Every week, I organize 400 to 700 links into roughly 60 categories as part of my ongoing effort to learn about AI. This is my personal notebook, which I enjoy sharing with friends… a hobby and a labor of love, rather than a commercial publication or product.
If you arrived here through a search or shared link, this page collects the links I found for RAG for the week ending August 28, 2026.
As part of my learning process, I like to automate the category covers. It gives me a chance to learn Python and APIs.
This week’s cover prompt was written using Claude Opus 4.7, and the image was generated using Nano Banana 2.1.
Category Cover Image Prompt: A 16:9 mid-1980s murder-mystery movie poster of a wide three-story Victorian library-mansion in stark black-and-white pen-and-ink engraving on pure black, with warm amber windows showing a monocled archivist holding a wooden card-catalog drawer, a prim librarian suspect fanning annotated scrolls, still lifes of index cards strung with red thread and open leather books with glowing bookmarks, and one window with the silhouette of a hand sliding a book off a shelf; the identical silver-haired butler in black tailcoat stands in the open front door holding a silver tray with a wax-sealed envelope stamped with a tiny book-and-magnifier symbol, with the fat rounded white title 'RAG' centered above the roofline. Campy spooky theatrical lighting, dense crosshatching, symmetrical frontal composition, no extra text or logos.
This Week in RAG News
Summary by Claude Sonnet 5.5 based on this week’s links:
The clearest RAG-relevant item is Cohere Parse 5, announced as a new document parsing model. Cohere says it offers the strongest price-performance on the market and keeps per-page prices at an industry low, aimed at high-volume enterprise work. Parsing is the step that turns documents into text a retrieval pipeline can use, so cost per page matters at scale.
A separate post points to a free MongoDB guide on agent memory. It argues for a discipline called Memory Engineering and says memory should be treated as more than RAG. The rest of the links are Cohere company news, such as a TIME 100AI mention for Joelle Pineau and a Canada and Germany partnership post, and don't add much on RAG itself.
This summary was generated by Claude Sonnet 5.5 to help you explore the links below. Rest assured, I select, organize, and check the links by hand in Google Sheets, and write the introduction and personal commentary in The Main Newsletters myself each week as a labor of love.
This week's links related to RAG
Cohere Parse | Enterprise Intelligence at Scale
https://cohere.com/blog/parse
A practical free guide on building AI agent memory → “Bringing Attention To Memory In AI Agents and Agentic Systems” by @MongoDB It makes the case for a whole new engineering discipline: Memory Engineering. Some of the useful tips inside: – Treat memory as more than RAG or”
https://x.com/TheTuringPost/status/2091339301804216338
How do you go from jailbreaking your PlayStation to CEO of Canada’s leading LLM provider? You go to the University of Toronto. “When you go to @UofT, you get raised into AI.” – @aidangomez”
https://x.com/cohere/status/2092365111415419205
Introducing Cohere Parse 5. Our newest document parsing model with the strongest price-performance on the market. Ideal for high-volume enterprise work. Get high-quality parsing accuracy while keeping per-page prices at an industry low.”
https://x.com/cohere/status/2092962399754055863
Canada and Germany are not just discussing the future of technology. We are building it.”
https://x.com/cohere/status/2092626691310952667
Cohere’s Chief AI Officer @jpineau1 has been named to this year’s TIME 100AI list, recognizing the world’s most influential people in artificial intelligence. Joelle has been shaping modern research in Canada for over two decades. We couldn’t be prouder to have her on our team.”
https://x.com/cohere/status/2093005855104913680
Cohere will support you. Build cool things, here.”
https://x.com/cohere/status/2093085350377758848
Leave a Reply