Speaker Notes

Agent experience

Designing APIs, docs and products for agents as the user.

1talk
7answers
0mainly about it
1new
DecJanFebMarAprMayJunJulAugSepOctNov

What your library answers 7

Why do most traditional observability vendors fail to preserve OpenTelemetry benefits?

Most vendors accept OpenTelemetry data but immediately convert it into their own proprietary internal formats, destroying the original semantic tags and context. Dash Zero avoids this by keeping the data strictly in the OpenTelemetry format throughout the platform.

Thumbnail: Why Most Observability Platforms Won't Survive the AI Agent Era ▶ 6:31 Why Most Observability Platforms Won't Survive the AI Agent Era

How do large language models natively understand OpenTelemetry structures?

Because OpenTelemetry is an open-source and openly documented standard, AI models are trained on its text-based syntax and semantics by default. This allows models to parse spans, logs, and status codes directly without needing custom parsers.

Thumbnail: Why Most Observability Platforms Won't Survive the AI Agent Era ▶ 11:02 Why Most Observability Platforms Won't Survive the AI Agent Era

How can AI agents leverage custom analysis tools for large-scale data?

While individual traces can be dropped directly into models, large-scale anomaly detection requires exposing backend features like triage tools via Model Context Protocol servers. This lets autonomous AI agents query millions of data points and receive precise correlated results.

Thumbnail: Why Most Observability Platforms Won't Survive the AI Agent Era ▶ 15:27 Why Most Observability Platforms Won't Survive the AI Agent Era

Why are interactive observability workflows superior to static chat interfaces?

Static chat interfaces merely output a final answer or rigid artifact like an image, preventing further user manipulation. An interactive workflow allows developers to modify parameters, filter data, and continuously collaborate with the agent to refine troubleshooting results.

Thumbnail: Why Most Observability Platforms Won't Survive the AI Agent Era ▶ 22:27 Why Most Observability Platforms Won't Survive the AI Agent Era

Why is shifting toward agent-first features an existential issue for observability platforms?

If observability tools fail to provide value inside their own platforms, they risk being commoditized into mere databases. To survive, they must empower all users to troubleshoot via agents and integrate broader external context sources like Jira or Notion.

Thumbnail: Why Most Observability Platforms Won't Survive the AI Agent Era ▶ 26:25 Why Most Observability Platforms Won't Survive the AI Agent Era

How does designing observability products agent-first change the user interface?

Agent-first design shifts the primary interface away from traditional charts and numbers toward textual status descriptions and direct agent interaction. While charts were built for human visual weaknesses, agents perform deep data analysis directly on underlying data. Users now review agent summaries and investigate flagged anomalies instead of scanning raw dashboards.

Thumbnail: Why Most Observability Platforms Won't Survive the AI Agent Era ▶ 41:25 Why Most Observability Platforms Won't Survive the AI Agent Era

How do AI agents democratize troubleshooting for non-expert developers?

Troubleshooting complex microservice architectures traditionally requires expert knowledge held by only a few people in an organization. AI agents bridge this gap by possessing a wider system scope and guiding regular developers through the right troubleshooting steps. This reduces reliance on tribal knowledge when key experts leave the enterprise.

Thumbnail: Why Most Observability Platforms Won't Survive the AI Agent Era ▶ 46:34 Why Most Observability Platforms Won't Survive the AI Agent Era