DEV Community: Ricardo Sueiras

Build without limits - SDLC Briefing, #5

Ricardo Sueiras — Mon, 09 Nov 2026 07:50:15 +0000

Hi! I am Ricardo Sueiras, leading SDLC transformation at Indicium AI. That means I get to work with customers and help them understand how to use agentic AI to build software. New tools, practices and opinions turn up every week, and Build without Limits cuts through the noise. In each edition we put together a short, curated briefing on what's worth reading, watching and worth trying. You can skim it in five minutes and dive deeper wherever something catches your eye.

Top of Mind

Top of mind this week is Developer Portals (sometimes referred to as IdP's, although as someone who has spent time building identity systems, I always get the hump that this TLA has been usurped!). I had several good discussions with customers, who are looking at leveraging their developer portals to include gold paths for agentic solutions.

One of the surprising things that has come up in these conversations is how to rethink those same developer portals for a new kind of developer. Citizen Developer specifically, and how platform teams are now beginning to rethink what the design and user experience looks like for this new kind of user. Hannah Foxwell added to this discussion in her post on LinkedIn by adding that it was not just Citizen developer we needed to think of but agents more broadly. This makes sense to me, one place in which to manage and govern everything. I am folllowing this closely, and will share what I find.

Must reads this week

These were my favorite posts this week.

Amazon rewrites its software engineering playbook for an era when AI writes the code - took me by surprise last week, with Marc Brooker sharing some of the lessons Amazon has learned across their engineering teams and how this is changing how they approach development.

https://github.com/adimango/ai-adoption-playbook - provides an opinionated guide on how you might roll out AI across your organisation. I haven't tried it yet, and I have my reservations on how this might work as in my experience, how you roll out and enable an organisation for AI varies hugely and is based on lots of factors. That said, they have done a lot of work pulling together useful tools that will help you with the planning activities.

Recap from GitHub universe- if you want a summary of the main things that went down at Github's annual tech conference, I found this post provided a good summary. I also listened to the Syntax podcast as well. There have been lots of stories about Github's future as it tries to cope with the sheer scale of the impact of agentic engineering. Inside GitHub’s new Git storage architecture looks at how they are innovating their storage architecture to cope.

Scaling software built with AI: where the real bottlenecks are - a long read that covers a lot of ground, looking at the current state of agentic development. Whilst there is nothing new or groundbreaking in this post, its ways its all brought together makes it a good read.

Watch this

Last week I listened to this episode of the Engineering Enablement podcast from the folks at DX, where Roblox's Andrew Swerdlow dived into how they approach code review across their engineering teams and how they measure the impact of agentic engineering. This one is packed with some great approaches that I will be adding to my toolbox.

Tools to try out

Third-party tools links are provided as-is. They belong to their owners, follow their own licenses, and are used at your own risk.

https://github.com/shanselman/sandbox-mcp - this was news to me, that Windows had a capability for creating sandbox environments that you can use to launch your agents in. None other than Microsofts Scott Hanselman has put together an MCP that gives your agent everything you need to get started. Many of the developers I work with use Windows, so this is a great tip.

https://github.com/govijr/terminal-mac - if you like the Windows sandbox tool above, then this tool provides a separate desktop for your computer use agents. The guest is a separate Mac: it has its own apps, files, accounts and permissions. Nice detailed docs, and this tool already has 2.5K stars.

https://github.com/richardedens/crissp - is another AI SLDC framework that has three layers (agent colleagues that build, guards that make sure it is built correctly , and then product which defines what gets built). Not had time to try it out, but I like to check the repos out and get inspired or borrow ideas from them.

From the field

Developer experience is increasingly surfacing in the work I do with customers, which should perhaps be no surprise for folk who are working at helping organisations adopt agentic engineering. Recently it has come up in the topic of quality, and how a good developer experience correlates to higher quality software. We knew this of course, and Accelerate and DORA provided the data to back this up, but as you start to think about your own agentic engineering roll outs and SDLC modernisation, make sure you put developer experience at the centre.

One of the ways I see developer experience manifest at a practical level is how they are setup for agentic development. When I speak with developers, I am pretty nosey and like to see their setup (and I also find that developers mostley love to share). When I saw this thread come up on Hacker News of developers sharing their setup, I spent a lot of time and went down lots of rabbit holes to find out just how developers were optimising for agentic development. When I last checked it, just over 600 responses.

If you enjoyed this, then remember to subscribe to the IndiciumAI blog so that you can keep up to date with future editions of this newsletter, as well as other great content that technologists at IndiciumAI will publish.

Build without limits - SDLC Briefing, #4

Ricardo Sueiras — Mon, 02 Nov 2026 08:23:16 +0000

Top of Mind

“Tell me how you measure me and I’ll tell you how I will behave.”

― Eliyahu M. Goldratt, Critical Chain

Hat tip to my former colleague Ray Krueger for that gem. Measurement is top if mind, and keeps coming up in conversations. James Shore has put together some of the best thinking in this space, so check out his series Assessing AI Impact: Notes for Your CFO

Must reads this week

These were my favorite posts this week.

The State of Context Engineering is a blog post come speaker notes from Drew Breunig's session at AgentCon. It was an easy read and I learned a few new things. I have given similar talks in the past (check out my talk at Prompt Engineering Conference, Tips and Tricks for better prompting)

Hello concurrent-cd is the new home that Patrick Debois has put together to share research, experiments, and findings on the confluence of people and agents.

What's next for DORA I was pretty shocked to find out that there are going to be no more independent studies on software engineering practices and productivity. If you care about developer experience, this is going to be a miss. However, the methodology and questions are there for anyone to see - who will step in and carry on the work?

What I Learned Building an AI Software Factory is a nice walk through of one persons journey and learnings in creating a software factory. Well worth a read.

Watch this

I am still messing around with Claude Code mods, and love seeing what folks are up to. AICodeKing shared a few that look genuinely interesting. I know a few folk who always need to see the files being created during a Claude Code session, so like to run it within an editor. One of the mods shown here might just present a cool solution for those folk.

Tools to try out

Third-party tools links are provided as-is. They belong to their owners, follow their own licenses, and are used at your own risk.

command centre is an amazing tool from my colleague Lee James. It provides an easy way for you to quickly extract insights across your Claude Code deployment. From finding out and managing token spend, discovering use cases, to tracking compliance and usage habbits. Give it a try.

paparats-mcp is a relly neat tool that gives Claude Code or any MCP client semantic code search across many repositories: by meaning, with who calls what, and what a change will touch. It runs on your machine or sandboxed in a container. Why might you want to try this out? This approach will help you consume way less tokens, and be much more responsive. The README of the project has some data on that so give it a go.

shunt is an interesting tool from the folks at Spotify that helps drastically reduce token used by implementing a technique that tries to intercept operations that consume large reads. I heard about it after reading the blog post, Portal by Spotify cut my Claude Code token usage by 90%

From the field

One of the best parts of the Forward Deployed Engineering job is that you get to see up close how engineers use agentic engineering tools like Claude Code. There is always stuff coming up that you can learn from, and this week, this issue surfaced up. TLDR; in your Claude Code sessions, a simple feature that helps you signpost where you currently are, can quickly consume tokens over time.

What is interesting is that this issue has two dimensions. The first, the recap message you see during your sessions, is one that you can easily disable via /config (turning recap from the default of true, to false to disable it). All good, except that this doesn't fix the issue for subagents. The issue comments go on to show how you can work around this (effectively disabling the spawning of agents). This gist provides a hacky solution which I would not implement myself, but am sharing as its interesting to dive deeper into this issue.

Build without limits - SDLC Briefing, #3

Ricardo Sueiras — Mon, 26 Oct 2026 06:58:58 +0000

Top of Mind

More Agents, Same Mythical Month is one of the more impactful posts I have read in recent months. It articulates beautifully patterns I have been seeing in the field, and that every engineer should read to understand more. The anecdotes and stories alone make this post worth reading, but the additional groups linked to have now been added to my blogroll.

Must reads this week

How to effectively debug when you no longer understand the code is a post that kept me glued to my screen (I tend to use my commute time as the perfect time to catch up on all these posts, especially long ones like this one). I have spent some time also looking at practical approaches to using agents to debug and troubleshoot, and there is a lot of good stuff in this one.

How To Use Decision Models for Evals came just in time as I managed to get some Jev tokens and am currently experimenting with decider models. A good intro that provides a lot of insights on how to get the best of these.

claude.dev is the new home for all things Claude Code for developers. A simpler layout makes it easier to find the things you care about.

LLMs are making formal software verification feasible at a much larger scale shares Anthropic's pov on the rise and rise of formal software verification in software development. It certainly follows what I have seen whilst I was working at AWS, and is well worth reading.

Watch this

There are several collections of Claude Code Skills and workflows that have gained developer attention over the last several months. You have probably heard of Matt Pocock, almost certainly read Addy Osmani's writings on agentic engineering, but perhaps are new to Lauren Tan's pstack. Rob Shocks provides an overview of these three approaches, and in coming videos will be doing a bake off to see how they compare when working on common workflows.

Tools to try out

Third-party tools links are provided as-is. They belong to their owners, follow their own licenses, and are used at your own risk.

https://github.com/Graphicle-AI/graphicle graphs are so hot right now, and so here is a new tool (written in Rust of course) that maps your repository into a code graph, remembers your project's docs, decisions and past agent sessions, and gives your coding agent cited excerpts from both. Its fast, provides options to help you manage token spend, and works natively with Claude Code.

https://github.com/The-PR-Agent/pr-agent is an agentic AI powered code review tool from the folks that brought you qodo. It provides a number of tools (/describe, /review, and /improve) that you can run within your CI workflows or in your CLI.

https://github.com/saphan-ai/proven is another agentic AI tool to help you with your code reviews. Proven takes a slightly different approach. Proven will review pull requests: proposed changes to a codebase. Every problem it reports must come with evidence you can check yourself, such as a test you can run or a data query you can repeat. If it cannot show the evidence, it does not report the problem.

https://github.com/gojko/lights-on-software-factory is a nice starting point for exploring software factories. There are a few of these kinds of repos, and one of the reasons I love open source is that the four freedoms always let me learn from what others have built.

From the field

This week it has been all about code reviews. I have been working with customers who unlock some real code review pain points, and wanted to share some of the content that I have been referencing that we have seen make an impact.

It is probably obvious, but needs stating - the larger the diff, the more findings LLMs will report. Thinking how to scope down tasks so that the PRs will be smaller, will make PR reviews easier - both cognitively for the human reviewer, but also bring back less findings. Posts like Speeding up code review with small-change provide some insights in how organisations are tackling this. Code Review After Code Gets Cheap is another post that looks (at a high level) at some of the options you should be thinking of. I am experimenting with some of the tools that I have shared above (in addition to the tools that Claude Code provides), and will report back how I get on with these.

As a side note, it can be confusing initially to know what the native review capabilities that existing within Claude Code. This is what I ended up with, and (I think) covers the different native capabilities for Code Review within Claude Code (as well as where your own or third party ones plugin).

Managed Code Review - run in GitHub, managed by Anthropic (docs dive into this here)
Local Code Review - run in your Claude Code session using /code-review
GitHub Actions Code Review - run code reviews within your GitHub/GitLab actions, as a CI process (Claude in headless mode)
Your own Review - implement your own Skills in your local sessions
3P Code Review - a number of third party Code Review services (similar to Managed Code Review) are available: Coderabbit, Quodo, etc

You can compare options here

Build without limits - SDLC Briefing, #2

Ricardo Sueiras — Mon, 19 Oct 2026 09:05:21 +0000

Top of Mind

How to approach reviewing code has been top of mind this week, and came up in conversations during the Applied AI Symposium that Indicium AI held in London this week. My timeline also had some interesting posts on this topic. First up was Spotify sharing how they tackle this in their post AI Changed How Spotify Builds. What We Learned (and Fixed) About Quality at Higher Velocity. Anthropic also dropped perhaps one of the more interested pieces on this topic, looking at how they approach doing review at scale in How the Claude Code team does code review, and one of the authors also pencilled another in this topic that is also worth reading, Agentic Verification. Anthropic also published a recipe in their Claude Cookbook that walks you through creating a scheduled reviewer for your repo, and it is well worth implementing this recipe. Go check it out (and other really cool recipes the folks are sharing), Building a scheduled repository reviewer.

Must reads this week

Escalate hard decisions with the advisor tool is an experimental feature within Claude Code that I will admit I did not know about it until I heard about it during a meetup I attended this week (remember folks, meetups are super valuable for learning these sorts of things!). This feature allows you to use cheaper models, and then when needed, advisor will kick in and consult stronger models when needed (for example, if its bumping into repeating errors, or before, task is completed)
Redesigning source control at Anthropic is an interesting post that looks at some of the engineering choices that Anthropic are making when it comes to how to make source control work at agentic engineering speed. Scion is their bet, and its unlikely that many will find themselves in need of implementing their own, but we are seeing folks already working on improving the scaling capabilities of git, so who knows.

Watch this

Zach Lloyd, founder and CEO of Warp did a talk at the AI Engineer conference in New York last week, talking about the software factory they built to help them manage the open sourcing of their Warp terminal (agent control plane). There is a lot of good stuff in this, including the detailed workflow and sample repo you can try for yourself. At Indicium AI we also help our customers implement software factories, and the architecture in this session had a lot of similarities to the approach we have taken, so lots of nodding from me.

Tools to try out

Third-party tools links are provided as-is. They belong to their owners, follow their own licenses, and are used at your own risk.

claude-code-templates - I was drawn to this repo because Daniel San put together a really cool Claude Code mod that lets you inspect whats inside your context window at every turn, but then got lost in all the other cool stuff Daniel has been putting together. Defo a repo to spend some time exploring.

diff-tour - this is a really neat idea, that follows a thread of similar other tools in this space. How can you make it easier to reviews to walk through your diffs during PR reviews. diff-tour attempts to solve this by creating guided walk throughs the way a senior engineer might do. Works with a number of coding agents, including Claude Code.

archify - is a tool that I am looking forward to trying out, especially in some of the code modernisation and onboarding use cases I am helping customers with. The tool uses agents to create beautiful interactive experiences that help you navigate and understand how a project or codebase works. It works with multiple coding harnesses, including Claude Code, and is one of the better tools in this space.

mixture-of-models-claude-mod - is a neat tool that allows you to provide dynamic routing of requests to your Anthropic models or cheaper, locally hosted ones. Similar to how Kiro's Auto mode works, but this one allows you to do this from within your Claude sessions. Requires a bit of fiddling, but if you like that sort of thing, give it a go.

From the field

This week, everyone has been talking about reverse engineering with agents. Whether that is using tools like rea, or one-shotting using the latest generation models, my socials are full of folks beginning to share what they are doing with it (including this cool one that looks at how gamers are using it). I am interested as I can see some practical use cases for this in code modernisation use cases where perhaps source code is not available or the confidence is low. Have you checked it out yet?

Build without Limits - SDLC Briefing - Edition #1

Ricardo Sueiras — Mon, 12 Oct 2026 12:30:39 +0000

Top of Mind

State of agent skills is a report from Vercel that looks at the state of agent skills, drawing from the data they have amassed from hosting the skills.sh registry (one of a few that are out there). Essential reading.

Must reads this week

git workstree gotchas is required reading for those of us who run parallel sessions within the same repo. Some of the points raised in this post will be familiar with folk, but there were enough new ones to make this post interesting.

Linux Foundation published its research into Developer Experience that contains some nice check lists that you can review/use as you look into what is, and how to measure developer experience. Why does this matter? SDLC transformation using agentic AI is a key driver for improving developer experience, and many organisations are now beginning to spin up developer experience teams where agentic AI tooling and governance sit.

Getting started with Claude Code mods is the official launch post that walks you through what Claude Code mods are and how to build one. Beginning to see a few folk doing some cool things with this, so check this out.

Watch this

Fixing the PR Bottleneck This week I spent some time on my commute watching the latest Matt Pocock knowledge drop on how to think and approach the review bottleneck in agentic engineering. Don't want to give too much away, but I think there are some really good perspectives here.

Tools to try out

Third-party tools links are provided as-is. They belong to their owners, follow their own licenses, and are used at your own risk.

Codebase-memory-mcp is a local MCP server that turns your repo into a searchable knowledge graph of functions, calls, routes and dependencies. AI coding agents can then answer questions like "what calls this?" or "what breaks if I change this?" with one query, instead of reading through files one at a time. This is really handy if you are tackling code modernisation or supporting legacy tech stacks, something that we at Indicium AI are increasingly helping customers with.

Shipreel is a neat tool that helps you create visuals (video), turning a pull request into a short narrated walkthrough video. It uses your harness to read the diff, write a story, draw the diagrams, record the real app if the change has a UI, and then render a compact MP4, about two and a half minutes by default, with captions, crossfade cuts and an ambient music bed.

From the field

Should workers be paid for AI skills? is a super interesting post that piqued my interest given recent customer meetings that have flagged the topic of how much is the premium for AI competent engineers, and what flight risk do they present to an organisation if they train their existing engineers in AI. Are you seeing this in your organisation?

Reading list (May 13th to June 28th)

Ricardo Sueiras — Sun, 28 Jun 2026 10:01:19 +0000

What I am currently reading ( 13th May 26 )

These were sufficiently interesting for me to read and bookmark.

CODING

Another tool that helps you manage the state of all your development agents - link [tool] - ( Added: 2026-06-28 09:58:02 )
A post from the Slack engineering team around how to use agentic AI in your end to end tests - link [case study] - ( Added: 2026-06-25 20:15:29 )
Great post from AWS Hero that looks at hooks in Claude Code and how these can help you stay safe - link [best-practice] - ( Added: 2026-06-25 20:14:13 )
The current impact of AI on engineering velocity. DX’s latest data reveals the reality behind AI-driven engineering productivity gains. - link [opinion] - ( Added: 2026-06-23 08:23:34 )
Want to know how to use Claude Code with local (or other) models - this guide shows you how to get up and running. - link [tutorial] - ( Added: 2026-06-16 11:56:24 )
AI-powered bug bounty hunting from your terminal - recon, 20 vuln classes, autonomous hunting, and report generation. All inside Claude Code. - link [security] - ( Added: 2026-06-16 11:55:21 )
The economics of AI agents in software development - an update post tokenmaxxing - link [opinion] - ( Added: 2026-06-16 11:41:35 )
A new tool that takes the output of your Claude Code logs (and Codex/Cursor) and then analyses them to tell you about your style of development. I am not sure this is super helpful, but at the same time, who doesnt want to know. Clickbait ahoy! - link [tool] - ( Added: 2026-06-09 21:31:46 )
Moldable Development is a way of programming through contextual micro tools built for each problem. Software is shapeless. We, humans, need a shape to reason about anything. Tools provide the shape of software. By molding our tools to match the context of our systems, every development problem can be exhibited in a way that a human can relate to and reason about. - link [opinion] - ( Added: 2026-05-28 13:32:42 )
A durable, supply-chain-aware agent that automatically triages Dependabot + Renovate PRs. (Powered by Temporal) - link [security] - ( Added: 2026-05-27 11:18:32 )
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. - link [code-repo] - ( Added: 2026-05-25 15:12:02 )
Another great post from ThoughtWorks on the application of AI agents for doing work. - link [opinion] - ( Added: 2026-05-21 18:07:38 )

AI

If you want to do anything with Amazon Bedrock AgentCore, then start here with these skills - link [code-repo] - ( Added: 2026-06-27 12:11:43 )
Nice deep dive on testing using AI and specifically looking at using Playright across a number of different control surfaces. Some really great insights here. - link [opinion] - ( Added: 2026-06-19 07:48:40 )
Great write up and deep dive looking at the security capabilities of /sandbox in Claude Code - link [security] - ( Added: 2026-06-18 06:52:27 )
A new open source project from Google that looks to create a standard format for sharing information (and knowledge) between AI Agents - link [best-practice] - ( Added: 2026-06-16 11:40:53 )
A new meta harness that allows you to compose Claude into different workflows - link [tool] - ( Added: 2026-06-16 11:39:46 )
Really nice post on the architecture of modern agentic systems - well worth checking out - link [best-practice] - ( Added: 2026-06-09 20:51:24 )
Using multiple agents with different personas and models to help tackle code review by "slicing" across concerns. - link [opinion] - ( Added: 2026-06-05 09:51:32 )
Compound engineering - what is it and how to implement it - link [opinion] - ( Added: 2026-05-29 14:38:44 )
Claude Code Dedicated Development Harness - Achieving High-Quality Development Through an Autonomous Plan→Work→Review Cycle - link [tool] - ( Added: 2026-05-28 14:08:24 )
A very nice and local tool to build your own AI coding pipelines - think n8n/Zappier - link [tool] - ( Added: 2026-05-28 14:07:45 )
A quick tweet storm on how Ramp used thousands of agents to scan for security vulnerabilities - link [security] - ( Added: 2026-05-28 14:05:20 )
A good read of Ramp's reason for setting up their own background AI agent, with specifics on what they setup. - link [case study] - ( Added: 2026-05-28 14:03:32 )
Tutorial on harness engineering - looks decent enough - link [tutorial] - ( Added: 2026-05-27 12:59:53 )
Essential guide on how to use Claude Code on large code bases. Contains a lot of great good practices that apply for general use of AI coding agents. - link [best-practice] - ( Added: 2026-05-27 11:46:07 )
Another tool to help you know which local LLM to run - runs and provides a dashboard of available models and recommendations. - link [tool] - ( Added: 2026-05-25 15:14:14 )
A tool to help you know which local LLM to run - runs and provides a dashboard of available models and recommendations. - link [tool] - ( Added: 2026-05-25 15:13:58 )
The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills. - link [tool] - ( Added: 2026-05-25 15:13:05 )
Official, Anthropic-managed directory of high quality Claude Code Plugins. - link [tool] - ( Added: 2026-05-25 15:12:28 )
The winner of an Anthropic hackathon open sourced the complete agent harness he used - link [code-repo] - ( Added: 2026-05-25 06:16:46 )
Case study from Wix on how they are automating and embedding AI in developer workflows - link [case study] - ( Added: 2026-05-21 18:13:23 )
A great read on how GitHub provide a layered approach to reduce the blast radius of running untrusted non deterministic wirkloads - link [security] - ( Added: 2026-05-18 08:03:54 )
A neat way to manage your Claude Code notifications- tamagotchi style! - link [tool] - ( Added: 2026-05-17 19:37:29 )

TECH

Really cool tool that helps you create sylised videos, making them pixelated or ascii - link [tool] - ( Added: 2026-06-16 11:57:24 )
Everything you ever wanted to know about networking with docker - link [tutorial] - ( Added: 2026-06-04 16:13:06 )
A really nice overview and tutorial on TCP sockets - link [tutorial] - ( Added: 2026-06-04 16:06:48 )

Generated on 2026-06-28 by Bookmark Manager | 13th May 26 to 28th Jun 26 | Total bookmarks: 37

Follow me on LinkedIn or GitHub

Reading list (27th April to May 12th)

Ricardo Sueiras — Tue, 12 May 2026 11:45:00 +0000

What I am currently reading ( 28th Apr 26 to May 12th )

These are the current online posts that I enjoyed reading and are worth sharing.

AI

Some interesting perspectives on the dependency that orgs might be falling into with the use of agentic ai coding assistants - link [opinion] - ( Added: 2026-05-11 21:07:31 )
Looks super interesting - this tool (open source) captures your agent AI session alongside your code commits. Works with multiple coding agents. - link [tool] - ( Added: 2026-05-06 16:45:22 )
This video shares how Anthropic build Skills, so worth paying attention to - link [best-practice] - ( Added: 2026-05-06 16:25:53 )
A must read post if you are looking to understand and write Skills files for AI Agents - link [opinion] - ( Added: 2026-05-06 14:07:52 )
Borrowing from concepts like memory paging that we used to use back in the 32bit CPU architecture era to access larger memory spaces by paging in/out memory, comes a new approach to memory management for your LLMs - link [tool] - ( Added: 2026-05-04 11:16:55 )
An essential resource for anyone using Kiro IDE or CLI - link [tool] - ( Added: 2026-05-04 10:59:03 )
Another read on the intersection of AI and legal constructs in tech - link [opinion] - ( Added: 2026-05-04 10:45:18 )
What alternatives to copyright can you use to protect the output of your agentic AI? This post looks at patents and trade secrets - link [opinion] - ( Added: 2026-05-04 09:00:09 )
Another post on copyright and IP controls in the agentic world - link [opinion] - ( Added: 2026-05-04 08:51:42 )
A post that explores how to build more robust AI systems by taking a look at how you can apply resilience engineering techniques and good practices - link [best-practice] - ( Added: 2026-05-03 19:37:48 )
A great post on the increasingly important topic of token economics - dont skip this post. - link [best-practice] - ( Added: 2026-05-03 19:35:58 )
A very nice workflow for using AI coding agents that provides a set of skills that helps walk you through from start to end. - link [best-practice] - ( Added: 2026-05-03 19:31:36 )
Interesting reference implementation of an agentic low code tool built on AgentCore - link [code-repo] - ( Added: 2026-04-29 21:59:33 )
Google Cloud's Chief Evangelist Richard Seroter discusses developer loyalty, AI dev tools competition with AWS and Azure, and Google's platform strategy. - link [opinion] - ( Added: 2026-04-29 13:53:13 )
A post on the conundrum around copyright, intellectual property, and the output of agentic AI - link [opinion] - ( Added: 2026-04-29 13:49:58 )
From this post, an interesting data point (needs validation) "44 percent of Gen Z workers admitted to sabotaging their employers’ AI deployments as a form of rebellion" - link [opinion] - ( Added: 2026-04-29 13:25:04 )
A training course from Jetbrains on spec driven development - link [tutorial] - ( Added: 2026-04-29 13:24:18 )
Planning and implementation guidance from AWS, with a focus on best practices and tools, for architects, managers, technical leads, and executives - agentic AI has some good info and pattern decomposition - link [best-practice] - ( Added: 2026-04-29 12:08:59 )
Thoughtworks unveils its agentic workflow - well worth checking out - link [best-practice] - ( Added: 2026-04-29 09:54:23 )

CODING

Move over Localstack, there is a new kid on the block - link [tool] - ( Added: 2026-05-11 21:06:47 )
A lightweight VM manager that allows you to mount local files/directories and then make them available to coding agents within a safe, sandboxed VM - link [tool] - ( Added: 2026-05-06 16:03:12 )
Very cool resource for making sure your UML diagrams look fresh, AWS architecture icons - link [code-repo] - ( Added: 2026-05-05 15:08:39 )
A must read post that takes a more pragmatic look at the hype around spec driven development - link [opinion] - ( Added: 2026-05-04 14:27:31 )
Blog post and tool that looks at creating a simulation of code deployment and how you can use this to simulate and predict what stress points you might see as you increase velocity of changes made - link [opinion] - ( Added: 2026-05-04 09:42:50 )
A nice walkthrough of using gittrees with AI coding agents to do multiple parallel tasks on the same code base - link [best-practice] - ( Added: 2026-05-03 19:35:03 )
Essential resource if you are using or wanting to learn about d3 - domain driven design - link [tool] - ( Added: 2026-04-29 22:03:04 )
A very “hit” agent harness setup for AI coding that looks to make this more deterministic - link [tool] - ( Added: 2026-04-29 07:24:16 )

TECH

An open source video tool that helps you create great videos for your demos or presentations - link [tool] - ( Added: 2026-05-08 08:49:30 )
The RICE method to help you priortise feature releases - simple formula with consistent rubric - link [best-practice] - ( Added: 2026-04-30 21:26:03 )

AWS

The MIT alternative to Localstack - link [tool] - ( Added: 2026-05-01 21:18:40 )

OSS

This is an incredibly thoughtful, must-read piece from Gabriele on open source sustainability. - link [opinion] - ( Added: 2026-04-28 16:35:34 )

Generated on 2026-05-12 by Bookmark Manager | 28th Apr 26 to 12th May 26 | Total bookmarks: 31

Follow me on LinkedIn or GitHub

Reading list (21st to 27th April)

Ricardo Sueiras — Mon, 27 Apr 2026 08:08:57 +0000

What I am currently reading

These are the current online posts that I enjoyed reading and made me think.

AI

If you are not the model, you are the harness. Long read, but well worth reading to stay on top of the latest thoughts on harness engineering. - link [opinion] - ( Added: 2026-04-27 08:06:01 )
Read to find out how the SOTA model. providers might be tweaking things that have an impact on how many tokens you use. - link [opinion] - ( Added: 2026-04-26 18:16:35 )
Start optimising your token usage when you use AI coding assistants. Read this to get you started. - link [best-practice] - ( Added: 2026-04-26 15:53:21 )
Every one is talking about agent harnesses but not many about the harness tax. Read and then think. - link [opinion] - ( Added: 2026-04-26 09:07:55 )
Another tool that explores your AI coding agent history files and offers up suggestions. Has a nice tui as well. - link [tool] - ( Added: 2026-04-25 14:51:54 )
An interesting tool that allows you to analyse AI coding agent sessions across a number of different tools. - link [tool] - ( Added: 2026-04-25 08:05:35 )
Long read, but a good one - in depth at how one organisation is running and scaling AI - link [case study] - ( Added: 2026-04-21 12:21:18 )
A blog post that looks at how you can measure which "level" (or as the post says, AI literacy) you are operating in when using agentic AI - link [opinion] - ( Added: 2026-04-21 12:19:34 )
Optimize token usage within Claude Code by speaking like a caveman. - link [tool] - ( Added: 2026-04-21 09:36:58 )
I have been deep into looking at evals and agent evaluation approaches over the past few weeks, and this blog post captured a lot of good stuff - link [blog] - ( Added: 2026-04-21 07:40:46 )
Great video that provides an essential overview of how to build with AI (in this instance using Spring AI). Has a supporting Github repo at https://github.com/tzolov/voxxeddays2026-demo - link [tutorial] - ( Added: 2026-04-20 17:14:20 )
Agent harness or harness engineering is the new hotness right now, so this is a breakdown of all the components need to build an ai coding agent - link [opinion] - ( Added: 2026-04-20 10:34:17 )
A new tool that allows you to put controls on your AI agent spending - link [tool] - ( Added: 2026-04-20 10:32:30 )
A recent example of the challenges of relying too much on a single vendor - in this instance, Anthropic - who cut off an entire organisation (60 developers) - link [case study] - ( Added: 2026-04-20 08:45:22 )

CODING

A write up of using gitnexus, a tool that works locally and will help your AI coding tool with the right insights about your code base - link [tool] - ( Added: 2026-04-26 16:00:21 )
This is an essential resource for any developers who might need one of the many utilities that are available - from working with json files, creating/testing APIs, and much more. - link [tool] - ( Added: 2026-04-21 13:30:36 )
A post that looks at how to think about ai coding agents with a different lens/perspective - really great stuff and a must read - link [opinion] - ( Added: 2026-04-21 12:12:28 )
A very nice interactive tool to help you understand some of the underpinning concepts of event driven, serverless application architectures - link [best-practice] - ( Added: 2026-04-20 17:07:39 )

Generated on 2026-04-27 by Bookmark Manager | 20th Apr 26 to 27th Apr 26 | Total bookmarks: 18

Follow me on LinkedIn or GitHub

Reading list (29th March to April 20th)

Ricardo Sueiras — Mon, 20 Apr 2026 17:16:51 +0000

These are the current online posts that I enjoyed reading and made me think.

AI

Great video that provides an essential overview of how to build with AI (in this instance using Spring AI). Has a supporting Github repo at https://github.com/tzolov/voxxeddays2026-demo - link [tutorial] - ( Added: 2026-04-20 17:14:20 )
Agent harness or harness engineering is the new hotness right now, so this is a breakdown of all the components need to build an ai coding agent - link [opinion] - ( Added: 2026-04-20 10:34:17 )
A new tool that allows you to put controls on your AI agent spending - link [tool] - ( Added: 2026-04-20 10:32:30 )
A recent example of the challenges of relying too much on a single vendor - in this instance, Anthropic - who cut off an entire organisation (60 developers) - link [case study] - ( Added: 2026-04-20 08:45:22 )
Use Obsidan as a memory layer for Claude - this tool works at the repo level, helping you capture essential information that will persist over the lifetime of that project - link [tool] - ( Added: 2026-04-19 14:18:16 )
Another great doc on RAG done properly, this time exploring the science of chunks - link [best-practice] - ( Added: 2026-04-19 13:52:26 )
Sits between your apps and your models and provides various security features. - link [tool] - ( Added: 2026-04-19 10:17:46 )
Detailed breakdown of what a production RAG system would look like, with a great context builder architecture - link [best-practice] - ( Added: 2026-04-18 09:19:40 )
Good post on caching techniques you can apply to optimise your token/inference usage - link [best-practice] - ( Added: 2026-04-18 09:18:31 )
Nice blog post from the folks at PwC on observability in your generative AI systems - link [best-practice] - ( Added: 2026-04-12 19:04:06 )
Thread on Reddit around the observability gap with AI, and suggests that this is why AI project failure rates are so high - link [opinion] - ( Added: 2026-04-12 18:42:17 )
Decision making framework when architecting agentic apps - link [best-practice] - ( Added: 2026-04-11 22:49:40 )
Great primer video if you want to learn more about different AI agent patterns - link [best-practice] - ( Added: 2026-04-11 22:41:51 )
Harness engineering is so hot right now - a post from the wonderful folks at Thoughtworks, so you know its going to provide you with a good insight into exactly what this means. - link [opinion] - ( Added: 2026-04-11 21:44:38 )
A post that helps you think about and then select the right design pattern for your use case and situation - link [best-practice] - ( Added: 2026-04-11 21:43:19 )
Nice post with some ideas and thoughts on team structure and dynamics in the age of agentic AI - link [opinion] - ( Added: 2026-04-11 21:42:09 )
Run agents, lots of them, using this open source project - link [tool] - ( Added: 2026-04-11 07:42:11 )
A contrarian post on why we are falling for the AI hype - link [opinion] - ( Added: 2026-04-10 07:01:22 )
Production-grade engineering skills for AI coding agents from the OG himself. - link [code-repo] - ( Added: 2026-04-09 11:39:31 )
A post on how new agentic AI is changing engineering team structure and dynamics - link [opinion] - ( Added: 2026-04-09 11:37:54 )
In a world where architecture teams are either feared gatekeepers or invisible bystanders, Oliver brings together a brilliant panel to ask a genuinely awkward question: is your governance framework actually helping anyone? - link [opinion] - ( Added: 2026-04-09 11:26:49 )
A really cool way to run Playright - link [tool] - ( Added: 2026-04-04 09:04:17 )
New open source framework from Microsoft that looks at agentic AI governance and security - link [security] - ( Added: 2026-04-03 16:08:22 )
Good post from Mr Assay on AI and developer productivity - as always, the gold is in there those hyperlinks. - link [opinion] - ( Added: 2026-04-02 16:02:24 )
A must watch video about Blackhat LLMs from the clever folks at Anthropic - link [security] - ( Added: 2026-04-02 09:32:43 )
Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack. It includes everything you need to go from early prototypes to production-ready applications. Mastra integrates with frontend and backend frameworks like React, Next.js, and Node, or you can deploy it anywhere as a standalone server. It's the easiest way to build, tune, and scale reliable AI products. - link [tool] - ( Added: 2026-04-01 08:49:08 )
Nice post from the great folk at Nearform on how to build production grade agentic applications with the right testing approach - link [best-practice] - ( Added: 2026-04-01 08:36:59 )
Seems like a theme this week - folks writing about the gap of using agentic AI, and however good the output they generate, they do not understand what good looks like, how to evaluate quality, and understand how to make the right trade offs. - link [opinion] - ( Added: 2026-04-01 08:07:51 )
An interesting take on AI - the fact that Agents do not understand what "good" looks like, thats on you. - link [opinion] - ( Added: 2026-04-01 08:06:26 )
Great blog post on implementing controls when deploying production AI agents to help minimise regression and drive up consistency - link [best-practice] - ( Added: 2026-04-01 07:34:15 )
Portkey is a tool that helps provide AI governance and observability to your apps. Now open source - link [tool] - ( Added: 2026-04-01 07:30:49 )
An interesting pov on the difference in how execs and individual contributors (ICs) are viewing agentic AI - link [opinion] - ( Added: 2026-03-31 15:23:36 )
Understand AI coding harnesses by looking at the (disclosed) source code for Claude Code - check the README to understand the. backstory here - link [code-repo] - ( Added: 2026-03-31 14:47:51 )
Research paper that seems to indicate that creating personas within your agentic AI applications might be leading to suboptimal output - link [research] - ( Added: 2026-03-31 09:59:49 )
Some interesting insights from a study of students and how they are using LLMs in their studying. - link [case study] - ( Added: 2026-03-31 08:22:41 )
Enforce runtime guardrails through a centralized control layer—configure once and apply across all agents. Agent Control evaluates inputs and outputs against configurable rules to block prompt injections, PII leakage, and other risks without changing your agent’s code. - link [tool] - ( Added: 2026-03-31 08:12:52 )
Run multiple agents in parallel — each in its own container, with its own workspace, collaborating on your code or project files simultaneously. - link [tool] - ( Added: 2026-03-30 14:53:06 )
This repo provides info on how you can integrate Cedar policies into your MCP Servers - link [code-repo] - ( Added: 2026-03-30 12:00:13 )
The folks at JPC Morgan have put together this post that outlines how they are using agentic AI to help them with threat modelling - link [security] - ( Added: 2026-03-29 18:28:46 )
Dify is an open-source LLM app development platform. Its intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features (including Opik, Langfuse, and Arize Phoenix) and more, letting you quickly go from prototype to production. - link [tool] - ( Added: 2026-03-29 11:20:22 )
A collection of use cases with supporting assets from OpenAI - link [best-practice] - ( Added: 2026-03-28 21:19:14 )
Scion is an experimental multi-agent orchestration testbed designed to manage concurrent LLM-based agents running in containers across your local machine and remote clusters. It enables developers to run groups of specialized agents with isolated identities, credentials, and workspaces, allowing for a dynamic and evolving graph of parallel execution of tasks such as research, coding, auditing, and testing. - link [tool] - ( Added: 2026-03-28 12:50:21 )

CODING

A very nice interactive tool to help you understand some of the underpinning concepts of event driven, serverless application architectures - link [best-practice] - ( Added: 2026-04-20 17:07:39 )
Agentic AI coding tools roll out infigraphic - link [best-practice] - ( Added: 2026-04-19 13:39:04 )
A post that dives into whether token maxing is a signal of dev productivity or whether there are other data points that matter. Well worth your attention - link [best-practice] - ( Added: 2026-04-18 09:43:57 )
A collection of great Claude files, especially around the domain of TDD and testing - link [best-practice] - ( Added: 2026-04-13 09:03:00 )
Measuring AI in software development: Interview with Jellyfish CEO Andrew Lau - link [case study] - ( Added: 2026-04-09 11:38:26 )
Great overview of how Spotify do releases - if you want to nerd out on details, this is the post for you. Whilst the stuff in here is pretty standard, the way it is described is excellent so well worth your time. - link [best-practice] - ( Added: 2026-04-09 11:23:00 )
Data points on software engineering jobs - slowly increasing over the past two years, despite the increasing usage of AI coding assistants. - link [report] - ( Added: 2026-04-01 09:05:22 )
Nice blog post on some architecture patterns when implementing gitops - link [best-practice] - ( Added: 2026-03-31 10:00:45 )
A nice tool from my good friend Danilo that allows you to take a code repo and then generate a very cool interactive tool to help explain the code, line by line - link [tool] - ( Added: 2026-03-30 12:04:12 )
A nice tool that helps you reduce token use when exploring your code base in Claude - link [tool] - ( Added: 2026-03-28 08:31:33 )

TECH

Trends in enterprise customers in software engineering - link [opinion] - ( Added: 2026-04-10 16:49:04 )
The State of Agentic AI 2026 Report - link [report] - ( Added: 2026-04-09 11:36:28 )
If you want to learn Kubernetes and all things cloud native, this resource will help you get started - all local, so as long as you have a good broadband and decent spec machine (home lab) you should be good to go - link [code-repo] - ( Added: 2026-04-09 11:35:11 )
A HBR post that looks at how AI is reshaping security and risk. Whether you are using it or not, security and risk are being impacted and you need to think about what your plan is to tackle these new threats. - link [security] - ( Added: 2026-04-09 11:29:53 )
Really great post on how to approach the fragmentation problem when teams want to leverage different tools - link [best-practice] - ( Added: 2026-04-02 15:57:51 )
A blog post on why you should start a blog - provides some good reasons, and these defo ring true for me. - link [opinion] - ( Added: 2026-03-31 08:21:35 )

Generated on 2026-04-20 by Bookmark Manager | 28th Mar 26 to 20th Apr 26 | Total bookmarks: 58

Follow me on LinkedIn or GitHub

Getting hands on with spec driven development

Ricardo Sueiras — Tue, 14 Apr 2026 10:02:06 +0000

If you are interested in learning more about Spec Driven Development, I am happy to share that I will be running workshop with Simon Martinelli on the 14th May, that will help developers get started.

A lot of developers today are already using AI but still struggling to make the output consistent and production-ready. That’s exactly what this workshop focuses on. You will walk away with a clear idea of how you can apply spec driven development to your own projects.

Use this link , and use the code RIC40 to get a discount.

Reading list (17th to 28th March)

Ricardo Sueiras — Sat, 28 Mar 2026 14:57:15 +0000

These are the current online posts that I enjoyed reading and made me think.

AI

Scion is an experimental multi-agent orchestration testbed designed to manage concurrent LLM-based agents running in containers across your local machine and remote clusters. It enables developers to run groups of specialized agents with isolated identities, credentials, and workspaces, allowing for a dynamic and evolving graph of parallel execution of tasks such as research, coding, auditing, and testing. - link [tool] - ( Added: 2026-03-28 12:50:21 )
Runtime safety infrastructure for AI agents. Kernel-enforced isolation, supply-chain security, immutable auditing, atomic rollbacks, credential management, and more. - link [tool] - ( Added: 2026-03-27 22:03:00 )
A great summary of agentic AI frameworks and tools for Java - link [tool] - ( Added: 2026-03-27 20:51:03 )
Run Claude Code in local sandboxed docker containers - tool that provides full Claude credentials - link [code-repo] - ( Added: 2026-03-24 19:55:01 )
Excellent post about how to improve accuracy of your agentic AI application using a number of approaches - link [best-practice] - ( Added: 2026-03-24 15:34:36 )
llm-d is a high-performance distributed inference serving stack optimized for production deployments on Kubernetes. We help you achieve the fastest "time to state-of-the-art (SOTA) performance" for key OSS large language models across most hardware accelerators and infrastructure providers with well-tested guides and real-world benchmarks. - link [code-repo] - ( Added: 2026-03-24 11:31:22 )
Some useful advice on how to prepare and position how developers interact with your platform or system - link [opinion] - ( Added: 2026-03-23 17:24:29 )
A great series diving into Claude Code. One of the better guides I’ve read. - link [opinion] - ( Added: 2026-03-21 20:40:24 )

CODING

A nice tool that helps you reduce token use when exploring your code base in Claude - link [tool] - ( Added: 2026-03-28 08:31:33 )
FeatureOps is the discipline of controlling software behavior at runtime. It extends DevOps pillars (flow, feedback, continuous learning) into the layer where real user value lives: the features themselves. Where DevOps asks "is the code deployed?", FeatureOps asks "is the feature working for the right users at the right time?" - link [opinion] - ( Added: 2026-03-23 12:02:55 )
A set of opinionated steering guides for a number of use cases around developing a web application - link [code-repo] - ( Added: 2026-03-17 09:57:26 )

TECH

Want to dive deep into how to measure your DevRel activities? Take a look at this blog post that has some good ideas that you can lean into. - link [opinion] - ( Added: 2026-03-23 16:56:22 )
The developer advocate flywheel - link [opinion] - ( Added: 2026-03-23 16:47:13 )
A nice history and timeline that looks at how we got to modern day developer advocacy from the initial evanglism roots - link [case study] - ( Added: 2026-03-23 13:35:08 )
A good summary of how to approach developer marketing - link [best-practice] - ( Added: 2026-03-23 13:31:01 )
A great set of essays on how to think about developer relations - link [opinion] - ( Added: 2026-03-23 12:03:27 )

Generated on 2026-03-28 by Bookmark Manager | 17th Mar 26 to 28th Mar 26 | Total bookmarks: 16

Follow me on LinkedIn or GitHub

Reading list (10th - 16th of March)

Ricardo Sueiras — Tue, 17 Mar 2026 09:32:17 +0000

These are the current online posts that I enjoyed reading and made me think.

AI

Find out how Anthropic models are being used across geographical regions. Broken down by use cases - link [report] - ( Added: 2026-03-15 14:49:37 )
A look at a new tool to sandbox AI agents on MacOS, which the zooms out and looks at some of the broader questions you need to ask yourself - link [tool] - ( Added: 2026-03-15 14:37:21 )
A new agent orchestration project, this time from Bytedance - link [tool] - ( Added: 2026-03-15 11:17:48 )
Rightsizing engineering teams in the agentic AI age - link [opinion] - ( Added: 2026-03-15 10:58:03 )
Great thoughtworks piece on the agentic SDLC and how to think and plan ahead - link [opinion] - ( Added: 2026-03-15 10:56:24 )
Fascinating write up by an openclaw agent that was tasked to research and come up with ways to improve itself - link [opinion] - ( Added: 2026-03-15 10:39:42 )
A great tool to test your agents to see if they can be asked to do things they shouldn’t do. - link [tool] - ( Added: 2026-03-15 10:31:33 )
A detailed guide on different security postures when it comes to deploying Claude Cowork - details and specifics are what set this post apart. - link [best-practice] - ( Added: 2026-03-12 21:16:15 )
A nice enterprise architecture reference implementation of agentic ai building blocks - link [opinion] - ( Added: 2026-03-12 20:55:11 )
This is a great read of one date engineer's experience of using Claude Code to generate data engineering pipelines with dbt - the good and the not so good is covered. - link [opinion] - ( Added: 2026-03-12 12:03:41 )
Research paper on the security foundations of agentic systems - well worth reading to understand the security problem space - link [research] - ( Added: 2026-03-12 10:56:55 )
Fantastic post that looks at the timeline of maturity for agentic aI - link [opinion] - ( Added: 2026-03-12 09:31:08 )
Want to run your agentic apps in Kubernetes? Give this repo a try out (looks like OpenAI only from the docs) - link [code-repo] - ( Added: 2026-03-11 14:51:55 )
It is rare to find a detailed post on how to approach testing agentic AI code, but this post walks you through how to use a layered approach. Very nice. - link [opinion] - ( Added: 2026-03-11 13:31:38 )
The lethal trifecta for AI agents: private data, untrusted content, and external communication - import post to understand some of the foundational risks with agentic based AI - link [best-practice] - ( Added: 2026-03-11 12:19:08 )
An implementation of integrate Cedar policies and Calude Code (via hooks) - link [tool] - ( Added: 2026-03-11 11:40:41 )
A nice blog post around using Cedar policies with agentic flows. Different to AgentCore which also uses Cedar. - link [opinion] - ( Added: 2026-03-11 11:36:46 )
State of the art open source text to speak model - Trained on over 10 million hours of audio across approximately 50 languages, S2 combines reinforcement learning alignment with a Dual-Autoregressive architecture to generate speech that sounds natural, realistic, and emotionally rich. - link [code-repo] - ( Added: 2026-03-11 09:27:11 )
A nice collection of prompts with explanations. I don’t normally read these as I find that spending time experimenting provides better learning but these were good and I’ll be testing a few out - link [opinion] - ( Added: 2026-03-10 19:16:31 )
A new macOS menu bar tool to run/manage local LLMs. Nice features and this one is optimised for Apple silicon - link [tool] - ( Added: 2026-03-10 08:24:52 )

CODING

Really good opinion piece on how to think (and approach) reviewing agentic code contributions - link [opinion] - ( Added: 2026-03-15 10:51:33 )
A TypeScript library for easy scripting of AI agents. Thinkwell provides a fluent API for blending deterministic code with LLM-powered reasoning. - link [tool] - ( Added: 2026-03-12 09:18:17 )
If you want to use AI coding assistants to build Rust code, then this is the framework you need to look at. Anecdotes say it generates consistently better code. - link [tool] - ( Added: 2026-03-12 09:17:45 )
AgentDiff is a CLI tool that hooks into Claude Code and tracks every file change with its prompt, reasoning, and task context. Think git blame, but for the why behind AI-generated code. Works with any language, any codebase. - link [tool] - ( Added: 2026-03-10 19:08:46 )

TECH

Newspeak House, The London College of Political Technology, is an independent residential college founded in 2015. Our mission is to study, nurture and inspire emerging communities of practice across civil society and the public sector in the UK. - link [opinion] - ( Added: 2026-03-11 14:22:09 )

AWS

A new and comprehensive resource for learning about DevSecOps and cloud security - link [best-practice] - ( Added: 2026-03-10 19:25:59 )

Generated on 2026-03-17 by Bookmark Manager | 10th Mar 26 to 16th Mar 26 | Total bookmarks: 26

Follow me on LinkedIn or GitHub