Tag: agents

All the articles with the tag "agents".

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

  9 Jul, 2026

  Corridor reviews AI-generated code inside the coding loop instead of after commit. I imported a real AWS control plane, planted an IDOR bug in a PR, and watched what it caught.

• How AgentCore Gateway Turns Any API Into an Agent Tool

  9 Jul, 2026

  AgentCore Gateway is a managed front door between agents and tools. It handles inbound auth, outbound auth, and protocol translation once, so any API or Lambda becomes an MCP tool that every connected agent can call. Here is how the wiring actually works.

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

  9 Jul, 2026

  A vector store keeps three things per record — a key, an array of floats, and a bag of metadata. Your document text is stored as metadata, and a 2 KB limit on the filterable part is what quietly breaks ingestion.

• Which Tier Does Your Vector Workload Live On?

  9 Jul, 2026

  Amazon S3 Vectors dropped the entry cost of vector storage on AWS to near zero. The question that matters now is which tier of the cost/latency curve your workload sits on — and why agents belong on the cheap one.

• Zed on Bedrock Makes the Agent Harness Portable

  6 Jul, 2026

  Wiring Zed to Amazon Bedrock turns Zed's agent harness into a provider-portable coding surface across the frontier models your account can reach.

• Agent Sprawl Is a Skills Problem

  6 Jul, 2026

  I had hundreds of skills scattered across agent harnesses, repos, and drafts folders. No single view of what existed, what was current, or what was actually wired in. The market is hitting the same wall.

• The Cross-App Workflow Cost $5.44. Here's How We Got It to $0.17.

  1 Jun, 2026

  A hybrid agent running browser research + desktop spreadsheet creation cost $5.44 baseline. Optimizing each leg independently — Playwright for the browser, CLI-first prompt for the computer use desktop leg — brought it to $0.17. The browser leg did most of the damage.

• The Test Isn't Whether the Agent Picks the Right Tool. It's What Happens When the Tool Fails.

  31 May, 2026

  I built a hybrid agent expecting the routing to be the demo. The actual demo turned out to be what happened when a tool call failed and the outer model retried with a different approach — twice in two runs.