Daniel Cárdenas
AI Automation · RAG · Edge ML
Portfolio
I'm Daniel Cárdenas, an applied AI and systems engineer. This site is a curated set of production-oriented case studies: retrieval quality, agent platforms, agentic document workflows, operational data products, Python APIs, and the embedded telemetry that makes edge ML useful in the field.
29
Case studies
11
Open repos
3
Tracks
Work by track
Production-oriented case studies across RAG, agent platforms, LLM automation, CRM and finance workflows, OCR, field devices, and edge ML — each with architecture notes and measurable outcomes where possible.
A channel-aware agent platform that turns conversations and visual process sources into governed SOPs and flowcharts, with parallel agent work, typed tools, durable state, and validated delivery.
Parallel agent collaboration with explicit ownership, durable callbacks, isolated workspaces, and human-controlled acceptance
An internal workflow platform for evidence verification, approvals, signatures, audit trails, notifications, and controlled billing handoffs.
One workflow foundation supports verification-only and full-signature paths
A read-only CRM intelligence layer that mirrors HubSpot customers and prospects into Supabase for account, owner, status, and whitespace analysis.
Typed TanStack Start dashboard for customers, prospects, account detail, pipeline metrics, roles, and whitespace
A local-first household finance system with an audited SQLite ledger, explicit FX handling, budgets, wallets, debts, and a private Hermes MCP interface.
One audited ledger for income, expenses, reimbursements, savings, wallets, and debts
A bounded software-delivery control plane that routes coding work across models while isolating implementation, preserving human state, and enforcing independent acceptance.
Separate implementation, acceptance, and human release authority
Multi-step document-agent workflows that turn conversations, attachments, and feedback into validated, template-controlled SOPs and Work Instructions.
Internally deployed Slack workflow for document intake, generation, validation, delivery, and feedback
RAG, voice/document workflows, evals, and Python services that can be tested and deployed.
STM32, telemetry, OTA safety, and ML pipelines that connect real devices to cloud systems.
Operational dashboards, reconciliation tools, and cloud-backed automations for business users.
I help teams turn messy documents, device telemetry, and business processes into maintainable AI systems with clear APIs, measurable quality, and deployable demos.