Summary

AI product leader with 15+ years, now owning end to end delivery of GenAI and agentic AI. I define agent behavior (system prompts, tool schemas, context management, human in the loop boundaries and guardrails), run evals (task completion, tool selection, failure recovery), and set agent level metrics (cost per task, escalation, time to resolution) tied to business outcomes. I prototype and build hands on with Claude and Claude Code daily, read code (Python, TypeScript), and engage engineering on architecture, cost and latency tradeoffs. From consulting, I frame technology tradeoffs for executives up to a bank's presidency; and from AI leadership, I manage AI hype with realistic expectations. Systems Engineer with an MBA. English C1.

Experience

Head of AI · Agentic AI Product: Agent Behavior, Evals & Delivery · DigitalHubAssist LLC Oct 2024 · Present

Remote · Applied AI / SaaS (Anthropic partner program)

Own end to end delivery of agentic AI: I built Agent Squad, multi step autonomous agents (AI co workers) in production (dev, QA, PMO, content). I define agent behavior (system prompts, tool schemas via function calling, context management, human in the loop boundaries and guardrails), run evals and observability (Langfuse) across task completion, tool selection and failure recovery, and iterate on evidence. I set agent level metrics (cost, escalation, resolution) tied to business outcomes. Under my leadership the company reached Registered Partner status in Anthropic's partner program.
AI forward: I prototype and build with Claude and Claude Code daily to validate hypotheses and de risk decisions, read code (Python, TypeScript), and engage engineering on architecture, cost and latency. My cloud is a modern stack (Supabase, Vercel, Cloudflare), with Azure in enterprise production work. I built AI4Managers to frame AI realistically for leaders.

Consulting Manager · Client Facing Delivery & Executive Tradeoff Framing · NTT DATA Colombia Apr 2021 · Oct 2024

Bogotá, Colombia · Consultancy · Financial services (banking)

Primary delivery lead on the office's largest client account: led discovery, prioritization and risk conversations with senior stakeholders, and framed tradeoffs for executive audiences up to the bank's presidency. Drove a platform to production under real ambiguity, de risking the hardest dependencies first and delivering in phased rollout.
Balanced business value, feasibility, cost and timelines; recovered a program in crisis by resolving critical blockers (recognized at the corporate level), with the lowest attrition on the account.

Project Manager / Delivery Lead · Client Software & Digital Products · VASS (2018·21) · GlobalHitss (2015·18) · Tecnocom (2012·15) 2012 · 2021

Bogotá, Colombia · Digital delivery

Shipped client digital products across sectors: modernized a pension fund's channels (millions of users, LATAMDIGITAL 2019 award), digital commerce, and public sector platforms, from discovery to launch.

Core Competencies

End to End Agentic AI Product Delivery (Discovery → Phased Rollout) Agent Behavior (System Prompts · Tool Schemas · Context · Working Memory) Human in the Loop Boundaries & Guardrails · Non Deterministic Systems Evals (Task Completion · Tool Selection · Failure Recovery · Safety) · Observability (Langfuse) Agent Level Metrics (Cost per Task · Escalation · Time to Resolution) + Business KPIs Prototyping with Claude · Claude Code · AI Forward · Reads Code (Python · TypeScript) Deep AI (LLMs · RAG · Agentic · Prompt/Context Engineering) · Cloud (Azure) Consulting / Client Facing · Executive Framing · Managing AI Hype · MBA

Summary

Experience

Education

Core Competencies