Progress Agentic RAG Expands Multi-Source Retrieval

// 1h agoPRODUCT UPDATE

Progress Agentic RAG Expands Multi-Source Retrieval

Progress Agentic RAG’s Smart Agent breaks complex questions into sub-questions, routes them across Knowledge Box data, MCP-connected apps, and the web, then checks whether evidence is sufficient before answering. REMi scores groundedness, answer relevance, and context relevance while tracing outputs to their source document, chunk, and model. [Official feature page](https://www.progress.com/agentic-rag/features/smart-agent)

// ANALYSIS

This is a credible move from single-corpus RAG toward governed retrieval orchestration, though the hard part shifts from wiring tools together to proving routing decisions are reliable at enterprise scale.

–Smart Agent reduces custom orchestration code by handling planning, source selection, decomposition, and iterative retrieval.
–MCP support lets live CRM, ERP, and ticketing data complement indexed documents, making cross-system questions more practical.
–REMi adds useful per-answer observability, but automated relevance scores still need task-specific evaluations and human review.
–The feature fits Progress’ broader enterprise positioning around traceability, access controls, and benchmarked RAG quality. [Announcement](https://www.progress.com/blogs/progress-agentic-rag-adds-a-smart-agent-plus-native-teams-and-wordpress-support)

// TAGS

progress-agentic-ragragagentmcpevaluationsearchenterprise-ai

DISCOVERED

1h ago

2026-11-06

PUBLISHED

1h ago

2026-11-06

RELEVANCE

8/ 10

AUTHOR

Prompt Engineering

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

RESEARCH9m ago

Coca-Cola Compresses Tool Outputs Into Latents

Tsinghua researchers’ Coca-Cola replaces verbose tool observations with continuous latent tokens injected directly into an agent’s embedding space. Its action-preserving training targets next decisions rather than text reconstruction, reducing token consumption by 70.01%-89.24% and runtime by 24.45%-55.97% across web-search QA benchmarks.

BENCHMARK1h ago

Kimi K3.1 Pro Narrows Frontier Gap

Moonshot’s open-weight Kimi K3.1 Pro approaches Claude Opus 5.5 on reported agentic coding benchmarks while undercutting it on price, with a 1M-token context window and weights now available. The broader snapshot also highlights Liquid AI’s compact LFM3 models for on-device workloads and a rapidly shrinking open-versus-closed gap. Kimi technical blog: https://www.kimi.ai/blog/kimi-k3-1-pro; Liquid AI LFM3: https://www.liquid.ai/blog/lfm3

UPDATE1h ago

Creem adds auto-refilling credit packs

Creem now lets AI developers sell prepaid credit packs, meter usage per generation or API call, and automatically refill balances before they run dry. The feature is part of Creem’s broader usage-based billing stack.