Managing RAG Costs, Agent Reliability Tests, and AI Operational Risks
What this edition covers
7 AI tools and development stories curated from seven sources on 17 August 2026, including Cutting RAG inference costs 6x starts with deciding what never reaches the LLM; DeepSeek's top-ranked V4 Flash stumbles on real agent tasks as its prices surge; Robert Harris the use of a generative AI model for chest X-rays in a large radiology practice.
This is a Pro briefing
The tools covered are listed below with their sources. The written summary and the “why this matters” workflow note for each one are part of the Pro edition.
Upgrade to Pro — €25/monthTools and stories covered
-
1. VentureBeat
Cutting RAG inference costs 6x starts with deciding what never reaches the LLM
-
2. VentureBeat
DeepSeek's top-ranked V4 Flash stumbles on real agent tasks as its prices surge
-
3. Radiology Business
Robert Harris the use of a generative AI model for chest X-rays in a large radiology practice
-
4. TechCrunch AI
Stripe will reportedly acquire AI gateway startup OpenRouter for $7B+
-
5. Law.com
Legal AI Evolves in Australia: Law Firms Take AI From Use Cases to Workflows
-
6. PhocusWire
AI tools are becoming a single point of failure for hotels: How to reduce the risk
-
7. Columbia Undergraduate Law Review
Roundtable #36: Scraping By: Generative AI and the Limits of Cross-Border Governance
Get the next briefing by email
A 3-minute read, three times a week. Free.
Subscribe free