GitNation
Log in
Upcoming Tech Conferences
AI Coding Summit NYCAI Coding Summit NYC

Your Agent Returned 200. Was It Right?

Nathan Marrs
Nathan Marrs
Grafana Labs
This talk is confirmed. The time of the talk will be announced soon.
The recording will be published after editing. Multipass and Full ticket holders have early access.
Get Multipass
Bookmark
Rate this content
Sentry
Promoted
Code breaks, fix it faster

Crashes, slowdowns, regressions in prod. Seer by Sentry unifies traces, replays, errors, profiles to find root causes fast.

Get started

AI agents can be fast, available, and still completely wrong. Standard application monitoring can show latency and errors, but not whether an answer was useful, a tool call behaved correctly, or a prompt change introduced a regression. This talk shows how to instrument, trace, and evaluate production AI agents using OpenTelemetry and AI Observability. 

This talk has been presented at AI Coding Summit NYC, check out the latest edition of this Tech Conference.

observability
Nathan Marrs
Nathan Marrs
Video transcription, chapters and summary will be available later.

Check out more articles and videos

We constantly think of articles and videos that might spark Git people interest / skill us up or help building a stellar career

Multithreaded Logging with Pino
JSNation Live 2021JSNation Live 2021
19 min
Multithreaded Logging with Pino
Top Content
Matteo Collina
Matteo Collina
Node.js TSC committee member. Pino & Fastify author.
Today's Talk is about logging with Pino, one of the fastest loggers for Node.js. Pino's speed and performance are achieved by avoiding expensive logging and optimizing event loop processing. It offers advanced features like async mode and distributed logging. The use of Worker Threads and Threadstream allows for efficient data processing. Pino.Transport enables log processing in a worker thread with various options for log destinations. The Talk concludes with a demonstration of logging output and an invitation to reach out for job opportunities.
node.jsobservability
Observability with diagnostics_channel and AsyncLocalStorage
Node Congress 2023Node Congress 2023
21 min
Observability with diagnostics_channel and AsyncLocalStorage
Top Content
Stephen Belanger
Stephen Belanger
Node.js core contributor and founder of the diagnostics working group.
Observability with Diagnostics Channel and async local storage allows for high-performance event tracking and propagation of values through calls, callbacks, and promise continuations. Tracing involves five events and separate channels for each event, capturing errors and return values. The span object in async local storage stores data about the current execution and is reported to the tracer when the end is triggered.
observabilitymachine learning
How Grafana Uses React to Power the World of Observability
React Summit 2023React Summit 2023
7 min
How Grafana Uses React to Power the World of Observability
Top Content
Nathan Marrs
Nathan Marrs
Grafana Labs
Grafana uses React to power its open source platform, leveraging its vast ecosystem, improved performance, and community contributions. The choice of state management tool depends on the team's problem space. React Hooks have posed challenges but have also been a powerful tool for developers. The new Scenes library simplifies development and reduces the learning curve. Despite challenges, React remains a powerful tool for complex frontends, and Grafana will continue to use it.
case studyobservabilityerror monitoringgrafana reactjsopentelemetry react
Observability for Microfrontends
DevOps.js Conf 2022DevOps.js Conf 2022
31 min
Observability for Microfrontends
Premium
Konstantinos Leimonis
Konstantinos Leimonis
monday.com
Microfrontends follow the microservices paradigm and observability is crucial for debugging runtime production issues. Error boundaries and tracking errors help identify and resolve issues. Automation of alerts improves incident response. Observability can help minimize the time it takes to understand and resolve production issues. Catching errors from the client and implementing boundaries can be done with tools like OpenTelemetry.
devopsmicro-frontendsobservability
GraphQL Observability
GraphQL Galaxy 2020GraphQL Galaxy 2020
8 min
GraphQL Observability
Ashley Narcisse
Ashley Narcisse
Apollo
This Talk discusses how to tool Apollo server with open tracing for observability. OpenTracing is a vendor-agnostic format that works well with distributed systems in microservices. It allows for converting GraphQL tracing data to a vendor-agnostic format and enriching information from GraphQL servers. If providers support OpenTracing, it can be easily integrated.
graphqlobservability
Creating an innovation engine with observability
Node Congress 2023Node Congress 2023
27 min
Creating an innovation engine with observability
Boris Tane
Boris Tane
Boris is the founder of Baselime.
Baseline provides observability for serverless architectures and has created an innovation engine within their team. They measure team performance using Dora metrics and the Accelerate book. Baseline emphasizes the importance of foundations, streamlined testing, and fast deployment. They practice observability-driven development and incorporate observability as part of their development lifecycle. Baseline believes in building a culture that fosters ownership and democratizes production.
node.jsobservability

Workshops on related topic

Scaling Databases For Global Serverless Applications
Node Congress 2022Node Congress 2022
83 min
Scaling Databases For Global Serverless Applications
Workshop
Ben Hagan
Ben Hagan
This workshop discusses the challenges Enterprises are facing when scaling the data tier to support multi-region deployments and serverless environments. Serverless edge functions and lightweight container orchestration enables applications and business logic to be easily deployed globally, often leaving the database as the latency and scaling bottleneck.
Join us to understand how PolyScale.ai solves these scaling challenges intelligently caching database data at the edge, without sacrificing transactionality or consistency. Get hands on with PolyScale for implementation, query observability and global latency testing with edge functions.
Table of contents- Introduction to PolyScale.ai- Enterprise Data Gravity- Why data scaling is hard- Options for Scaling the data tier- Database Observability- Cache Management AI- Hands on with PolyScale.ai
node.jsobservabilityserverlessenterprise