Daily recap for May 17, 2026

Today we shipped two new step-by-step tutorials for small-business AI: one for controlling AI agent costs across any provider, another for searching SharePoint documents with a hybrid RAG pipeline. Both come with downloadable code and detailed walkthroughs.

New tutorials

Agnostic AI Budget Control for SMB Agent Workflows

If you run several AI agents for customer support, sales, or ops, unpredictable API costs can eat into margins. This tutorial shows you how to enforce per-session and monthly spending limits across any LLM provider, and automatically route calls to the cheapest model that can handle the task. It combines a budget controller, a multi-provider router, and telemetry into a single Next.js endpoint.

Read the tutorial → · Download the code (zip)

Built with @reaatech/agent-budget-engine, @reaatech/llm-router-core, @reaatech/agent-budget-middleware, @reaatech/llm-router-engine, @reaatech/llm-cost-telemetry, @reaatech/llm-cost-telemetry-aggregation on agnostic · 122 tests / 99.59% coverage.

Anthropic RAG Pipeline for SharePoint Knowledge Search

Employees often waste hours digging through SharePoint libraries, and keyword search rarely finds the right context. This tutorial walks through building a hybrid RAG system that indexes your document libraries, combines vector and BM25 search for accurate answers, and escalates low-confidence results to a human reviewer via Slack. It uses Claude for generation and includes caching and budget middleware to keep costs predictable.

Read the tutorial → · Download the code (zip)

Built with @reaatech/hybrid-rag, @reaatech/hybrid-rag-embedding, @reaatech/confidence-router, @reaatech/agent-budget-middleware, @reaatech/llm-cache on anthropic · 119 tests / 100.00% coverage.

Browse all solutions →

More building blocks ship weekly. See the full product catalog at reaatech.com/products.