2026

Which of Your Work Is Actually Verifiable?

TL;DR: Two well-argued pieces already say the same thing about the AI era: AI takes over the work that is cheap to verify, and human value moves to the expensive verification that is left. Jason Wei c…

AISolutionsArchitectVerificationAgenticAICareerDevelopment
From Prompt to Context to Memory: The Arc, Grounded on AWS

A while back I argued that context engineering had quietly replaced prompt engineering as the skill that decides whether an agent is any good [1]. That piece was the framing. This one is the build. I …

AIContextEngineeringAmazonBedrockRAGAgentMemory
Terms in the 402: The Payment Challenge That Also Tells You What You're Licensed To Do

TL;DR: An HTTP 402 usually just quotes a price. In the last post I argued that terms (what you’re licensed to do) and payment (the money) are different layers that belong together on one origin. Here …

AIAgentsAgenticWebContentMonetizationHTTP402x402RSLPublishing
Worried About Germany? You Should Be. What Can We Actually Do?

TL;DR: Yesterday the AfD won the Saxony-Anhalt state election with 43.8%. Its state branch has been formally classified as confirmed right-wing extremist since 2023. If that worries you, good. It shou…

MediaLiteracyMisinformationSocietyAIDemocracy
Why Doesn't the Web Just Use HTTP? It Does — and It Doesn't

TL;DR: Publishers are building dedicated ā€œcontent ingest APIsā€ to sell access to AI agents, and the obvious question is: why not just use HTTP, which already delivers the content and, with x402, can n…

AIAgentsAgenticWebContentMonetizationHTTP402x402AWSWAFPublishing
The Psychology of "We'll Call You"

TL;DR: ā€œWe’ll call youā€ turns a relationship into an asymmetric wait: one side owns the timeline and the information, the other can only sit with it. Decades of research explain why the silence often …

PsychologyTrustCommunicationLeadershipHiring
The Gate That Couldn't See the Defect

TL;DR: I am building narrated demo videos for an upcoming conference, and one of them went back for rework six times. Three of my own quality checks were involved, and each failed differently. One ran…

EvaluationVoiceCloningTTSQualityEngineeringSageMaker
Who Pays to Un-Bias Your Agent?

TL;DR: If brands will pay to tilt an AI’s answer, someone will pay for the answer that isn’t tilted. That splits the agent economy in two: cheaper, ad-funded agents whose answers lean toward whoever p…

AIAgentsAgenticWebContentMonetizationAmazonBedrockStrategy
A Content Pipeline That Doesn't Trust Itself

TL;DR: My AI content pipeline once recorded a claim as ā€œVerifiedā€ in two separate gate reports while the cited page said the opposite — both gates had matched the page’s topic, not the claim. Another …

AIContentAIAgentsAIQualityVerification
Every Catalog Wants to Be an MCP Server

TL;DR: AWS just shipped an open-source MCP server for the Registry of Open Data — 1,100+ datasets from 400+ organizations (NASA, NOAA, NIH, the Allen Institute), now discoverable by asking your AI ass…

MCPAgenticAIAWS