The Author
Carlos Chinchilla Corbacho
Senior AI Engineer building ML systems that run in production at scale: real-time recommendation, multi-agent systems, deep learning on edge devices. PhD candidate on testing LLM-based agents and multi-agent systems: how to tell whether they work and where they break. Trust, but Trace covers the engineering side of both: what survives between research papers and production systems.
This site does not cover, describe, or comment on confidential or proprietary systems or work tied to the author’s employment or institutional affiliations. All content is independent.
- Email hello@cchinchilla.dev
- LinkedIn /in/cchinchilla
- GitHub @cchinchilla-dev
Open source
Contributions
Merged work in Linux Foundation projects for AI agents.
- 01a2aproject/a2a-pythonA2A protocol Python SDK: async client lifecycle and an agent card signature fix (RFC 8785), shipped in its 1.0.
- 02a2aproject/a2a-goA2A protocol Go SDK: executable examples for pkg.go.dev and typed streaming errors over REST.
- 03i-am-bee/beeai-frameworkBeeAI Framework: task cancellation in its A2A server that no longer stops other tasks, agent cloning that keeps client settings, and an MCP prompt-arguments fix.
Own projects
Open-source tools
Python, on PyPI. AI-assisted and author-owned, under a public AI policy.
- 2026On PyPIagentloomA deterministic LLM workflow orchestrator for production. You define the execution graph; the LLM only fills in content. Circuit breakers, rate limiters, token budgets and OpenTelemetry traces as first-class primitives.PythonPydanticOpenTelemetry
- 2026On PyPIagentanvilContract-based testing for LLM agents and multi-agent systems, with deterministic record and replay. Runs on its own or on top of AgentLoom.PythonA2APytest
Also: swiftbar-devkit, macOS menu bar tools for local development, and vocal-biomarkers-ml, companion code to the IEEE Access 2024 paper.
Research
Publications
Peer-reviewed. Reviewer for IEEE Access; Program Committee, DITTET (4th and 5th editions). Full list: Google Scholar · ORCID.
- 2025PaperAdvanced Machine Learning and Deep Learning Approaches for Estimating the Remaining Life of EV Batteries — A ReviewBatteries
- 2024PaperApplication of Machine Learning Techniques for the Characterization and Early Diagnosis of Respiratory Diseases such as COVID-19IEEE Access
- 2024ChapterFrom Waste to Wealth: Circular Economy Approaches for Recycled EV Batteries in Energy StorageNew Trends in Disruptive Technologies, Tech Ethics, and Artificial Intelligence
- 2024PaperAutomated Identification of Cylindrical Cells for Enhanced State of Health Assessment in Lithium-Ion Battery ReuseBatteries