~/krishna_dhakal

Profile photo
#AWS#Bedrock#AgentCore#Agents#AI

Agents in Amazon Bedrock AgentCore — Fundamentals, Patterns, and the Agent vs Workflow Divide

> June 12, 2026

What an agent is at a fundamental level, how any agent code plugs into Amazon Bedrock AgentCore, the different architectural patterns an agent can follow, the full set of AgentCore platform features you can lean on, and a crisp explanation of when you want an agent versus a workflow.

// read_more →

PII & PHI Detection and Redaction in AI Pipelines — with AWS Bedrock Guardrails

> July 1, 2025

Why PII and PHI must be protected in AI systems, the different ways to detect and redact sensitive data, and how AWS Bedrock Guardrails fits into a RAG pipeline built on S3, Bedrock Knowledge Base, and LangChain.

$ ls /blog →

// projects

> escrow-agent

Multi-signature transaction platform with a Go backend and PostgreSQL, implementing cryptographically secure payment orchestration workflows.

> crowdsourced-book-platform

Next.js educational platform for children, with dynamic content management and interactive learning modules.

> textql

LLM-driven text-to-SQL pipeline using Google Gemini and FastAPI; normalizes natural language queries into structured SQL via prompt-engineered LLM calls.

> ocr-grocery-discount-designer

Automated retail asset generation using Tesseract OCR, Google Custom Search, and PIL — eliminating manual design work for weekly promotional materials.

> loki-log-aggregator

Observability stack using Grafana Loki, Prometheus, and Kubernetes for centralized log monitoring and alerting at scale.

> react-chimebox

Zero-setup feedback widget for static websites — users embed a single script tag to collect structured feedback. Built with Supabase, React, Netlify Functions, and Cloudflare Turnstile.

// experience

  • $ March 2025 – Present

    Software Engineer – AI/ML & Full-Stack @ Leapfrog Technology

    Architected end-to-end RAG pipelines and AI workflow automation using AWS Bedrock, Qdrant, and llama.cpp. Built an AI-powered Video Assistant and a conversational chatbot for a Nursing Management Platform with agentic orchestration over REST APIs.

  • $ Jan 2024 – July 2024

    Professional Services Consultant – AI & Search @ Upland Software

    Engineered enterprise-scale semantic vector search over 2M+ SharePoint documents using Azure OpenAI embeddings and Azure AI Search. Delivered an OCR + OpenAI pipeline for an Australian client to extract and index structured data from unstructured PDFs.

  • $ Nov 2023 – April 2024

    Software Engineer – Full-Stack @ Sherpa Technologies

    Led migration of a credit card dispute management platform from legacy infrastructure to GCP Cloud Functions using Node.js, TypeScript, and PHP. Drove cross-functional performance triage across client-facing web and mobile applications.

  • $ April 2021 – April 2022

    Software Engineer – Blockchain & Web3 @ 0chain LLC

    Re-architected a React-based blockchain explorer and maintained two Go CLI tools (zwalletCLI, zboxCLI) for 0chain's decentralized storage protocol. Migrated the business website to a Netlify CMS + GatsbyJS stack and contributed to a TypeScript + WebAssembly storage migration.

  • $ April 2020 – Nov 2023

    Full-Stack Developer @ Freelance

    Built production-grade platforms including a real-time media app (AWS S3, Redis, WebSockets) and SEO-optimized 3D animation sites using Three.js. Automated client workflows with Pipedream and AssemblyAI, and upgraded a financial trading platform built on Angular and TradingView APIs.

// products

// under_construction

// testimonials

Jane Smith

"John's work is fantastic! He delivered exactly what we needed."

- Jane Smith, CEO of XYZ Company

Bob Johnson

"Working with John was a pleasure. He's professional and skilled."

- Bob Johnson, Freelance Designer

// roadmap

  1. Learn advanced JavaScript frameworks
  2. Contribute to open-source projects
  3. Develop a mobile app

// stack

© 2024 krishna_dhakal