DevDebug Team - AI Tinkerers Dublin: Agentic Architect Hackathon with Lyzr AI
AI Tinkerers - Dublin
Hackathon Showcase

DevDebug Team

Team led by an Insight Centre emerging technologies researcher with an MSc from DCU, skilled in Digital Twins, IoT integration, GIS, and data analytics.

1 member

DevDebug — an AI debugging assistant that argues with itself before giving you a fix. Developers have lost hours to an error message that turned out to be a one-line fix. The deeper problem isn’t the lack of AI debuggers, it’s that single-LLM debuggers hallucinate confidently. They propose a fix, you trust it, and it makes things worse.

DevDebug solves this by implementing Lyzr’s ACE-V (Proposer–Challenger–Judge) tri-agent governance protocol for code debugging. A developer pastes an error message and optional config file. Four agents execute in strict sequence:

  1. Intake parses the error and config into structured data (language, runtime, packages, error class).
  2. Proposer (Perplexity sonar-pro) generates a root-cause hypothesis and concrete fix, verified against the npm registry and live web search.
  3. Challenger (Claude Sonnet, different model family by design) actively tries to falsify the Proposer’s fix — checking for version conflicts, deprecated APIs, runtime mismatches, and transitive dependency issues.
  4. Judge (GPT-5.1, a third independent model) issues a final verdict with a confidence score, changing the Proposer’s recommendation only when the Challenger produces new evidence — never on rhetoric.

The user watches the deliberation live: agent outputs stream into a transcript, evidence cards expand inline, and a final Verdict card auto-scrolls into view with a copyable fix. Because each agent runs on a different model provider, the disagreement is genuine, not theater.

Why this matters: The ACE-V pattern means the output can be trusted in a way a single-LLM debugger’s output cannot. The architecture is general, any high-stakes agent decision benefits from an adversarial challenger and an evidence-only judge. DevDebug is a deployable instance of a pattern that scales to any domain where hallucinated confidence is dangerous.

Anthropic Claude Sonnet 4.6 — Intake Agent (structured parsing) and Challenger Agent (adversarial reasoning). Lyzr ACE-V Protocol — the tri-agent governance pattern (Proposer → Challenger → Judge) is the core architectural choice that gives Stack Doctor its trust properties. Lyzr Agent Studio — hosts and runs the four agents (Diagnosis Orchestrator manager + Intake / Proposer / Challenger / Judge sub-agents) Lyzr Architect (architect.new) — prompt-to-deployed agentic application. Generated the PRD Next.js + Tailwind CSS — frontend Next.js UI OpenAI GPT-5.1 — Diagnosis Orchestrator (Manager) and Judge Agent (neutral arbiter Perplexity sonar-pro — Proposer Agent and deployment pipeline from prompts and observability. chosen for live web-grounded evidence gathering. deliberately on a third model family to prevent vendor bias). deployed on Lyzr's hosted environment. generated by Architect including the streaming output multi-agent orchestration graph npm Registry API — Custom OpenAPI tool integrated for live package version verification. state passing between agents