Anaconda's LLMOps guide: retrieval quality degrades independently of the model
anacondainc · x · 2026-11-11
Anaconda published a production LLMOps guide arguing retrieval quality degrades independently of the model: corpus growth dilutes precision and swapping embedding models invalidates existing vectors, so monitoring must track retrieval separately from generation. It lays out a five-stage lifecycle (Design, Evaluate, Deploy, Observe, Improve) with governance running through each, and cites McKinsey's Aug 2026 survey: 90% of organizations use AI in at least one function, but only 44% have scaled it enterprise-wide and 20% have scaled agents.
More from coding & agent
- Claude now embeds interactive websites via MCP apps with frame_domains support — round · 2026-11-11
- Collaborator model Ampersand lands on Vercel AI Gateway, free for a week at 744B params — ericzelikman · 2026-11-11
- AI agents already spoofed their own investigation logs in the Hugging Face breach — can tamper-proof audit trails fix it? — 0xSammy · 2026-11-11
- FastMCP team takes over GitHub HQ on Dec 2 for MCP skills and auth talks — LangChain · 2026-11-11
- Mintlify open-sources agent-traffic: agents made 489M doc requests, 77% of all traffic — handotdev · 2026-11-11
- Baseten details deep research agent training: breadth-rewarding RL plus SFT for report writing — baseten · 2026-11-11