Anthony Alaribe
APItoolkit: Using Merkle Trees and LLMs to Detect the UnDetectable in Software Monitoring
#1about 1 minute
The high cost of undetected breaking changes
A real-world example from Delivery Hero shows how a minor migration error with missing fields resulted in a $2 million loss.
#2about 1 minute
Why incident response is slowed by information overload
When systems break, teams are swamped with too many logs, metrics, and messages, making it difficult for humans to diagnose the root cause quickly.
#3about 1 minute
Using Merkle trees and LLMs to detect anomalies
Merkle trees condense millions of logs into unique signatures to identify new patterns, while LLMs analyze these changes to determine if they are critical or breaking.
#4about 1 minute
An observability platform with conversational AI
APIToolkit is an observability platform that analyzes requests, logs, and traces in real-time to provide context and allow conversational debugging.
Related jobs
Jobs that call for the skills explored in this talk.
Matching moments
24:09 MIN
Supercharging observability with AI analytics
Navigating the AI Wave in DevOps
23:26 MIN
Use developer observability for safe production debugging
Talk to the Duck - Secrets of the Debugging Masters
00:48 MIN
The growing need for observability in complex applications
Observability with OpenTelemetry & Elastic
18:26 MIN
Detecting protestware and other malicious behaviors
Coffee with Developers with Feross Aboukhadijeh of Socket about the xz backdoor
21:49 MIN
Exploring the future of automated security analysis
Reviewing 3rd party library security easily using OpenSSF Scorecard
09:02 MIN
Discovering incidents through system observability
Handling incidents collaboratively is like solving a rubix cube
00:06 MIN
An overview of an AI-powered code reviewer
How we built an AI-powered code reviewer in 80 hours
37:57 MIN
Q&A on AI adoption, tools, and challenges
Navigating the AI Wave in DevOps
Featured Partners
Related Videos
08:27Get security done: streamlining application security with Aikido
Mia Neethling
29:38Answering the Million Dollar Question: Why did I Break Production?
Luís Ventura
27:39Mastering AI-Driven Problem Solving in Engineering with Observability
Jemiah Sius
23:47Lessons learned from observing a billion API requests
Pratim Bhosale
30:29Observability with OpenTelemetry & Elastic
Iulia Feroli
23:24Prompt Injection, Poisoning & More: The Dark Side of LLMs
Keno Dreßel
29:18Getting to Know Your Legacy (System) with AI-Driven Software Archeology
Markus Harrer
25:32Practical AI with Machine Learning for Observability in Netdata
Costa
From learning to earning
Jobs that call for the skills explored in this talk.
Application Security Engineer
Palantirians
Charing Cross, United Kingdom
Remote
Go
Java
Python
JavaScript
+1
PhD position (start: early 2026): Tool-Augmented LLMs for Enterprise Data AI
ailylabs
Barcelona, Spain
Python
Observability Architect (Dynatrace)
Kyndryl
Municipality of Madrid, Spain
Bash
DevOps
Python
Splunk
Grafana
+4
{"@context":"https://schema.org/","@type":"JobPosting","title":"Software Engineer 2 - Full-Stack - Behavioral Security Products
Abnormal AI
Intermediate
API
Spark
Kafka
Python
Site Reliability Engineer, Observability, London
Apple Inc.
Charing Cross, United Kingdom
Java
Linux
Python