
What happened
Ampersend built a pay-per-intelligence routing layer on top of Amazon Bedrock AgentCore Payments, allowing AI agents to autonomously select models by capability tier, pay per request, and operate within spending budgets. The system completed end-to-end integration—including wallet management, x402 protocol signing, and settlement on the Base network—in under two weeks.
Why it matters
Agent builders previously faced months of infrastructure work to implement wallet management, payment signing, spending limits, and integrations with each provider's billing system. AgentCore Payments handles the full payment lifecycle—managed wallets, session-level budget enforcement, x402 protocol negotiation, and observability—so developers can focus on agent logic instead of payment plumbing.
What to watch
The two-hop payment pattern routes payments from agent to Ampersend to the upstream model provider (such as BlockRun), abstracting away provider complexity while keeping agents within deterministic spending boundaries they cannot override. This model demonstrates what agentic commerce looks like in practice: discovery, evaluation, selection, and payment for services within a governed and auditable framework.
Summaries like this, in your inbox every morning.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Docker published an analysis of major AI coding agent incidents from October 2024 to February 2026, including…

Using ClickCapture screenshots of Robocopy Scheduler, Gemini 2.0 Flash-Lite produced a structured parameter ta…

A solo Amazon reseller uses Claude's scheduled tasks to run shipping requests, shipment notices, inventory syn…

A weekend solo engineer asked Claude Code to move a skill that triggers CodeRabbit reviews every 65–70 minutes…

A Zenn guide says vague prompts like "add a nice animation" carry no spec, so Claude or ChatGPT decides elemen…

After two ✓-marked items turned out wrong post-publication — a nonexistent "創業枠(200万円)" and a 3-month photo ru…
