The 15-page PDF lays out a four-step loop—write, consolidate, recall, apply—to give AI agents a persistent memory. Agents log each attempt, distill lessons into reusable insights, review those insights before new tasks, and skip past dead ends. Anthropic engineers use this approach in Claude Code to boost agent performance.

• A 15-page PDF from a senior Anthropic engineer outlines a four-step memory loop for AI agents: Write, Consolidate, Recall, Apply
• The system distills messy task logs into a handful of reusable lessons rather than replaying full transcripts
• Agents use these distilled lessons to skip previously failed approaches even on new tasks
• Anthropic has already integrated this loop into Claude Code, with setup scripts available to inspect

This TLDR roundup covers AWS’s plan to start selling its Trainium AI chips to outsiders, and Midjourney’s launch of a full-body ultrasound scanner for its new health spas. It also highlights NASA’s award to Relativity Space for a Mars orbiter, the shift to usage-based AI pricing, the deep dive on agent loop architecture, plus Intel’s stock jump and warnings about the “infinite workweek.”

• AWS is in talks to sell Trainium AI chips to outside data centers, directly challenging Nvidia despite its own capacity already being maxed out.
• Midjourney is launching a (non-AI) full-body ultrasound scanner called the "Midjourney Scanner," planning 50,000 units starting with a branded SF spa.
• AI companies are shifting from flat-fee subscriptions to usage-based pricing, pushing customers to monitor and justify each query's cost.
• Intel's stock jumped after Trump and Apple announced a US chipmaking partnership under CEO Lip-Bu Tan.

Yanli Liu clones Anthropic’s open-sourced finance agent repo and identifies four key architectural patterns—single-source dual-delivery, write-holder isolation, schema-validated trust boundaries, and prompt-based guardrails—that set regulated-industry agents apart from generic frameworks. She also flags a 20% gap of non-code compliance artifacts (risk registers, accuracy declarations, transparency docs) needed to meet the EU AI Act’s high-risk requirements.

• Anthropic's finance agent templates use one markdown system prompt per agent that drives both interactive and headless modes, with no runtime prompt assembly
• Each agent splits duties across subagents (one writes, one reads, one enforces rules) to limit damage if the LLM misbehaves, mirroring bank workflows
• Data between agents is passed as regex/length-constrained JSON schemas rather than free text, blocking prompt injection from masquerading as instructions
• Guardrails like "recommend, don't decide" are prompt-based, not hard-enforced, and 3 of the 10 templates trigger EU AI Act high-risk rules on August 2, leaving roughly 20% of compliance work (risk registers, accuracy statements) still needed

Anthropic released a two-hour course led by the engineer behind Claude Code that walks you through building self-managing Claude agents. It covers terminal integration, file-system memory, hallucination-blocking hooks, and scaling to large codebases. Whether you’re a beginner or advanced user, you’ll finish ready to use Claude professionally.

• Anthropic released a free two-hour course on building Claude agents, led by the engineer who writes Claude Code
• Covers terminal integration, file-system-based memory, and hooks designed to catch and block hallucinations
• Includes guidance on scaling agents to large codebases via isolated environments and multi-file task orchestration
• Shows real failure examples (missing dependencies, misread logs) and how to harden pipelines against them