DEV Community: Vince Elizaga

I Built an Interactive Playground for Understanding AI Agent Harnesses

Vince Elizaga — Wed, 04 Nov 2026 16:49:07 +0000

When we talk about AI agents, we usually focus on the model, prompts, and tool calls. But there's a lot more happening behind the scenes.

Context engineering, memory, guardrails, policies, approvals, execution, tracing, evaluations, and releases are all part of building an agent system. Yet these pieces are rarely explored together in a way that's easy to understand.

I wanted to see these pieces work, not just read about them.

So I built Harnesswalk, an open-source, interactive environment for exploring how an AI agent harness works, one node at a time.

What is Harnesswalk?

Think of it as a visual playground for understanding AI agent engineering.

Instead of looking at a static architecture diagram, you can interact with an agent's execution flow and see what happens at each stage.

Some things you can explore:

Step-by-step execution: Follow a request as it travels through the harness, one node at a time.
Prompt inspection: See the exact prompt being prepared before a model call.
Component inspection: Explore the code and configuration behind individual nodes.
Human-in-the-loop: Approve or reject tool actions before execution.
Event replay: Go back and inspect what happened during an execution.
Experimentation: Disable individual nodes and observe how the system behaves without them.

The idea is to make the architecture tangible rather than treating the agent as a black box.

A note on scope

Harnesswalk currently models a governed assistant with policies, approvals, audit, memory, and a release gate.

It's a teaching model, not a debugger for existing agents or a coding-agent harness with shell access and subagents.

It's still evolving, and there are plenty of things I'd like to improve. But the webapp is already available, runs in the browser without installation, and supports an offline mode using a scripted model.

What's next?

I'm interested in exploring how this could evolve beyond an interactive learning environment.

Some directions I'm considering include multimodal agent workflows, more extensible component contracts, and eventually a registry where developers can add or replace capabilities such as RAG, memory implementations, model providers, and evaluation workflows.

For now, I'm focusing on making the existing experience useful and learning from people building agentic systems.

Give it a try

🌐 Explore the Harnesswalk webapp

📦 Source code on GitHub

📝 A deeper look at the architecture

It's open source under the Apache-2.0 license.

I'd love to hear from other developers:

What's missing from the architecture? Which components would you add, replace, or remove? And how would you approach making an agent harness more observable and easier to understand?

Feedback, ideas, and contributions are welcome!

Rovy Part 3: Initial outdoor tests with onboard 4G/LTE modem and sensors

Vince Elizaga — Mon, 30 Oct 2023 22:02:18 +0000

We’re now moving on to the third phase of the project, which involves the integration of an onboard 4G/LTE modem to enable remote outdoor mobility. Additionally, a new set of sensors has been introduced for telemetry transmission via AWS IoT Core using MQTT.

The testing also extends to outdoor conditions, providing valuable assessments of the data gathered from temperature, humidity, GPS (including coordinates, speed, and altitude), IR range, and battery voltage during the rover’s full-load operations.

Checkout the full write-up on my blog:

https://www.vynci.dev/posts/robot-sensors-4g-lte-modem

Rovy Part 2: Video stream from onboard camera using AWS KVS

Vince Elizaga — Sat, 14 Oct 2023 21:03:03 +0000

Overview

This is the second part of the project that tackles on sending a video stream from the rover's onboard camera through AWS Kinesis Video Stream (KVS) using the WebRTC communication protocol.

If you want to dive right away into the code, you can check it out here:

Rover Hardware (branch -> rovy-part-2)
Mobile App (branch -> rovy-part-2)

I will be pushing updates to the repositories as I add more things (i.e. sensors) into the rover as I progress in the future, so the main branch might look different by the time you are reading this. As for this article, please refer to the specified branch.

I have a full write-up of this in my blog. You can check it out here here.

Weekend project: Remote-controlled Rover over the Internet using AWS IoT Core and React.

Vince Elizaga — Mon, 09 Oct 2023 19:48:43 +0000

Source Code:

Rover Hardware (branch -> rovy-part-1)
Mobile App (branch -> rovy-part-1)

I have a full write-up of this in my blog. You can check it out here here.

Rovy Part 1: Control motors remotely using AWS IoT Core (MQTT)

Vince Elizaga — Mon, 09 Oct 2023 18:55:25 +0000

This is the first part of the project which focuses on controlling the motors on a rover over the internet via MQTT.

If you want to dive right away into the code, you can check it out here:

Rover Hardware (branch -> rovy-part-1)
Mobile App (branch -> rovy-part-1)

I will be pushing updates to the repositories as I add more things (i.e. video stream) into the rover as I progress in the future, so the main branch might look different by the time you are reading this. As for this article, please refer to the specified branch.

I have a full write-up of this in my blog. You can check it out here here.