams](<https://devfeed.tech/tags/teams.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Splunk's survey of 2,050 IT and engineering professionals across ten countries finds that AI agents are widely used to diagnose system failures, while many organizations lack reliable ways to verify their answers. Teams commonly use agents for root-cause analysis, alert tuning and runbook drafts, but are more cautious about code changes; most report faster problem detection, though 14% say recovery slowed. Hallucinations expose a monitoring gap: 85% consider detecting invented answers important, but only 58% say they can do so reliably, and about half say their observability tools were not built for AI. Ownership is unresolved at 38% of organizations, even as 81% say AI monitoring has increased collaboration with security. Costs add pressure: observability exceeds monitored infrastructure costs in 57% of organizations, and half faced a surprise telemetry bill this year.

### Source excerpt

Sixty-two percent of IT and engineering professionals now rely on AI agents frequently to work out why their systems broke, and more than half have no way to measure whether the agents get it right. Splunk surveyed 2,050 of them across ten countries. Source: Splunk Agents diagnose, people still ship the code Teams have been careful about where they let agents work. Finding root causes, tuning alerts, and drafting runbooks, the step-by-step guides engineers follow ... More -> The post AI agent observability is struggling to keep up with hallucinations appeared first on Help Net Security.

## Asymptote Labs Lands $5.5 Million Seed for AI Agent Runtime Security

DevFeed: [Asymptote Labs Lands $5.5 Million Seed for AI Agent Runtime Security](<https://devfeed.tech/articles/asymptote-labs-lands-5-5-million-seed-for-ai-agent-runtime-security-92820.md>)

Original publisher: [Read original article](<https://www.securityweek.com/asymptote-labs-lands-5-5-million-seed-for-ai-agent-runtime-security/>)

Author: SecurityWeek News

Published: 2026-10-21T13:17:35Z

Content type: news

Language: en

Sources: [SecurityWeek](<https://devfeed.tech/sources/securityweek.md>)

Topics: [Security](<https://devfeed.tech/topics/security.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-harnesses](<https://devfeed.tech/tags/agent-harnesses.md>), [agent-runtime-security](<https://devfeed.tech/tags/agent-runtime-security.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-runtime](<https://devfeed.tech/tags/ai-agent-runtime.md>), [ai-agent-runtime-security](<https://devfeed.tech/tags/ai-agent-runtime-security.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [asymptote-labs](<https://devfeed.tech/tags/asymptote-labs.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [beacon](<https://devfeed.tech/tags/beacon.md>), [blocks](<https://devfeed.tech/tags/blocks.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cybersecurity-funding](<https://devfeed.tech/tags/cybersecurity-funding.md>), [funding](<https://devfeed.tech/tags/funding.md>), [platform](<https://devfeed.tech/tags/platform.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [runtime-security](<https://devfeed.tech/tags/runtime-security.md>), [runtime-security-platform](<https://devfeed.tech/tags/runtime-security-platform.md>), [security](<https://devfeed.tech/tags/security.md>), [tower](<https://devfeed.tech/tags/tower.md>)

### AI overview

Asymptote Labs raised $5.5 million in a seed round led by Tower Research Ventures to develop Beacon, an AI agent runtime security platform. Its open source telemetry layer standardizes activity from more than 20 agent harnesses, including Cursor, Codex, and Claude Code, in a data model extending OpenTelemetry. A commercial platform builds on that layer to monitor live activity and enforce policy at prompt and tool execution levels, aiming to steer agents away from unsafe behavior and block risky actions. Funding will support product development, engineering, and go-to-market work.

### Source excerpt

Asymptote Labs raises $5.5M seed led by Tower Research Ventures to commercialize its Beacon AI agent runtime security platform. The post Asymptote Labs Lands $5.5 Million Seed for AI Agent Runtime Security appeared first on SecurityWeek.

## API Observability for AI Agents

DevFeed: [API Observability for AI Agents](<https://devfeed.tech/articles/api-observability-for-ai-agents-92486.md>)

Original publisher: [Read original article](<https://www.swytchcode.com/content/api-observability-ai-agents>)

Author: Swytchcode Team

Published: 2026-10-21T09:53:12.592027Z

Content type: article

Language: en

Sources: [Swytchcode](<https://devfeed.tech/sources/swytchcode.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [tracing](<https://devfeed.tech/topics/tracing.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [API Logging](<https://devfeed.tech/topics/api-logging.md>), [observability](<https://devfeed.tech/topics/observability.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [api](<https://devfeed.tech/tags/api.md>), [api-governance](<https://devfeed.tech/tags/api-governance.md>), [api-monitoring](<https://devfeed.tech/tags/api-monitoring.md>), [apm](<https://devfeed.tech/tags/apm.md>), [arguments](<https://devfeed.tech/tags/arguments.md>), [audit](<https://devfeed.tech/tags/audit.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [governance](<https://devfeed.tech/tags/governance.md>), [logging](<https://devfeed.tech/tags/logging.md>), [logs](<https://devfeed.tech/tags/logs.md>), [observability](<https://devfeed.tech/tags/observability.md>), [tracing](<https://devfeed.tech/tags/tracing.md>)

### AI overview

For AI agents, useful API observability must trace the model's tool-selection decision as well as the resulting request. Capture the selected canonical method and considered alternatives, policy rule and outcome (allowed, denied, or held for approval), arguments with secrets redacted, response status, a parsed check against the expected shape, and retry count. Request-only traces miss why a method was chosen and whether a call was refused or never attempted. Status-code monitoring can also miss failures returned in an HTTP 200 body, so responses need semantic checks. Existing APM tools can carry custom spans and attributes, but the selection and policy data must be captured upstream. Observability records what happened; governance determines what is allowed. The excerpt recommends starting with denied and held calls, which are often absent from logs.

### Source excerpt

Span the decision, not just the request: what an observability setup needs to capture when the call it's tracing was chosen by a model, not a fixed code path.

## Grafana Labs leans on AI agents to automate AI agent observability

DevFeed: [Grafana Labs leans on AI agents to automate AI agent observability](<https://devfeed.tech/articles/grafana-labs-leans-on-ai-agents-to-automate-ai-agent-observability-90876.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/20/grafana-labs-leans-on-ai-agents-to-automate-ai-agent-observability/>)

Author: Mike Wheatley

Published: 2026-10-20T17:00:41Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Grafana Cloud](<https://devfeed.tech/topics/grafana-cloud.md>), [Grafana](<https://devfeed.tech/topics/grafana.md>), [digital experience monitoring](<https://devfeed.tech/topics/digital-experience-monitoring.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [adaptive-logs-archive](<https://devfeed.tech/tags/adaptive-logs-archive.md>), [adaptive-telemetry](<https://devfeed.tech/tags/adaptive-telemetry.md>), [agent-observability](<https://devfeed.tech/tags/agent-observability.md>), [ai-agent-observability](<https://devfeed.tech/tags/ai-agent-observability.md>), [ai-applications](<https://devfeed.tech/tags/ai-applications.md>), [ai-monitoring](<https://devfeed.tech/tags/ai-monitoring.md>), [ai-observability](<https://devfeed.tech/tags/ai-observability.md>), [ai-workloads](<https://devfeed.tech/tags/ai-workloads.md>), [assistant-watchers](<https://devfeed.tech/tags/assistant-watchers.md>), [autonomous-agents](<https://devfeed.tech/tags/autonomous-agents.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-agents](<https://devfeed.tech/tags/cloud-agents.md>), [grafana-assistant](<https://devfeed.tech/tags/grafana-assistant.md>), [grafana-cloud](<https://devfeed.tech/tags/grafana-cloud.md>), [grafana-cloud-agents](<https://devfeed.tech/tags/grafana-cloud-agents.md>), [grafana-cloud-logs](<https://devfeed.tech/tags/grafana-cloud-logs.md>), [grafana-labs](<https://devfeed.tech/tags/grafana-labs.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [news](<https://devfeed.tech/tags/news.md>), [observability](<https://devfeed.tech/tags/observability.md>), [observability-stack](<https://devfeed.tech/tags/observability-stack.md>), [observabilitycon](<https://devfeed.tech/tags/observabilitycon.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>)

### AI overview

Grafana Cloud is adding agents and telemetry features to monitor AI workloads and help investigate and remediate issues. Assistant Watchers are always-on agents that learn typical telemetry patterns and flag anomalies; Grafana Cloud Agents, available in preview, analyze code alongside production behavior and prepare fixes for human review. Grafana treats agent sessions and LLM conversations as telemetry alongside conventional logs, metrics, and traces. Other updates include Pages for custom AI workload visualizations; faster full-text search across low-frequency logs at no additional cost; Adaptive Logs Archive, which routes logs to customer object storage in open formats for lower-cost retention; and Knowledge Graph, linking infrastructure and application dependencies to user experience. Mobile Observability and Session Replay add a user perspective. The article presents these as a workflow for detection, diagnosis, and proposed action, with human review of fixes.

### Source excerpt

Observability software pioneer Grafana Labs Inc. is flexing its muscles in the rapidly emerging market for artificial intelligence monitoring tools with a swath of updates to its Grafana Cloud platform announced at ObservabilityCON 2026 today. The startup announced a new suite of AI agents, including Assistant Watchers for monitoring AI workloads and autonomous agents, and [...] The post Grafana Labs leans on AI agents to automate AI agent observability appeared first on SiliconANGLE.

## Grafana Applies SLOs and Error Budgets to AI Agent Behaviour

DevFeed: [Grafana Applies SLOs and Error Budgets to AI Agent Behaviour](<https://devfeed.tech/articles/grafana-applies-slos-and-error-budgets-to-ai-agent-behaviour-88462.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/10/grafana-slo-ai-agent/>)

Author: Craig Risi

Published: 2026-10-16T12:00:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>)

Tags: [agent-observability](<https://devfeed.tech/tags/agent-observability.md>), [agentic-ai-architecture](<https://devfeed.tech/tags/agentic-ai-architecture.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [ai-observability](<https://devfeed.tech/tags/ai-observability.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [devops](<https://devfeed.tech/tags/devops.md>), [grafana](<https://devfeed.tech/tags/grafana.md>), [grafana-slo-ai-agent](<https://devfeed.tech/tags/grafana-slo-ai-agent.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [news](<https://devfeed.tech/tags/news.md>), [observability](<https://devfeed.tech/tags/observability.md>), [reliability-engineering](<https://devfeed.tech/tags/reliability-engineering.md>), [slos](<https://devfeed.tech/tags/slos.md>)

### AI overview

Grafana Labs proposes applying service-level objectives and error budgets to measurable AI agent behaviors such as task fulfillment, groundedness, toxicity, and cost. Evaluations can turn these behaviors into indicators that teams monitor over time, helping reveal gradual quality drift and guide decisions about experimentation versus remediation. The approach depends on sound evaluation criteria and reliable evaluators, with datasets, deterministic checks, and human review helping address measurement limits.

### Source excerpt

Grafana Labs is proposing a familiar reliability engineering approach for one of the less familiar problems in modern software: how to measure whether an AI agent is actually behaving well. By Craig Risi

## Best API Observability Tools for Agent Traffic

DevFeed: [Best API Observability Tools for Agent Traffic](<https://devfeed.tech/articles/best-api-observability-tools-for-agent-traffic-90692.md>)

Original publisher: [Read original article](<https://www.swytchcode.com/content/best-api-observability-tools-agents>)

Author: Swytchcode Team

Published: 2026-10-16T05:20:00Z

Content type: comparison

Language: en

Sources: [Swytchcode](<https://devfeed.tech/sources/swytchcode.md>)

Topics: [API Logging](<https://devfeed.tech/topics/api-logging.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [observability](<https://devfeed.tech/topics/observability.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [api](<https://devfeed.tech/tags/api.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [observability](<https://devfeed.tech/tags/observability.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

This comparison explains how API monitoring and AI model tracing tools capture different parts of agent activity. HTTP traces show requests that were sent, while model traces can record tool choices; neither necessarily captures policy refusals made before a request. It recommends recording the tool choice, policy decision, and normalized provider result, with sensitive data redacted, and describes Swytchcode's local audit log as a complement to existing monitoring and tracing tools.

### Source excerpt

API observability shows the HTTP call. Agent traffic also has a tool choice and a set of calls that were refused before any request was sent. Most tools show one of those, not both.

## Taking a look under your agent's hood

DevFeed: [Taking a look under your agent's hood](<https://devfeed.tech/articles/taking-a-look-under-your-agent-s-hood-78705.md>)

Original publisher: [Read original article](<https://stackoverflow.blog/2026/10/09/taking-a-look-under-your-agent-s-hood/>)

Author: Phoebe Sajor

Published: 2026-10-09T07:40:00Z

Content type: article

Language: en

Sources: [Stack Overflow](<https://devfeed.tech/sources/stack-overflow-blog.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-security](<https://devfeed.tech/tags/ai-security.md>), [applying](<https://devfeed.tech/tags/applying.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [observability](<https://devfeed.tech/tags/observability.md>), [podcast](<https://devfeed.tech/tags/podcast.md>), [product](<https://devfeed.tech/tags/product.md>), [se-stackoverflow](<https://devfeed.tech/tags/se-stackoverflow.md>), [se-tech](<https://devfeed.tech/tags/se-tech.md>)

### AI overview

Ryan and Datadog Chief Product Officer Yanbing Li discuss applying observability to non-deterministic AI agents, the convergence of software development and production workflows, and emerging challenges in AI security and tokenomics.

### Source excerpt

Ryan is joined by Yanbing Li, Chief Product Officer at Datadog, to talk about applying observability to non-deterministic AI agents, blurring the boundaries between software development and production workflows, and navigating emerging challenges in AI security and tokenomics.

## OpenSearch veterans launch Infino. Here's why it matters for agent builders.

DevFeed: [OpenSearch veterans launch Infino. Here's why it matters for agent builders.](<https://devfeed.tech/articles/opensearch-veterans-launch-infino-here-s-why-it-matters-for-agent-builders-66603.md>)

Original publisher: [Read original article](<https://thenewstack.io/infino-agent-retrieval-layer/>)

Author: Adrian Bridgwater

Published: 2026-10-07T14:25:54Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [opensearch](<https://devfeed.tech/topics/opensearch.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [apache-parquet](<https://devfeed.tech/tags/apache-parquet.md>), [data](<https://devfeed.tech/tags/data.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>)

### AI overview

Infino has launched a retrieval platform that lets AI agents query structured and unstructured data through one interface, using a single copy stored in Parquet on object storage. The article describes how it combines search, filtering, joins, and aggregation, and reports Infino's claims about centralized access policies, reduced data infrastructure, and lower costs. It also notes that the core engine is open source, while some hosted-service features are proprietary.

### Source excerpt

Software vendors like to claim unified systems that act as a so-called single pane of glass for any given coding The post OpenSearch veterans launch Infino. Here's why it matters for agent builders. appeared first on The New Stack.

## Rossoctl for agent discoverability, security, and observability on Kubernetes

DevFeed: [Rossoctl for agent discoverability, security, and observability on Kubernetes](<https://devfeed.tech/articles/rossoctl-for-agent-discoverability-security-and-observability-on-kubernetes-65383.md>)

Original publisher: [Read original article](<https://developers.redhat.com/articles/2026/10/06/rossoctl-for-agent-discoverability-security-and-observability-on-kubernetes>)

Author: Shri Charan

Published: 2026-10-06T13:01:21Z

Content type: article

Language: en

Sources: [Red Hat](<https://devfeed.tech/sources/red-hat.md>), [Red Hat Developer](<https://devfeed.tech/sources/red-hat-developer.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [Plover](<https://devfeed.tech/topics/plover.md>)

Tags: [a2a-protocol](<https://devfeed.tech/tags/a2a-protocol.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentruntime](<https://devfeed.tech/tags/agentruntime.md>), [agents](<https://devfeed.tech/tags/agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [developer](<https://devfeed.tech/tags/developer.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [observability](<https://devfeed.tech/tags/observability.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

The article presents Rossoctl as a Kubernetes controller for discovering and managing AI agents across a cluster. It describes A2A AgentCards for publishing agent capabilities, a layered security approach using short-lived certificates, mTLS, signed cards, and scoped tokens, and MLflow tracing for agent decisions and tool calls. It notes that this architecture is most appropriate for multiple teams, cross-agent dependencies, or demanding compliance and debugging needs.

### Source excerpt

Imagine deploying a pair of agents to Red Hat OpenShift and watching them thrive. But fast-forward 6 months and you find your environment cluttered with 40 of them, their purposes largely unknown. Redundant agents emerge across namespaces, duplicating work. Meanwhile, a security review uncovers agents utilizing static API keys over insecure HTTP. When an agent falters, the lack of tracing makes it impossible to distinguish between model hallucinations, tool errors, or downstream failures. The post Rossoctl for agent discoverability, security, and observability on Kubernetes appeared first on Red Hat Developer.

## Updates to Conversations in Monte Carlo, a first-class unit for establishing agent trust

DevFeed: [Updates to Conversations in Monte Carlo, a first-class unit for establishing agent trust](<https://devfeed.tech/articles/updates-to-conversations-in-monte-carlo-a-first-class-unit-for-establishing-agent-trust-83148.md>)

Original publisher: [Read original article](<https://montecarlo.ai/blog-updates-to-conversations-in-monte-carlo>)

Author: Virna Sekuj

Published: 2026-09-30T13:00:00Z

Content type: release

Language: en

Sources: [Monte Carlo](<https://devfeed.tech/sources/monte-carlo.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [observability](<https://devfeed.tech/topics/observability.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>)

Tags: [agent-observability](<https://devfeed.tech/tags/agent-observability.md>), [agent-trust](<https://devfeed.tech/tags/agent-trust.md>), [alert](<https://devfeed.tech/tags/alert.md>), [observability](<https://devfeed.tech/tags/observability.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>), [user](<https://devfeed.tech/tags/user.md>)

### AI overview

Monte Carlo announces agent observability updates that make conversations a first-class unit alongside individual traces. The release adds conversation counts, end-user identity for Snowflake Cortex and Databricks Genie, and metric and evaluation monitors scoped or segmented by conversation cluster.

### Source excerpt

New in Agent Observability: conversation counts, end-user identity on platform agents, and monitors scoped to conversation clusters. Conversational agents don't run in isolation. An end user asks a question, the agent answers, and the person follows up. It's only clear if the answer succeeds or fails by examining the whole exchange. Most agent telemetry, however, ...

## Teaching a 9B model to investigate production alerts

DevFeed: [Teaching a 9B model to investigate production alerts](<https://devfeed.tech/articles/teaching-a-9b-model-to-investigate-production-alerts-58762.md>)

Original publisher: [Read original article](<https://www.datadoghq.com/blog/ai/investigate-production-alerts/>)

Author: Scott Kramer; Junaid Ahmed

Published: 2026-09-23T00:00:00Z

Content type: article

Language: en

Sources: [Datadog](<https://devfeed.tech/sources/datadog-the-monitor-blog.md>)

Topics: [incident](<https://devfeed.tech/topics/incident.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [LLM Techniques](<https://devfeed.tech/topics/llm-techniques.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Self-hosted](<https://devfeed.tech/topics/self-hosted.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [bits-ai](<https://devfeed.tech/tags/bits-ai.md>), [datadog](<https://devfeed.tech/tags/datadog.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [deployments](<https://devfeed.tech/tags/deployments.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [feature-flags](<https://devfeed.tech/tags/feature-flags.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [glm](<https://devfeed.tech/tags/glm.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [llm-serving](<https://devfeed.tech/tags/llm-serving.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [model](<https://devfeed.tech/tags/model.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [models](<https://devfeed.tech/tags/models.md>), [monitor](<https://devfeed.tech/tags/monitor.md>), [monitors](<https://devfeed.tech/tags/monitors.md>), [offer](<https://devfeed.tech/tags/offer.md>), [production](<https://devfeed.tech/tags/production.md>), [qwen3-5](<https://devfeed.tech/tags/qwen3-5.md>)

### AI overview

Datadog describes fine-tuning Qwen3.5-9B on investigation traces generated by GLM-5.3 to investigate production alerts and attribute them to recent changes. The specialized model achieved 87% of GLM-5.3's recall at substantially lower self-hosted serving cost, making higher-volume agentic investigations more practical.

### Source excerpt

Learn how we fine-tuned Qwen3.5-9B into a specialized agent for change attribution that achieved 87% of GLM-5.3's Recall@5 roughly 5% of the investigation cost.

## Introducing Amazon CloudWatch Omni: AI-powered observability for generative AI and agentic workloads

DevFeed: [Introducing Amazon CloudWatch Omni: AI-powered observability for generative AI and agentic workloads](<https://devfeed.tech/articles/introducing-amazon-cloudwatch-omni-ai-powered-observability-for-generative-ai-and-agentic-workloads-58213.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/aws/introducing-amazon-cloudwatch-omni-ai-powered-observability-for-generative-ai-and-agentic-workloads/>)

Author: Daniel Abib

Published: 2026-09-22T22:21:13Z

Content type: release

Language: en

Sources: [AWS News Blog](<https://devfeed.tech/sources/aws-news-blog.md>)

Topics: [Amazon CloudWatch](<https://devfeed.tech/topics/amazon-cloudwatch.md>), [observability](<https://devfeed.tech/topics/observability.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [ide](<https://devfeed.tech/topics/ide.md>), [Kiro](<https://devfeed.tech/topics/kiro.md>), [experiments](<https://devfeed.tech/topics/experiments.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>), [Single sign-on (SSO)](<https://devfeed.tech/topics/sso.md>)

Tags: [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [ide](<https://devfeed.tech/tags/ide.md>), [kiro](<https://devfeed.tech/tags/kiro.md>), [launch](<https://devfeed.tech/tags/launch.md>), [login](<https://devfeed.tech/tags/login.md>), [management-tools](<https://devfeed.tech/tags/management-tools.md>), [news](<https://devfeed.tech/tags/news.md>), [observability](<https://devfeed.tech/tags/observability.md>), [trace](<https://devfeed.tech/tags/trace.md>)

### AI overview

Amazon CloudWatch Omni is a unified observability, evaluation, and experimentation solution for generative AI and agentic workloads. It provides tracing, built-in quality evaluators, prompt comparison, test datasets, experiments, and regression detection through IDE extensions and a standalone web experience.

### Source excerpt

Learn how Amazon CloudWatch Omni delivers AI-powered observability purpose-built for generative AI and agentic workloads. Trace, evaluate, and experiment with AI agents across any framework--directly from your IDE or a standalone web experience--using open standards and built-in evaluators for quality, correctness, and coherence.

## Beacon Uses Jev to Extract Reusable Knowledge from AI Coding Agent Traces

DevFeed: [Beacon Uses Jev to Extract Reusable Knowledge from AI Coding Agent Traces](<https://devfeed.tech/articles/jev-clearly-explained-57588.md>)

Original publisher: [Read original article](<https://blog.dailydoseofds.com/p/jev-clearly-explained>)

Author: Avi Chawla

Published: 2026-09-21T19:39:16Z

Content type: article

Language: en

Sources: [Daily Dose of Data Science](<https://devfeed.tech/sources/daily-dose-of-data-science.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [coding](<https://devfeed.tech/tags/coding.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>)

### AI overview

The article explains how Beacon, an open-source telemetry and memory layer from Asymptote Labs, captures activity across multiple AI coding-agent harnesses. It uses Jev to evaluate agent traces, identify high-signal runs, and turn recurring workflows, corrections, and debugging patterns into reusable skills.

### Source excerpt

...with visuals.

## Cloudflare Proposes an Agent Development Lifecycle for AI-Driven Software Engineering

DevFeed: [Cloudflare Proposes an Agent Development Lifecycle for AI-Driven Software Engineering](<https://devfeed.tech/articles/cloudflare-introduces-the-agent-development-stack-lifecycle-to-replace-traditional-sdlc-57617.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/09/cloudflare-adlc-agents/>)

Author: Olimpiu Pop

Published: 2026-09-21T14:14:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Cloudflare](<https://devfeed.tech/topics/cloudflare.md>), [sdlc](<https://devfeed.tech/topics/sdlc.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [Orchestration](<https://devfeed.tech/topics/orchestration.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [observability](<https://devfeed.tech/topics/observability.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [Deployment](<https://devfeed.tech/topics/deployment.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [maintenance](<https://devfeed.tech/topics/maintenance.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [agentic-development-lifecycle](<https://devfeed.tech/tags/agentic-development-lifecycle.md>), [agents](<https://devfeed.tech/tags/agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [ci-cd](<https://devfeed.tech/tags/ci-cd.md>), [cloudflare](<https://devfeed.tech/tags/cloudflare.md>), [cloudflare-adlc-agents](<https://devfeed.tech/tags/cloudflare-adlc-agents.md>), [delivering-quality](<https://devfeed.tech/tags/delivering-quality.md>), [development](<https://devfeed.tech/tags/development.md>), [devops](<https://devfeed.tech/tags/devops.md>), [lifecycle](<https://devfeed.tech/tags/lifecycle.md>), [news](<https://devfeed.tech/tags/news.md>), [observability](<https://devfeed.tech/tags/observability.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [quality](<https://devfeed.tech/tags/quality.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

Cloudflare has introduced an Agent Development Lifecycle for AI-driven software engineering, proposing automated software factories and agent-managed testing, deployment, maintenance, and orchestration. Its approach includes Workflows-based CI/CD, preview deployments, dependency caching, autonomous remediation, and OpenTelemetry-compatible observability for model calls and tool executions.

### Source excerpt

Cloudflare has introduced the Agent Development Lifecycle to enhance AI-driven engineering. The approach replaces the traditional SDLC, addressing bottlenecks in testing, deployment, and maintenance. Key components include automated software factories, dynamic orchestration, advanced observability, and a security model for autonomous agents, aiming for more efficient software management. By Olimpiu Pop

## Your Feedback Becomes the AI Agent's Memory: How OrionIQ AI Agents Learn From You

DevFeed: [Your Feedback Becomes the AI Agent's Memory: How OrionIQ AI Agents Learn From You](<https://devfeed.tech/articles/your-feedback-becomes-the-ai-agent-s-memory-how-orioniq-ai-agents-learn-from-you-56870.md>)

Original publisher: [Read original article](<https://logz.io/blog/orioniq/your-feedback-becomes-the-agents-memory/>)

Author: David Lotan Bolotnikoff

Published: 2026-09-20T07:58:06Z

Content type: release

Language: en

Sources: [Logz](<https://devfeed.tech/sources/logz.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [observability](<https://devfeed.tech/topics/observability.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [blog](<https://devfeed.tech/tags/blog.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [logz-io-features](<https://devfeed.tech/tags/logz-io-features.md>), [memory](<https://devfeed.tech/tags/memory.md>), [observability](<https://devfeed.tech/tags/observability.md>), [orioniq](<https://devfeed.tech/tags/orioniq.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>)

### AI overview

OrionIQ AI agents in the Logz.io platform can use feedback on completed runs to create lessons for future runs. The feature applies across agent types, keeps lessons scoped to the relevant account and agent, and lets users control what the agent retains.

### Source excerpt

TL;DR: OrionIQ AI agents, available inside the logz.io platform, now learn from your feedback. Rate any agent run, thumbs up or thumbs down, say why, and the agent re-reads its own run, finds the decision behind the outcome, and writes a lesson. The next run of that agent in your account starts with the lesson [...]

## Datadog named the Company to Beat for observability platforms in 2026 Gartner® AI Vendor Race report

DevFeed: [Datadog named the Company to Beat for observability platforms in 2026 Gartner® AI Vendor Race report](<https://devfeed.tech/articles/datadog-named-the-company-to-beat-for-observability-platforms-in-2026-gartner-ai-vendor-race-report-17413.md>)

Original publisher: [Read original article](<https://www.datadoghq.com/blog/datadog-observability-platforms-gartner-ai-vendor-race-2026/>)

Author: Yanbing Li

Published: 2026-09-14T00:00:00Z

Content type: article

Language: en

Sources: [Datadog](<https://devfeed.tech/sources/datadog-the-monitor-blog.md>)

Topics: [observability](<https://devfeed.tech/topics/observability.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [incident](<https://devfeed.tech/topics/incident.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [observability pipelines](<https://devfeed.tech/topics/observability-pipelines.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [Security](<https://devfeed.tech/topics/security.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agent-observability](<https://devfeed.tech/tags/agent-observability.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [datadog](<https://devfeed.tech/tags/datadog.md>), [incident-response](<https://devfeed.tech/tags/incident-response.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [observability](<https://devfeed.tech/tags/observability.md>), [observability-pipelines](<https://devfeed.tech/tags/observability-pipelines.md>), [opentelemetry](<https://devfeed.tech/tags/opentelemetry.md>)

### AI overview

Datadog says it was named the Company to Beat for observability platforms in Gartner's August 2026 AI Vendor Race research and a Leader in the 2026 Gartner Magic Quadrant for Observability Platforms. The article presents Datadog's unified observability and security platform, including autonomous incident investigation, AI agent and LLM application observability, an MCP Server for querying telemetry, and Observability Pipelines with OpenTelemetry support.

### Source excerpt

Datadog has been recognized as the Company to Beat for observability platforms in the August 2026 Gartner® AI Vendor Race research.

## Knowledge Graph as context for LLMs: demonstrating decisive RCA and faster production performance

DevFeed: [Knowledge Graph as context for LLMs: demonstrating decisive RCA and faster production performance](<https://devfeed.tech/articles/knowledge-graph-as-context-for-llms-demonstrating-decisive-rca-and-faster-production-performance-8591.md>)

Original publisher: [Read original article](<https://grafana.com/blog/knowledge-graph-as-context-for-llms-demonstrating-decisive-rca-and-faster-production-performance/>)

Author: Sarah Constant

Published: 2026-09-12T11:22:06.456390Z

Content type: article

Language: en

Sources: [Grafana Labs](<https://devfeed.tech/sources/grafana-labs-blog-on-grafana-labs.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Grafana Cloud](<https://devfeed.tech/topics/grafana-cloud.md>), [debugging](<https://devfeed.tech/topics/debugging.md>), [incident](<https://devfeed.tech/topics/incident.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [grafana](<https://devfeed.tech/tags/grafana.md>), [grafana-cloud](<https://devfeed.tech/tags/grafana-cloud.md>), [incident](<https://devfeed.tech/tags/incident.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [llms](<https://devfeed.tech/tags/llms.md>), [logs](<https://devfeed.tech/tags/logs.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [observability](<https://devfeed.tech/tags/observability.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>), [traces](<https://devfeed.tech/tags/traces.md>)

### AI overview

The article reports Grafana Labs experiments testing whether providing AI agents with Grafana Cloud's Knowledge Graph improves incident debugging compared with raw telemetry alone. In one incident replayed 16 times per approach, Knowledge Graph context led to the correct root cause 15 times, versus once with raw telemetry. The article also describes challenges including misleading signals, unsupported confident answers, and inconsistent investigations, arguing that well-structured context matters more than context-window size alone.

### Source excerpt

On the product team here at Grafana Labs, we consider AI agents our users, too. That's why we set out to test how well agents can debug incidents across the full stack, and how much better they perform with Grafana Cloud's Knowledge Graph vs. using raw telemetry alone. Our early results are promising. In one real incident we replayed 16 times each way, an agent with Knowledge Graph context found the correct root cause 15 times, compared with just once using raw telemetry alone. Along the way, we also uncovered some of the challenges that still stand in the way of reliable AI-assisted debugging, from chasing the wrong signals to confidently making things up and producing inconsistent answers. We're still early, but our findings point to an important idea. The industry's shorthand right now is that a bigger context window will lead to better outputs. Our findings suggest it's not just about more context; it's about structuring your data well enough to serve the right context. Here's a look at what we've learned so far, as we continue to experiment out in the open and bring you along, the Grafana Labs way. Giving an agent access to telemetry is just the beginning Give a current-generation model like Opus 4.8 access to your raw telemetry during a live incident, and it genuinely starts to figure things out: querying metrics and logs, forming a hypothesis, and checking it. We have watched it work on our own incidents, and it does it affordably. But if you run software at scale, where uptime is business-critical and large teams share the responsibility, a better model alone doesn't get you all the way there for debugging. From analyzing how LLMs do root-cause analysis on our own infrastructure, and from speaking to our customers, we've uncovered three problems that get in the way: The further the cause is from the alert, the more likely the model is to get it wrong. An agent may confidently make things up when it doesn't have the evidence it needs. The same investigation c

## Agent Night demo recap: Brian Douglas's self-healing Pokémon agent

DevFeed: [Agent Night demo recap: Brian Douglas's self-healing Pokémon agent](<https://devfeed.tech/articles/agent-night-demo-recap-brian-douglas-s-self-healing-pokemon-agent-15985.md>)

Original publisher: [Read original article](<https://workos.com/blog/agent-night-bdougie-self-healing-pokemon-demo-recap>)

Author: WorkOS

Published: 2026-08-17T18:34:12Z

Content type: news

Language: en

Sources: [WorkOS](<https://devfeed.tech/sources/workos-blog.md>)

Topics: [Demo](<https://devfeed.tech/topics/demo.md>), [observability ai agents](<https://devfeed.tech/topics/observability-ai-agents.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Python](<https://devfeed.tech/topics/python.md>), [DuckDB](<https://devfeed.tech/topics/duckdb.md>), [Apache Kafka](<https://devfeed.tech/topics/apache-kafka.md>), [Code](<https://devfeed.tech/topics/code.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [demo](<https://devfeed.tech/tags/demo.md>), [duckdb](<https://devfeed.tech/tags/duckdb.md>), [kafka](<https://devfeed.tech/tags/kafka.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [python](<https://devfeed.tech/tags/python.md>), [self-healing](<https://devfeed.tech/tags/self-healing.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>), [traces](<https://devfeed.tech/tags/traces.md>)

### AI overview

A recap of Brian Douglas's Agent Night demo shows how Paper Compute ran Pokémon as a self-healing agent for six months. The setup uses Claude Code, a headless Python emulator, and traces from each session and turn. The article explains how labeled traces and per-session reflections can make the agent's history searchable and useful for improvement.

### Source excerpt

Brian Douglas of Paper Compute closed Agent Night with six months of running Pokémon as a self-healing agent: traces, anomalies, dreams, and inceptions.

[Next page](<https://devfeed.tech/topics/observability-ai-agents.md?cursor=WyIyMDI2LTA4LTE3VDE4OjM0OjEyKzAwOjAwIiwgIjE5ODM1NDFjLWI1NjktNDJiNi1iNjg5LTZhZWU0N2NjZTdmMSJd>)