owulveryck
AP2 and A2A: two agents working together and getting paid (in tokens)
Show HN: A deterministic governance harness for agentic development loops
https://github.com/owulveryck/poc-agentic-platform
I genuinely think that autonomous code generation is the future. But today we are facing a problem: we cannot be confident enough in the result produced by an LLM. The problem is its way of working. Even with strong directive such as “make a button blue”, we cannot be sure that the button will be blue (maybe the context has contradictory informations). This POC is based on hooks and is...
Codifying the Rules: Building the Platform Behind the Agentic SDLC
What Happens When AI Agents Refuse to Work Until They're Paid
Re:From Isolated Agents to Agentic Mesh: Orchestrating SDLC with A2A a...
on Friday June 26, 2026 @09:17AM (#48686272)
I am curious : is this format with scrolling and figure that is appearing on the flow is good for understanding or does it generate noise ?
From Isolated Agents to Agentic Mesh: Orchestrating SDLC with A2A and AP2
Re:Who Does What? Team Topologies for the Agentic Platform
on Wednesday June 24, 2026 @02:35AM (#48656005)
This is an interesting feedback. I do that a lot to guide the reader’s system 1.
I like reading article that have those emphasis.
Maybe this is too much. I will investigate what are the good proportions.
Re:Who Does What? Team Topologies for the Agentic Platform
on Tuesday June 23, 2026 @09:56AM (#48645064)
I fully agree
Re:Who Does What? Team Topologies for the Agentic Platform
on Tuesday June 23, 2026 @09:31AM (#48644696)
And thank you for your comment, no offense taken. I post here to get valuable feedback like yours.
Re:Who Does What? Team Topologies for the Agentic Platform
on Tuesday June 23, 2026 @09:04AM (#48644374)
Because as a consultant I see that this model (TT) is a proven solution to the problems of cognitive load that prevent models to scale.
It will require some adaptations indeed, but I trust that this is a missing piece in the integration of AI in organisations.
But I get your point and this is the reason it share it on a personal blog and not on my company blog or in a more trustworthy source of truth.
Re:Who Does What? Team Topologies for the Agentic Platform
on Tuesday June 23, 2026 @08:50AM (#48644161)
Thank you for the feedback.
I actually use AI as a ghost writer, but I am guilty: I usually tend to add too many concepts for a single article (even without AI).
I usually follow Divio’s documentation to reference explanations and references, but it is not suitable for a blog post
Re:Who Does What? Team Topologies for the Agentic Platform
on Tuesday June 23, 2026 @07:38AM (#48643456)
(Op here)
I genuinely think that multi-agent is a probable future to enable coding at the scale of a big corporation.
I agree and I did not see it work yet, but the trial were most likely on small scale where it is simply over engineering.
(Btw : I do not sell tokens. I I think distributed the work through agents in a plateform is a way to control costs by optimizing specialised agents)
Who Does What? Team Topologies for the Agentic Platform
Vibe Coding at Scale? Engineering Strikes Back
Things I wish I had been taught about coding agents for engineering
See, Act, Correct: three levers for working with a code agent
What I learned by building an agentic system in Go to generate Google slides
An agentic system from scratch to generate Google slide deck from templates
The Agentic Mesh: Cognitive Automation at Scale
Re:The Agentic Mesh: Cognitive Automation at Scale
on Sunday May 31, 2026 @04:51AM (#48344087)
I (co)wrote an article with some ideas about an agentic mesh with principle I took from the data-mesh.
The main idea is that an agent is a product and the value will come from the agentic ecosystem in a company. The article also explain a breadcrumb to bring agentic into companies.
The Agentic Mesh: Cognitive Automation at Scale
Re:Show HN: A simple MCP Server in bash
on Wednesday May 07, 2025 @11:27AM (#43916971)
Just for fun and educational purpose: this is a simple MCP server in shell that helps understanding how it works under the hood without third party libraries.
Just a toy, and very incomplete, but hopefully useful.
Show HN: A simple MCP Server in bash
MCP's 3 U's: Making a Tool Useful, Usable, and Used by and for an LLM
MCP's 3 U's: Making a Tool Useful, Usable, and Used by and for an LLM
Show HN: GoMCPTest: Go Playground for Model Context Protocol Experimentations
Show HN: Gomcptest – A Go toolkit for testing LLM agents (MCP) with VertexAI
https://github.com/owulveryck/gomcptest
I built a Go toolkit that helps test and interact with Model-Calling-Protocol (MCP) tools, primarily for developing and understanding agentic systems. It currently works with Google's VertexAI SDK.What it does:- Provides a basic set of tools for testing MCP implementations- Includes a CLI that emulates Claude Code functionality- Offers an OpenAI API v1 compatible server (with some...
Re:Ghostwriter – use the reMarkable2 as an interface to vision-LLMs
on Saturday February 08, 2025 @01:15AM (#42980826)
At some point I wanted to turn goMarkableStream into a MCP server (model context protocol).
I could get the screen, but without “hack” I couldn’t write the response back.
Re:Ghostwriter – use the reMarkable2 as an interface to vision-LLMs
on Saturday February 08, 2025 @01:12AM (#42980811)
Awesome.
I wanted to try to implement this for months. You did a really good job.