Developer Builds Voice-Controlled AI Coding Tool to Work While Walking Outside

·6 views

Software developer Benoit Hirbec created Squad33, a macOS app that lets users control AI coding agents entirely by voice, after chronic back pain in March 2026 forced him to find an alternative to desk-based work. The tool uses Whisper for transcription on a Mac, routing spoken instructions to Claude Code or Opencode, with responses read aloud through earbuds on a paired phone. This setup allows Hirbec to dictate tasks during outdoor walks, with AI agents handling development work in parallel git worktrees while he moves on to the next feature. He reports that listening to agent output is less mentally draining than reading it at a screen, and that voice input removes the keyboard fatigue that often limits detail in written prompts. Squad33 is currently available as a free macOS beta and works with existing Claude Code or Opencode subscriptions rather than providing its own model access.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

One-Page Charter and Linter Script Proposed to Prevent AI Agent Pilot Failures

A software development post argues that most AI agent pilots fail not due to model quality but because of unclear ownership and poor handoff structure. The author proposes a single-page charter assigning three distinct roles — scout, scribe, and signer — each with defined responsibilities and a strict one-way handoff sequence. A hard-coded stop rule and a named revert command are required fields, ensuring the pilot has a clear exit path before it begins. A lightweight Python linter, designed to run in CI, validates the charter by rejecting missing fields, malformed dates, and placeholder text such as 'tbd' or 'todo'. The entire system is intended to fit on one wiki page and one script, reducing ambiguity and drift during time-boxed agent experiments.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Why Causal Diagnosis, Not Metric Breaches, Should Trigger AI Agents in Production

Anthropic's AI-Native SDLC Playbook outlines a six-stage software development lifecycle where autonomous agents handle production monitoring, with Stage 6 closing the feedback loop by triggering a Claude session when a metric breaches a statistical control band. The approach uses deterministic detection — no language model decides when to fire — applying Western Electric rules across sigma thresholds to escalate from logging, to read-only diagnosis, to limited action such as opening a pull request. However, a key limitation is that single-metric band watches can miss distributed degradation across dependent services, where no individual threshold is decisively breached. Tools like Causely address this gap by computing causal diagnoses from existing instrumentation, identifying root causes and their downstream effects across the cluster before the agent begins its work. Starting an agent from a named causal issue rather than a raw metric breach means it spends less time reconstructing what broke and more time acting on pre-established evidence.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Engineers Urged to Add Review Boundaries Around AI Code Generators

A software architect argues that using free AI models and servers changes your budget but not your security threat model, making a defined review boundary around code generators essential. The proposed architecture treats every AI workspace as ephemeral and disposable, assuming it can be reclaimed mid-run and that model versions may change without notice from providers. Generated code is never written directly to a working repository; instead, it flows through a five-stage pipeline ending in a human reviewer decision before anything reaches the main branch. A shell script and Python tool are proposed to capture each run's output as a structured 'packet' containing a diff, model fingerprint, and file classification, giving reviewers clear context. The author emphasizes that prompt-level restrictions are insufficient and that egress denial and sandbox-layer controls must be enforced at the infrastructure level.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Freeze Your Error Taxonomy Before AI Agents Generate Code, Case Study Shows

A software engineering case study demonstrates how AI coding agents produce inconsistent HTTP error mappings when given no predefined error taxonomy to work from. Without a frozen contract, an agent assigned the same failure mode may return different HTTP status codes and incorrect retry semantics across separate generations. The proposed fix involves committing a machine-readable JSON file that defines each error code's HTTP status, retry behavior, message key, and log level before any code generation begins. A SHA-256 hash of that contract file is stored in the repository and verified in CI, preventing silent modifications during automated regeneration passes. This approach keeps the generated mapper as a pure function of an immutable contract, removing the agent's ability to invent or drift on policy decisions.

0 comments Read more at DEV Community