Hands-on prompt engineering and LLM evaluation. Built around a diagnose-then-ship loop: forensic transcript critique ▎ that names the exact failure mode, paired with a fixer that produces complete, deployment-ready rewrites — not ▎ vague advice.
Send an exported n8n workflow and get back a severity-ordered defect report — broken connections, leaked credentials, sticky-note collisions, Code-node logic flaws — plus a runnable regression test suite for its Code nodes.
Turn your AI pilot data into a traceable decision pack with TCO, ROI, NPV, payback, sensitivity analysis, evidence gaps, risks, and clear next steps.
Un cycle Brainstorm → Spec validée → Plan à cases à cocher → TDD strict → Review de conformité, conçu pour les devs qui construisent des SaaS pilotés par IA (générateurs, agents, outils no-code) en HTML/CSS/JS vanilla ou Node/Express, avec intégrations multi-fournisseurs (Anthropic, OpenAI, Gemini, Mistral). Exemples d'usage : "ajoute une fonctionnalité X à mon générateur", "intègre un nouveau fournisseur IA", "refonds ce module"
Three blind reviewers audit an AI agent's or contractor's done report, cross-examine each other, and give one accept/reject verdict.
Audit Excel workbooks before you trust, send, or deliver them. Detect formula, structure, data-quality, hidden-content, dependency, validation, and consistency risks with traceable evidence — without modifying the original file.
Audit AI agents, Skills, MCP configurations, tool permissions, and coding-agent setups for prompt injection, excessive agency, credential exposure, data leakage, unsafe code execution, supply-chain risks, memory risks, missing approval controls, and runaway autonomy. Get a calibrated Security Score, Audit Confidence, evidence-backed findings, remediation steps, verification checks, and residual-risk analysis.
Analysez logs, diagnostics, erreurs et éléments techniques fournis afin d’identifier des causes probables, prioriser les anomalies et préparer un plan de correction.
Systematic QA of CLI tools and pipelines across multiple real workspaces using SFDPOT heuristics. Executes structured test flows, evaluates consistency oracles, collects evidence, and produces a structured bug report with P1/P2/P3 priorities and a release readiness verdict.