Agent Reliability
Is my agent's data fresh, behavior observable, and safe to run?
← All topics · Subscribe by email · RSS feed · llms slice (14d)
-
Agent Reliability — June 10, 2026
Perplexity launches 'Search as Code': agents write Python to compose retrieval, rerank, and dedup primitives directly; LlamaParse adds word/line/cell-le…
retrieval-architecture · agentic-search · reranking · cost · ingestion · parsing
-
Agent Reliability — June 8, 2026
Microsoft open-sources OmniVec, an embedding pipeline platform that auto-syncs vectors with changing operational data on Azure; Volcengine open-sources …
embeddings · ingestion-pipeline · vector-sync · azure · open-source · context-database
-
Agent Reliability — June 6, 2026
Microsoft Foundry IQ knowledge bases lift evidence recall up to 54% with agentic retrieval tiers; Cohesity Gaia patents embedding-based RAG over backup …
agentic-retrieval · semantic-rerank · hybrid-search · microsoft · embeddings · knowledge-ingestion
-
Agent Security — June 6, 2026
Microsoft MXC SDK enforces policy-driven agent containment on Windows and WSL; Microsoft documents Claude Code GitHub Action secret exfiltration via Rea…
runtime-containment · policy-enforcement · windows · agent-identity · prompt-injection · ci-cd
-
Observability & Evals — June 6, 2026
Microsoft Foundry extends tracing and evals to any agent framework at Build 2026; Amazon Bedrock AgentCore ships Lambda code-based evaluators for CI gat…
tracing · evaluation · opentelemetry · multi-turn · microsoft · agentcore
-
RAG & Knowledge — June 6, 2026
Microsoft Foundry IQ knowledge bases lift evidence recall up to 54% with agentic retrieval tiers; Cohesity Gaia patents embedding-based RAG over backup …
agentic-retrieval · semantic-rerank · hybrid-search · microsoft · embeddings · knowledge-ingestion