Sophia Antipolis | Engineering-first | EU jurisdiction

Applied AI. Integrated into real workflows.

I design and implement AI systems that reduce operational friction — not demos, not experiments, but working processes embedded in real environments.

Document Intelligence · Workflow Automation · Controlled AI Systems

agent_audit_trace.log
10:42:01 input_received source="RFP_Project_Alpha.pdf" size=4.2mb
10:42:02 initializing_context mode=retrieval_augmented
10:42:04 Data boundary: No external egress (local execution)
10:42:05 risk_detected: clause=3.4 • type=Ambiguous SLA • severity=HIGH
"Vendor shall provide reasonable support."
-> Flagged for Legal review.
10:42:06

Tools I build with

Mistral AI LangGraph Docker Python Azure n8n

Modes of Engagement

Two ways to apply AI to complex workflows — depending on your stage.

Engineering Service

Studio

Design and implementation of AI-assisted workflows. Workflow analysis → architecture design → controlled deployment. Focus on operational clarity, reproducibility, and measurable impact.

Workflow mapping & system design
AI-assisted process implementation
Guardrails & traceability
Production deployment support

Structured scope · Measurable outcomes · Working systems

Strategic Guidance

Advisory

Strategic guidance for teams integrating AI internally. Focus on feasibility, governance, and long-term maintainability.

Workflow feasibility evaluation
Architecture & responsibility boundaries
Risk and governance design
Team enablement

Architecture-first · Risk-aware · Sustainable systems

Deeply integrated with your stack.

I don't replace your tools. I connect AI systems to them.

J
Jira / Linear
G
GitHub / GitLab
S
Slack / Teams
N
Notion / Wiki
P
Postgres / SQL
G
Google / O365
API
Custom Webhooks
P
PDF / Docx

Applied Projects

Selected implementations translating workflow architecture into operational systems.

E-commerce Infrastructure

StikrAI

AI-driven commerce platform converting prompts into physical merchandise.

Problem

Fragmented infrastructure between concept and production.

Approach

AI generation → structured product pipelines → fulfillment automation.

Live product
AI Generation Webhooks Stripe
Infrastructure Layer

MCP Gateway

Infrastructure layer enabling AI systems to access external tools safely.

Problem

AI systems isolated from execution environments.

Approach

Validation layers, permission boundaries, traceable execution.

Active development
Protocol Design Security Monitoring
Document Intelligence

clarify.run

Document intelligence system extracting structured knowledge from complex documents.

Problem

Critical information locked in unstructured formats.

Approach

AI analysis → structured extraction → validated outputs → workflow triggers.

Pilot-stage
NLP Extraction Validation

Building Direction

Focus areas shaping the next phase of applied AI systems.

Document Intelligence

Extracting structured knowledge from unstructured documents and triggering downstream workflows.

Agent Infrastructure

Building safe interfaces between AI systems and external tools with validation and monitoring.

Workflow Automation

Connecting AI generation to operational pipelines with quality gates and fulfillment systems.

-> StikrAI

Control & Observability

Measure impact, reduce risk, keep humans in the loop.

Implementing guardrails, audit trails, and traceability layers for deterministic AI operations.

-> Cross-project pattern

Core Principles

How I approach building reliable AI systems inside real organizations.

01

Ground Truth First

Systems are constrained to existing data and documented schema. No fabrication. When uncertainty exists, the system raises an ambiguity alert instead of generating an assumption.

02

Controlled Automation

Automation must be measurable, observable, and reversible. Every action generates an audit trail. Every decision can be traced back to its inputs and reasoning path.

03

Human Oversight

AI systems operate within guardrails and clear responsibility boundaries. Critical decisions require human approval. Escalation paths are explicit, not emergent.

04

Operational Impact

The goal is reduced friction and improved decision speed — not technical novelty. I measure success by time saved, risks caught, and operational confidence gained.

Deployment Options

LLM Inference
Hosted (EU): Commercial APIs with EU data processing
Your infrastructure: Open-weight models (e.g. Llama, Mistral)
Data Storage
Hosted (EU): Managed Vector DB
Your infrastructure: Self-hosted Qdrant/Pgvector
Connectivity
Hosted (EU): Public API
Your infrastructure: Private VPC / VPN
Audit Logs
Hosted (EU): Retention agreed per project
Your infrastructure: Kept in your systems; SIEM export

Engineering FAQ

How do you prevent hallucinations in technical specs?
I use a "Ground Truth First" architecture. The system is not allowed to generate new facts: it only extracts and compares data against your existing documentation or schema. If it is unsure, it raises an "Ambiguity Alert" instead of guessing.
Does our code or data leave our infrastructure?
Not when the system runs in your infrastructure. The whole stack (model, vector database, orchestration) is deployed on your servers or private cloud (Azure/AWS VPC) with open-weight models, so nothing depends on an external API.
What is the difference between AI Agents and traditional RPA?
Traditional RPA follows rigid, rule-based scripts that break when inputs change. AI Agents use Large Language Models to understand context, handle variations, and make judgment calls. They can process unstructured data (documents, emails, logs) and adapt to edge cases that would crash RPA bots.
What is deterministic AI and why does it matter?
Deterministic AI produces consistent, predictable outputs for the same inputs. Unlike chatbots that can give different answers each time, the agents I build follow explicit state machines (using LangGraph) where every decision is traceable, auditable, and reproducible. This is critical for engineering workflows where mistakes are expensive.
Which LLM models do you use?
It depends on the latency, accuracy and compliance requirements of the workflow. Hosted setups use commercial model APIs with EU data processing; setups in your own infrastructure use open-weight models such as Llama or Mistral. The exact model is chosen per project.
How do you ensure AI outputs are trustworthy?
Three mechanisms: (1) Guardrails validate inputs and outputs against defined schemas. (2) Confidence scoring flags uncertain decisions for human review. (3) Audit logging records every state transition and LLM call, creating a complete trace for compliance and debugging.
What happens when the AI Agent is unsure?
The agents I build include human-in-the-loop checkpoints. When confidence falls below the threshold set for the workflow, the agent pauses, presents its analysis with its reasoning, and asks a person to confirm before it continues. This prevents silent failures.
Can AI Agents integrate with your existing tools?
Yes. I build integration layers for Jira, Linear, GitHub, GitLab, Slack, Teams, Notion, Confluence and custom APIs. The agents don't replace your tools—they orchestrate them, without disrupting existing processes.
How do you handle GDPR?
aixagent.io is based in Sophia Antipolis, France, and operates under EU jurisdiction. Hosted setups use EU-based infrastructure where the provider offers it; setups in your own infrastructure keep all processing inside it. The GDPR obligations of each project are documented with you before work starts.

What I don't do.

I don’t build chatbots for chit-chat.
I don’t automate without guardrails.
I don’t move fast and break production systems.

"Engineering decisions deserve engineering-grade AI."

Bring one document, incident, or release
you regret.

Email me about a workflow

One email is enough to start.