Blog on Jettro Coenradie

Discovering Amazon Bedrock AgentCore through the CLI

Sun, 21 Jun 2026 08:00:00 +0000

This blog introduces Amazon Bedrock AgentCore through the AgentCore CLI. You’ll learn how to use AgentCore Memory and Observability, develop and test an agent locally, and deploy it to AWS.

Testing Agents Before They Test You: Voxxed Days Amsterdam

Fri, 01 May 2026 00:00:00 +0000

A reflection on presenting at Voxxed Days Amsterdam with Daniël Spee — covering AI agent evaluation using Spring AI, OpenAI, Dokimos, and Langfuse.

Embabel: Adding Guardrails to the Agent

Thu, 09 Apr 2026 00:00:00 +0000

Adding PII detection guardrails to an Embabel agent using Microsoft Presidio, with a ToolLoopTransformer for content transformation before LLM calls.

Reliable AI with Spring AI: Guardrails, Observability, and Evaluations

Wed, 01 Apr 2026 10:08:21 +0000

When building AI features with Spring AI, it is tempting to focus on prompts and model calls. That works for demos, but it quickly breaks down in real applications. You need to…

Evals for Spring AI Agents with Dokimos

Tue, 10 Mar 2026 20:03:42 +0000

Whisky barrels With Java entering the AI domain, I wanted to experiment with an evaluation framework for Agentic applications. I found Dokimos; it looked good, and I decided to…

Building AI agents safely: PII, jailbreaks, and real guardrails”

Sun, 22 Feb 2026 12:11:05 +0000

Guardrails to safe the day We’re building more and more AI agents that process real company data. That data often includes PII — email addresses, phone numbers, dates of birth, and…

Using the agent-browser skill with Spring AI

Thu, 12 Feb 2026 08:08:20 +0000

I did not jump on the skill wagon until recently. I think it is an interesting new way to teach your agent new ‘ skills ’. You wonder where the name comes from. If you are new to…

Agents that extract and use preferences from conversations.

Wed, 28 Jan 2026 19:51:10 +0000

In this blog, I experiment with Embabel Domain Injected Context Engineering (DICE). Dice can be used to manage extracted user preferences and use them to enrich your LLM context. I…

ChatBot with Embabel: A complete walkthrough

Thu, 15 Jan 2026 19:04:25 +0000

Before you think that AI Agents are all about chat, that is not my standpoint. Agents can be integrated into solutions like business processes, moderation, report generation, and…

Agentic RAG with Embabel: A complete walkthrough

Thu, 08 Jan 2026 00:09:42 +0000

For me, 2024 was the year of RAG, 2025 was the year of Agents. 2026 will be the year of Agentic RAG. This blog post explains why Agentic RAG differs from the 2024 version of RAG…

My 2025: Building agents, Writing, Speaking

Tue, 30 Dec 2025 17:01:18 +0000

My year in review It is that moment of the year when we reflect on the past year. You get a few emails about what you did in the past year. I am used to having an email from…

Short and long-term memory with Amazon Bedrock AgentCore and Spring AI

Tue, 23 Dec 2025 10:00:37 +0000

Short and long-term memory with Amazon Bedrock AgentCore and Spring AI In a previous post, you can read about the mechanics of integrating short-term and long-term memory into your…

Deep dive into AgentCore Memory using the Java SDK

Sun, 14 Dec 2025 17:13:54 +0000

Deep dive into AgentCore Memory using the Java SDK In a video from the Amazon Show & Tell series about Bedrock AgentCore Memory, a slide included this sentence. AI Agents are…

Spring Security 7 and Passkeys: A Practical Guide

Wed, 10 Dec 2025 09:50:45 +0000

In this blog, you’ll follow along as we create a Spring Boot application with Spring Security 7 that uses passkeys for authentication.

The Ladder and the Lanterns

Mon, 08 Dec 2025 18:44:34 +0000

A short story on tech panics: from writing to compilers to AI. Tools shift skills upward — if we keep understanding and judgment.

A practical walkthrough for parsing PDFs and chatting about their content

Fri, 28 Nov 2025 12:35:07 +0000

In this blog, we’ll build a small application that lets you parse PDFs into sections and tables, and then let you chat about the content.

Supercharge your MCP service with Embabel + human-in-the-loop

Wed, 29 Oct 2025 18:17:55 +0000

You are a developer with a task to create a service for AI Agents to order food and drinks on location. Model Context Protocol (MCP) is a…

Implement the Agentic Chaos pattern

Wed, 29 Oct 2025 09:44:03 +0000

describes the agentic chaos pattern also known as group-chat pattern. You find an explanation, a demo and a pointer to the code for the demo.

Spec‑driven development using Codex and Backlog.md

Mon, 20 Oct 2025 14:15:29 +0000

You can read about Spec‑driven development using Codex and Backlog.md. In this post we create the game connect four using these technologies.

The True Value of Public Speaking

Sun, 19 Oct 2025 10:47:31 +0000

It’s Sunday morning. I open my laptop, preparing slides for another talk and workshop. A week ago, I presented a session at Devoxx 2025…

My Devoxx 2025 Experience

Mon, 13 Oct 2025 11:53:18 +0000

A summary of the talks I attended at Devoxx 2025, including the workshop we have presented. All about Agents, Security and Java 25.

Creating and using an MCP server using Spring AI and Embabel

Mon, 01 Sep 2025 22:25:26 +0000

I wrote how to start writing an Agent on the JVM with Embabel in a previous blog post Building Agents with Embabel: A Hands-On…

Testing an Elastic Agent with an AI Agent (Warp + Claude)

Wed, 20 Aug 2025 13:06:50 +0000

In this post, I want to discuss using Generative AI to generate test scripts for an Elastic Agent configuration. I would not create these…

Building Agents with Embabel: A Hands‑On Introduction

Wed, 30 Jul 2025 08:47:54 +0000

This post gives you a hands on introduction into building agents with embabel. The sample is built using Java.

Strands, the new Agent framework supported by Amazon

Mon, 07 Jul 2025 13:48:05 +0000

If you’ve read my previous posts, you know I’ve been writing about Agents a lot. Every post is prepared with a demo using a new framework…

Secure Agents with Semantic Kernel, OAuth, and OpenAPI

Thu, 22 May 2025 17:38:15 +0000

Acting on your behalf — without exposing everything. Learn how to build trusted, secure agents that work across systems as your digital…

Create a multi-agent system with Amazon Bedrock

Sun, 04 May 2025 14:08:48 +0000

In this blog, you will read the details for creating a multi-agent system using Amazon Bedrock. It contains an example usecase with code.

Create a multi-agent system with OpenAI Agent SDK

Wed, 26 Mar 2025 17:02:01 +0000

This blog gives you a detailed example of a multi-agent system created using the OpenAI Agents SDK. Contains theoretical intro plus code.

Learn AI Agent basics using Python and Ollama

Mon, 17 Feb 2025 09:38:01 +0000

In this blog, you learn about the different AI Agent building blocks and how to implement them without big frameworks.

Listing Your Entitled Models in Amazon Bedrock

Fri, 31 Jan 2025 16:09:05 +0000

Until January 2025, there is no API to list the models you are entitled to. This blog explains creating this list of entitled models only

This was 2024 for me.

Thu, 26 Dec 2024 14:27:50 +0000

We are approaching the end of 2024 — a good moment to reflect on a year full of personal milestones and significant developments in the…

Mastering State in Stateless LLMs

Mon, 16 Dec 2024 12:36:11 +0000

Large Language Models (LLMs) are stateless by design. In this blog, you read about managing state for a stateless llm.

Elastic.ON Amsterdam 2024

Fri, 29 Nov 2024 09:56:26 +0000

This week, I attended Elastic.ON in Amsterdam. I still remember the first few Elastic events with just a few people, then going to San Francisco with many people. It has been a few years since I last visited Elastic.ON, so I liked going this year.

The Evolution of Creativity: Thriving in the Age of AI

Tue, 22 Oct 2024 08:36:57 +0000

Artificial Intelligence, in its quest to help us in our evolution of creativity invites us to reconsider: are we losing the essence of the creative journey, or can we find a way to thrive alongside this powerful new companion?

Build an Agent using Amazon Bedrock.

Fri, 20 Sep 2024 09:03:14 +0000

Blog describes the CDK and lambda code to deploy an Amazon Bedrock agent that writes data to DynamoDB with user interaction.

RAG: splitter chain for proper chunks

Thu, 08 Aug 2024 14:32:57 +0000

Describes a splitter chain including a semantic splitter to create the best chunks for you RAG based solution.

What? A Synonyms API for Elasticsearch?

Fri, 12 Jul 2024 15:41:27 +0000

In this blog post, I demo the synonym API from Elasticsearch, explain its limitations, and show you how cool it is now.

RAG optimisation: use an LLM to chunk your text semantically

Tue, 09 Jul 2024 13:10:40 +0000

In this post, you learn about more advanced chunking and embedding techniques like hierarchical chunking, and semantic chunking.

Automate customer interaction using OpenAI Assistants

Mon, 04 Mar 2024 15:46:12 +0000

LLM Assistants give your users a better interactive experience. Learn about using OpenAI assistants to improve your user’s experience.

GenAI, It’s Happening Now

Tue, 16 Jan 2024 09:54:35 +0000

A blog post about GenAI where you can read about how to apply it, the risks, and how to start with GenAI for your business.

Decoding Similarity Search with FAISS: A Practical Approach

Tue, 29 Aug 2023 06:58:00 +0000

In this blog post, you read about FAISS and your options for implementing similarity search using FAISS.

Searching through images using the CLIP model

Wed, 12 Jul 2023 04:41:30 +0000

A walktrough for writing an application that is searching through images using the clip model. An explanation of the model, plus python code.

Vector search using Langchain, Weaviate and OpenSearch

Tue, 30 May 2023 05:53:04 +0000

With the popularity of ChatGPT and Large Language Models (LLM), everybody is talking about it. On my Linkedin home page, about 90% of the posts seem to speak about ChatGPT, AI, and LLM. With my experience in search solutions and interest in everything related to Natural Language Processing and Search, I also had to start working on solutions.

Introduction of Frank and Amy at HaystackConf USA

Tue, 02 May 2023 10:42:36 +0000

Last week, at the end of April 2023, I attended the HaystackConf in Charlottesville, USA. HaystackConf is the conference to participate in if you are a search relevance engineer. With over a hundred people attending on-site and more than a hundred online, this is a good representation of the almost 4000 members at the time of writing in the search relevance community on Slack.

Learn Elasticsearch from my liveProject at Manning

Mon, 13 Feb 2023 08:54:09 +0000

Learn about the creation process for a Manning liveProject. The liveProject I created is called Elasticsearch for a search API.

Java with Lambda does not have to be slow

Mon, 29 Mar 2021 08:43:50 +0000

As a seasoned Java programmer, usually with Spring Boot, it hurts to learn that most lambdas use JavaScript/TypeScript. What if you want to keep writing your Lambda in Java? A query in google teaches us that Quarkus is the way to go. This blog post introduces Quarkus, GraalVM, and we top it off with AWS CDK to deploy the sample.

AWS Lambda here, there and everywhere

Thu, 25 Mar 2021 06:34:59 +0000

Everybody is talking about serverless, and with serverless comes serverless functions. Small pieces of code (in theory) that receive an event (input) and return a message (output). They do not need a server. Therefore they are serverless, and they scale on demand. On the AWS platform, a serverless function is called a Lambda. In theory, you write the code, and AWS takes care of the rest. There is a reason why I put “in theory” in some locations in the text. Even writing the hello world sample does need some authorization configuration, and when running complete Docker images as a lambda, you cannot talk about small pieces of code. Time to focus on typical usage patterns for lambdas.

Deploying a secure AWS Elasticsearch cluster using cdk

Wed, 03 Mar 2021 17:34:09 +0000

If there is one thing that I have seen a lot with elasticsearch clusters in the wild, it is problems with security. The out of the box Elasticsearch installation does not have a user_id password protection like most databases do. Using the basic license these days does give you the option, but you still have to configure it yourself. When AWS introduced their AWS Elasticsearch service, it did not configure security out of the box. Therefore Elasticsearch clusters have been famous for exposed data. Check an article like this, but there are lots more. Does this mean Elasticsearch should not be used? No, but you must know what you are doing.

Let’s talk about the Elastic license change

Fri, 12 Feb 2021 17:18:19 +0000

Is it a bomb under the open source model, or a genius move to protect their business from pirates?

On January 14, 2021 a blog post was published on Elastic’s website, titled: licensing change. In this blog post, they announced a license change in the next release of all their tools (including Elasticsearch and Kibana). The purpose of this change is mainly to block AWS: Elastic wants to make it impossible for AWS to create its own competing managed Elasticsearch service. The announced changes were not very well received in the open source world. In this blog post I tried to give an overview of what happened, and what the consequences are for companies that use Elasticsearch and Kibana. Just a disclaimer, I am not a lawyer. Hence I will not go into the content of the new license model. The aim of this post is mainly to provide an overview of varying opinions on the internet and the possible consequences for users.

Tip for Configuring Oh My Z Shell

Fri, 04 Jan 2019 00:00:00 +0000

A quick tip on how to extend oh-my-zsh using custom shell scripts to switch JDKs or modify your PATH.

Creating an Elastic Canvas for Twitter while visiting Elasticon 2018

Wed, 14 Mar 2018 15:40:08 +0000

The past week we visited Elasticon 2018 in San Francisco. In our previous blog post we wrote about the Keynote and some of the more interesting new features of the elastic stack. In this blog post, we take one of the cool new products for a spin: Canvas. But what is Canvas?

AngularJS directives for C3.js chart library

Tue, 19 Aug 2014 09:00:09 +0000

For one of our projects we wanted to create some nice charts. Feels like something you often want but do not do because it takes to much time. This time we really needed it. I had prior experience with Highcharts, which is also a nice library. But this time we wanted more control. We had […]

Creating an advanced Kibana dashboard using a script

Tue, 20 May 2014 11:21:24 +0000

Discover how to create an advanced dashboard using a script. These days Kibana is becoming more advanced. But with more users also come more demands.

Evaluating elasticsearch and marvel on the raspberry pi

Sat, 08 Feb 2014 19:29:40 +0000

The past years I have been working with search solutions, mostly elasticsearch. During this time a bought myself a raspberry pi and installed java and elasticsearch on it. Then I put it in the closet and it did not come out anymore. Than a few weeks a go the guys from elasticsearch released marvel. Marvel […]

Use Kibana to analyze your images

Thu, 28 Nov 2013 11:06:20 +0000

If you are reading some technical blogs, maybe about search or data analysis, chances are big you have read about Kibana. You have seen stories about how easy it is to use. Most of the blogging effort deals with getting data into kibana using logstash for instance. Maybe some of you have installed Kibana […]

Improved search for Hippo CMS websites using ElasticSearch

Tue, 30 Jul 2013 08:00:42 +0000

We have done multiple big Hippo projects. A regular Hippo project consists of multiple components like the website, the content management system and a repository for the documents. In most of the projects we also introduce the integration component. This component is used to pull other data sources into Hippo, but we also use it […]

Introducing a Query tool as an Elasticsearch plugin (part 2)

Wed, 20 Mar 2013 08:30:55 +0000

In the first part of this series of blogs on Introducing a Query as an Elasticsearch plugin, I described the functionality of a query tool I also discussed the functionality of the tool as the structure of the project. In this part I want to take a deeper dive in interacting with Elasticsearch. The post […]

AngularJS: Lessons learned

Thu, 14 Mar 2013 14:32:05 +0000

At Devoxx 2012 I attended the AngularJS presentation by Igor Minar and Misko Hevery. I was very enthusiastic about the capabilities of this front-end framework. Therefore I started experimenting with it. I created a sample for the Axon Framework, read more about it here. After my experiments I felt confident enough to start using it […]

Introducing a Query tool as an Elasticsearch plugin (part 1)

Tue, 12 Mar 2013 08:14:45 +0000

In the past few weeks I have been working with Elasticsearch. I was missing a plugin to look at the data, create queries and evaluate different facets. That was when I decided to start working on a plugin that enables you to do just this. I have been working on AngularJS together with Twitter Bootstrap, […]

Basic Axon Framework sample using vert.x and angular.js

Tue, 27 Nov 2012 09:20:17 +0000

Some people on the Axon Framework mailing list were asking for more basic samples, preferably using something like vert.x. Since I am familiar with Axon as well as vert.x I thought I could help out. Therefore I have created a very basic application based on vert.x using the Axon Framework. The application is all about […]

And that was Devoxx 2012, partnering with 10gen and a lot of knowledge gaining

Sat, 17 Nov 2012 11:44:04 +0000

Last week a couple of my colleagues and I were in Antwerp visiting the Devoxx conference. In this blog post we try to give you an idea about what we did & learned: The sessions I attended a lot of sessions, if you want to know more I urge you to read on. I briefly discuss […]

Authenticate against a hippo repository using spring security

Tue, 17 Jul 2012 08:00:58 +0000

Within a number of my projects we use Hippo to create a website. Hippo contains a JackRabbit repository that has capabilities for authenticating and authorizing users. Hippo builds on this functionality for its own security model. In most of these projects we create an integration component to store content in the repository from other systems […]

Basic Health check library for your application

Thu, 19 Apr 2012 08:28:29 +0000

For a few years now I have been running multiple Hippo projects. All the projects use multiple servers and services. The biggest one has over 15 servers in production. A standard hippo solution consists of site servers and cms servers. We also had some other servers for things like rss and integration. The complete landscape […]

Using the spring-data project and the mongodb adapter specifically

Thu, 29 Mar 2012 14:40:49 +0000

In this blog post I want to share some of my experiences with the spring-data project. At Orange11 we have been working on a sample for the Axon Framework. We have created the Axon Trader. For the trader we use the MongoDB based event store. Therefore I also wanted to store the data for the […]

Running Hippo CMS from Intellij

Fri, 03 Feb 2012 14:37:03 +0000

For a number of years we are doing hippo development using our beloved tool “Intellij”. We can import the project using the pom. Deploying from within Intellij was done using the maven provided jetty integration to run the cms. Then we would run the site in another tomcat or as well from maven with jetty. […]

Embedding RSS in Hippo using the pipelines feature

Tue, 13 Dec 2011 14:41:44 +0000

For one of the biggest Hippo projects I have been working on, we have created a custom rss solution. When we started the project, Hippo did not have an rss solution and we had some requirements for caching and reusability that we could not implement with standard hippo. A few years have passed and hippo […]

Gather content for Lucene from WordPress using Groovy

Tue, 16 Aug 2011 06:43:03 +0000

I am learning about the capabilities of Lucene. Here at JTeam we have a few people that are specialized in Search using technology like Lucene and Solr. Therefore I want to have a higher level of knowledge of Lucene than I have now. So I started reading the Lucene in Action book. As I read […]

Cleaning up your maven repository

Mon, 01 Aug 2011 08:13:45 +0000

A few days a go I was looking at a warning that my disk was getting to full. I just upgraded to apple osx lion. There were a few things that were related to the upgrade, but another large directory was the maven repository directory. The easy way out is to just remove everything, but […]

Combining java and node.js

Thu, 28 Jul 2011 10:27:43 +0000

I just wrote a new blogpost about a sample application I have created. The sample is combining a node.js front-end application with a axonframework java based backend. The following image gives you a good idea. The front end contains a node.js application that uses the http library to obtain and send data a rest based […]

The new axon incubator and the google app engine project

Wed, 06 Jul 2011 14:08:38 +0000

Some time ago we started adding modules or classes to axon that were not really the core of the system. The most important one of them is a MongoDB based event store. The amount of testing of this module was not as high as the other parts. It has not yet been tested in a […]

Learning Node.js

Mon, 18 Apr 2011 09:44:20 +0000

For projects and for some experiments I want to get a better way to do server push. With the new HTML 5 becoming the standard and therefore WebSockets becoming available in all mayor browsers, it seems that WebSockets is the way forward. A very nice implementation of WebSockets that is backwards compatible with older browsers […]

Using Spring social to connect your online profiles

Tue, 15 Mar 2011 20:27:21 +0000

Some time a go I wrote an item on my personal blog about a sample that I created with the spring social project. I explained how to connect to linkedin. In this blog post I want to go one step further. I want to create an application that a user need to log in to. […]

Using the Spring RESTTemplate with Jackson

Thu, 27 Jan 2011 13:46:12 +0000

About a week a go I wrote a blog post on gridshore about the NOS open data API. Most of the technical items are explained in that post. In this post I want to tell you about the small library I have created around the NOS open data REST based API. With this client it […]

Deploying a CQRS application based on the Axon framework on Google App Engine

Tue, 04 Jan 2011 08:30:19 +0000

The Axon framework is a CQRS framework created by Allard Buijze. From the beginning I am trying to help him out, mostly by creating samples. This blog post is about a sample I am creating for Google App Engine. Everybody that has been working with Google App Engine (GAE) knows that it enforces some limitations […]

Monitoring Hippo Connection pool using JMX and Groovy

Thu, 19 Aug 2010 10:10:32 +0000

For a project we are using Hippo to manage our content. We have a few components that interact with the repository using the connection pool as provided by hippo. I have modified the connection pool to increase the amount of logs and I have added statistics to the pool which can be exposed using JMX. […]

Logging to the syslog from a java application

Thu, 14 Jan 2010 16:16:42 +0000

Every application needs logging, it can help you during development and when debugging those annoying things that do not work in production. One question is where to put the logging events. All linux servers use a system log to log events that take place on the operating system level. You can find logs for the kernel, […]

Using ehcache monitor

Tue, 22 Dec 2009 10:50:58 +0000

In my previous blog post serving a heavy load rss feed with spring 3 and ehcache I showed a solution for rss and caching using ehcache. After posting, Alex Miller commented about using a new product from ehcache called ehcache monitor. As curious as I am I decided to have a look. In this blog […]

Serving a heavy load rss feed with Spring 3 and EHCache

Thu, 17 Dec 2009 14:50:13 +0000

For a project I am doing there was a feature request to come up with an rss component for their new website. This seems pretty easy but the amount of possible feeds (100.000) and the potential for very high load made us think about a custom made solution based on ehcache, spring 3 and rome. […]

Using GIT coming from subversion

Thu, 12 Nov 2009 12:56:47 +0000

A while a go I upgraded to subversion 1.6. That was the moment I started to have more and more problems with subversion. The past years I was a strong advocate of subversion, but now I am having a hard time defending the usage of subversion. I got interested in GIT. About a month a […]

Second meetup DDDNL usergroup

Thu, 01 Oct 2009 16:16:41 +0000

Is has been more than a month a go that we had our first meeting, it is shorter than a month before we have the second event. The next event will take place on the 27th of october. The second event will be held at JTeam office in Amsterdam. The program for the event will […]

DDD and modern software development

Tue, 08 Sep 2009 15:07:09 +0000

One of the main things we do @ jteam is creating rock solid custom development. Of course we use proven frameworks, we keep innovating and we use a lot of the best practices for custom software development. Best practices I am talking about are: Continuous Integration, Test Driven Development, Peer reviews and of course Scrum. […]

A perspective on content management

Tue, 19 May 2009 21:04:50 +0000

For more than a year I am working with the Hippo CMS. I started with hippo 6. For the project OnsOranje, I created a springframework layer on top of hippo. This layer enabled us to create a website using the techniques we are familiar with (spring mvc). After the onsoranje project, my interest for content […]