OTel

Agents Are Where Microservices Were in 2015 — Roberto Milev & Uday Kanagala, Navan

Aug 29, 2026 · 19:28

Roberto Milev, chief architect at Navan, and Uday Kanagala argue agents are where microservices were in 2015: master a single agentic loop before multi-agent orchestration. At Navan, agentic workflows run on AWS AgentCore with custom session persistence, composing context from skills as pluggable units. Traditional logs fail when agents emit too much thinking, so Navan uses pre/post-tool hooks to emit goals, reasoning, belief status, and confidence scores into BrainTrust traces, routing inferred answers to humans. Testing is nondeterministic, scored by trajectory evals; cost, replay, and standards remain unsolved. Guardrails run before and after every tool call because 'book a flight whenever it's under $200' blurs who authorized the purchase.

LLM Observability, Evaluation, Experimentation Platform — Dat Ngo, Arize

Jun 7, 2026 · 16:32

Dat Ngo from Arize AI explains that observability and evaluation are essential for debugging nondeterministic LLM agents, where code no longer audits behavior—telemetry does. He outlines five flavors of eval signal—LLM as judge, human feedback, golden datasets, deterministic checks, and business metrics—and describes running them at different scopes: single span, multispan, trajectory, and session. Arize’s open-source Phoenix runs as a single container without Kubernetes, while the enterprise Arize AX adds Alex, an AI that scans traces for latency and errors and creates evals automatically. The goal is to automate the entire observability loop, letting developers focus on improvement rather than manual monitoring.

Everything You Need To Know About Agent Observability — Danny Gollapalli & Zubin Koticha, Raindrop

May 7, 2026 · 50:25

Zubin Koticha and Danny Gollapalli of Raindrop argue that agent observability must shift from evals to production monitoring because agent failures are non-deterministic and unbounded. They break down explicit signals (tool error rate, latency, cost) and implicit signals (user frustration, refusals, task failure) detected by trained classifiers and regex, emphasizing that aggregate patterns even from imperfect regex are valuable. Experiments let teams ship changes to a percentage of users and compare semantic signal rates, with statistical relevance often reached after a few hundred events. Self-diagnostics—a simple tool and system prompt—enable agents to report their own failures, capability gaps, and even self-correction behavior, as demonstrated in a live coding agent demo where a disabled write tool caused the agent to use bash and then report the bypass. The episode covers alerting, trace visualization, data export to BigQuery/Snowflake, and the challenge of managing fast-paced experimentation at scale.

Conquering Agent Chaos — Rick Blalock, Agentuity

Jul 1, 2025 · 14:40

Rick Blalock, founder of Agentuity, argues that deploying AI agents remains the number one headache for developers, citing common issues like serverless timeouts (agents running 15–30 minutes), statelessness, and networking complexities. He demonstrates Agentuity’s platform, which treats agents as first-class infrastructure citizens: users scaffold projects via a CLI (supporting Bun, Python/UV, Node.js), write a simple request handler, and deploy with automatic routing, tunneling, and a built-in AI gateway that tracks costs per run. The platform decouples inputs and outputs—agents can be triggered via email, SMS, webhooks, or cron—and provides human and agent-facing telemetry via OTel tracing. Blalock notes Agentuity already hosts 50–60 internal agents and is building infrastructure agents to replace tools like PagerDuty, with plans to add Slack/Discord integrations and service-level reasoning capabilities.

How to build world-class AI products — Sarah Sachs (AI lead @ Notion) & Carlos Esteban (Braintrust)

Jun 27, 2025 · 1:43:46

Sarah Sachs (AI lead at Notion) and Carlos Esteban (Braintrust) explain that building great AI products requires 10% prompting and 90% evals and observability, with Notion AI using Braintrust to iterate on prompts and models. Sachs details their cycle: curate small datasets, tie them to scoring functions (LLM-as-a-judge with per-sample prompts and heuristic checks), run evals before shipping, and use production logs to catch regressions. She notes Notion AI supports 100M+ users, switches models in under a day, and 60% of enterprise users are non-English—requiring multilingual eval rigor. Carlos and Doug then walk through Braintrust's framework: tasks (prompts, tools, agents), datasets, and scores (0-1). They demonstrate offline evals via playground and SDK, online scoring in production, user feedback capture, human review setup, and remote evals to bridge complex code with the playground. The workshop covers moving from pre-prod evals to production monitoring, closing the feedback loop by adding underperforming spans to datasets.

Building LinkedIn's GenAI Platform — Xiaofeng Wang

Apr 16, 2025 · 17:53

Xiaofeng Wang, manager of LinkedIn's GenAI Foundation, explains the evolution of LinkedIn's GenAI platform from simple prompt-in string-out applications to a multi-agent system for LinkedIn Hire Assistant, arguing that a unified platform is critical for bridging the gap between AI and product engineers in the era of compound AI systems. He details the platform's four-layer architecture—orchestration, prompt engineering, tools/skills invocation, and memory management—and key investments like a Python SDK, centralized skill registry, experiential memory across working, long-term, and collective layers, and observability built on OpenTelemetry. Wang discusses hiring philosophy: prioritize strong software engineers over AI expertise, hire for potential, and build diverse teams integrating full-stack engineers, data scientists, and AI engineers. He recommends solving immediate needs first, leveraging existing scalable infrastructure like messaging systems for memory, and focusing on developer experience to drive adoption.