DEV Community

Amit profile picture

Amit

I run agents as daily infrastructure — not demos. Artificial Curiosity Labs is where I document what actually works: agent fleets, skills as institutional memory, cost discipline, and the gap between

An Agent That Can Pay for Its Tools

An Agent That Can Pay for Its Tools

Comments
9 min read
MPP vs x402: Two Competing Answers to the Same HTTP 402

MPP vs x402: Two Competing Answers to the Same HTTP 402

Comments
4 min read
A Browser That Pays

A Browser That Pays

Comments
4 min read
AgentCore Registry Is a Governed Catalog for Agent Interfaces

AgentCore Registry Is a Governed Catalog for Agent Interfaces

Comments
6 min read
What the Trace Knew That the Logs Didn't

What the Trace Knew That the Logs Didn't

Comments
11 min read
Multi-Agent Memory: Agents That Actually Share Context

Multi-Agent Memory: Agents That Actually Share Context

Comments
6 min read
Beyond Semantic Retrieval: Metadata Filtering in Agent Memory

Beyond Semantic Retrieval: Metadata Filtering in Agent Memory

Comments
5 min read
Bedrock Managed Knowledge Bases as a Native Gateway Tool

Bedrock Managed Knowledge Bases as a Native Gateway Tool

Comments
5 min read
Harness vs. Runtime: When to Graduate

Harness vs. Runtime: When to Graduate

Comments
7 min read
Build a Regression Suite for an Agent

Build a Regression Suite for an Agent

Comments
6 min read
AgentCore Browser: A Managed, Isolated Browser an Agent Can Drive

AgentCore Browser: A Managed, Isolated Browser an Agent Can Drive

Comments
8 min read
Grok 4.6 Is on Amazon Bedrock. Here Is How to Wire Grok Build to It

Grok 4.6 Is on Amazon Bedrock. Here Is How to Wire Grok Build to It

Comments
7 min read
Where AgentCore Sits in the Architecture

Where AgentCore Sits in the Architecture

Comments
7 min read
What You Build on the AgentCore Harness

What You Build on the AgentCore Harness

Comments
6 min read
The AgentCore Map: What Each Piece Actually Does

The AgentCore Map: What Each Piece Actually Does

Comments
10 min read
Who May Call What: Per-User Authorization on AgentCore With Cedar

Who May Call What: Per-User Authorization on AgentCore With Cedar

Comments
8 min read
Browser Use vs. AgentCore Browser: Two Managed Browsers, and Which Layer Each One Wins

Browser Use vs. AgentCore Browser: Two Managed Browsers, and Which Layer Each One Wins

Comments
9 min read
Two Ways to Authorize an Agent Tool: IAM or OAuth on Amazon Bedrock AgentCore Gateway

Two Ways to Authorize an Agent Tool: IAM or OAuth on Amazon Bedrock AgentCore Gateway

Comments 2
7 min read
AgentCore Runtime: Where an Agent Actually Runs

AgentCore Runtime: Where an Agent Actually Runs

Comments
5 min read
AgentCore Memory: What an Agent Remembers When the Session Is Gone

AgentCore Memory: What an Agent Remembers When the Session Is Gone

Comments
10 min read
Four Tools, One Loop: The AgentCore Knowledge Worker

Four Tools, One Loop: The AgentCore Knowledge Worker

Comments
8 min read
AgentCore Code Interpreter: When the Agent Has to Actually Run the Math

AgentCore Code Interpreter: When the Agent Has to Actually Run the Math

Comments
7 min read
Benchmark saturation is real. The price collapse is an illusion.

Benchmark saturation is real. The price collapse is an illusion.

Comments
3 min read
Dictation and Meeting Notes, Fully Local: Rebuilding Wispr Flow and Granola Without the Cloud

Dictation and Meeting Notes, Fully Local: Rebuilding Wispr Flow and Granola Without the Cloud

Comments
6 min read
Building Voice Agents with LiveKit, Cartesia, and AWS

Building Voice Agents with LiveKit, Cartesia, and AWS

Comments
6 min read
The AI Chips After NVIDIA

The AI Chips After NVIDIA

Comments
12 min read
The Five-Layer AI Stack Is an Inverted Pyramid

The Five-Layer AI Stack Is an Inverted Pyramid

Comments
8 min read
MCP Became Stateless: Migrating a Real AgentCore Gateway

MCP Became Stateless: Migrating a Real AgentCore Gateway

Comments
6 min read
Building an Autonomous AI News Agent on Step Functions and AgentCore

Building an Autonomous AI News Agent on Step Functions and AgentCore

Comments
9 min read
Open Data Wasn't Missing. The Interface Was.

Open Data Wasn't Missing. The Interface Was.

Comments
6 min read
Every Way to Attribute Cost on Amazon Bedrock, Live-Tested

Every Way to Attribute Cost on Amazon Bedrock, Live-Tested

Comments
8 min read
Web Search as a Managed Connector: Wiring Amazon Bedrock AgentCore WebSearch Into Any Agent

Web Search as a Managed Connector: Wiring Amazon Bedrock AgentCore WebSearch Into Any Agent

Comments
9 min read
Does Graphify Actually Help an AI Coding Agent?

Does Graphify Actually Help an AI Coding Agent?

Comments
9 min read
Prompt Caching Is a Harness Design Problem, Not an API Toggle

Prompt Caching Is a Harness Design Problem, Not an API Toggle

Comments
7 min read
Flux LoRA fine-tuning on fal.ai is shockingly simple

Flux LoRA fine-tuning on fal.ai is shockingly simple

Comments
2 min read
Building AI Voice Agents with Amazon Nova Sonic and LiveKit: Patterns, Architecture, and a RAG Latency Surprise

Building AI Voice Agents with Amazon Nova Sonic and LiveKit: Patterns, Architecture, and a RAG Latency Surprise

Comments
8 min read
Which Tier Does Your Vector Workload Live On?

Which Tier Does Your Vector Workload Live On?

Comments
8 min read
What Actually Gets Stored When You Put a Vector in S3 Vectors

What Actually Gets Stored When You Put a Vector in S3 Vectors

Comments
6 min read
How AgentCore Gateway Turns Any API Into an Agent Tool

How AgentCore Gateway Turns Any API Into an Agent Tool

1
Comments
8 min read
I Pointed an AI Code-Security Tool at My Own Control Plane

I Pointed an AI Code-Security Tool at My Own Control Plane

Comments
7 min read
Skills Are a Git-Native Distribution Primitive

Skills Are a Git-Native Distribution Primitive

Comments
6 min read
Agent Sprawl Is a Skills Problem

Agent Sprawl Is a Skills Problem

Comments
6 min read
Zed on Bedrock Makes the Agent Harness Portable

Zed on Bedrock Makes the Agent Harness Portable

Comments
14 min read
Zed Is Open Source and Can Drive Every Frontier Model on Bedrock

Zed Is Open Source and Can Drive Every Frontier Model on Bedrock

Comments
6 min read
Your Agent Doesn't Need the Secret. It Needs the Result.

Your Agent Doesn't Need the Secret. It Needs the Result.

Comments
5 min read
One Token for Everything Is Still One Token

One Token for Everything Is Still One Token

Comments
6 min read
Go-to-Market Was a Relay Function. AI Makes It a Decision Function.

Go-to-Market Was a Relay Function. AI Makes It a Decision Function.

Comments 1
5 min read
Reset Windows Are Product Design

Reset Windows Are Product Design

Comments
7 min read
How To Optimize Agent Subscriptions Without Getting Tricked

How To Optimize Agent Subscriptions Without Getting Tricked

Comments
7 min read
Autonomous Agents Break Flat-Rate Pricing

Autonomous Agents Break Flat-Rate Pricing

Comments
7 min read
AI Subscriptions Are Secretly Usage Models

AI Subscriptions Are Secretly Usage Models

Comments
13 min read
Your AI Agent Needs Communication Modes, Not a Voice Clone

Your AI Agent Needs Communication Modes, Not a Voice Clone

Comments
9 min read
What Is an Agent — And What Isn't

What Is an Agent — And What Isn't

Comments
9 min read
What Is an Agent Harness — The Infrastructure That Makes Agents Actually Work

What Is an Agent Harness — The Infrastructure That Makes Agents Actually Work

Comments
8 min read
What Is a Tool — The API Call Your Agent Makes on Your Behalf

What Is a Tool — The API Call Your Agent Makes on Your Behalf

Comments
9 min read
What Is a Skill — Why Methodology Resets Every Session Without One

What Is a Skill — Why Methodology Resets Every Session Without One

Comments
8 min read
We're All Builders Now

We're All Builders Now

Comments
5 min read
Voice Is a Layer, Not a Setting

Voice Is a Layer, Not a Setting

Comments
6 min read
Two AI interfaces. Same desktop. Completely different jobs.

Two AI interfaces. Same desktop. Completely different jobs.

Comments
4 min read
The Website Is Not the Product

The Website Is Not the Product

Comments
3 min read
loading...