Oscar Gracia

Python Automation, Applied AI, and Analytical Workflows.

I build practical Python systems for workflow automation, document retrieval, and reviewable AI-assisted work. My strongest proof is project-backed: orchestration tooling, CLI-first AI utilities, retrieval pipelines, and monitoring-oriented analytical systems.

Technical work grounded in usable workflows.

My current positioning is centered on Python automation, applied AI, document workflows, and analytical infrastructure. I work best on systems that need inspectability, repeatable execution, and clear operational value.

Automation

CLI-first tools, internal workflows, structured execution, state, and validation.

Applied AI

Responses API integrations, structured outputs, retrieval flows, and grounded review.

Analytical Systems

Market-data processing, alerting, monitoring, and operator-facing reporting.

Cost-Aware AI Coding Orchestrator

Proposed multi-agent coding system that routes routine implementation to cheaper models while enforcing budgets, retries, validation, Git checkpoints, and escalation.

  • Cost and timeout controls
  • OpenCode builder workflow
  • Controlled model escalation

Reliable AI Agents

Technical note on constrained agent design: deterministic software for rules and validation, focused LLM use for ambiguous language and reasoning tasks.

  • Controlled orchestration
  • Rules and permissions
  • Code-first reliability

Lead Intelligence Engine

Python CLI workflow for finding, enriching, scoring, and reviewing business leads before manual outreach, with structured OpenAI analysis only on qualified rows.

  • Google Places plus website enrichment
  • Deterministic scoring before LLM use
  • Human-reviewed outreach preparation

Custom KPI Trend Reports for Marketing Agencies

Frontend-only demo of a custom reporting workflow that cleans exported marketing CSVs, flags anomalies, and drafts client-ready KPI summaries for human review.

  • CSV-to-report workflow
  • Trend summaries and anomaly flags
  • No-access-first demo

AI Orchestrator

Terminal-first Python orchestration for bounded coding-task workflows with planning, execution, review, and resumable state.

  • Structured outputs
  • Inspectable execution
  • Workflow reliability

Legal RAG Pipeline

Document-ingestion and retrieval workflow with metadata persistence, validation, and reviewable question-answering over indexed legal materials.

  • Retrieval workflows
  • Document processing
  • Cost-aware controls

ask-cli

Lightweight CLI utility around the OpenAI Responses API with local-file input, attachments, and retrieval-oriented document workflows.

  • Local-first ergonomics
  • Reusable terminal workflows
  • Practical AI tooling

Market Data Analysis And Alerting Infrastructure

Python-based analytical infrastructure for market-data ingestion, time-series processing, monitoring, charting, and operator-facing alerts.

  • Canonical history handling
  • Monitoring and alerting
  • Reviewable analytical support

Where I create the most value.

The strongest fit is technical work where implementation quality matters more than hype: workflow automation, retrieval systems, AI evaluation, technical operations, and documentation-heavy problem spaces.

Good match for

  • Python automation and workflow engineering
  • Applied AI and retrieval pipelines
  • AI evaluation, review, and QA workflows
  • Internal tooling for documentation-heavy teams

Available for remote work and focused consulting.

If you need Python automation, retrieval workflows, or structured AI review support, email is the fastest way to reach me.