Daily recap for May 25, 2026

We published 10 new tutorials for production‑grade small‑business AI today. The headline is a QuickBooks invoice pipeline that extracts data from PDFs and emails, but we also shipped guardrails for Databricks, a voice agent for housecall bookings, a competitive intelligence mesh, and more.

What we shipped

Anthropic Document Pipeline for QuickBooks Online Invoice Automation

This tutorial shows how to build an invoice processing pipeline that takes PDFs, email attachments, or scanned images, extracts structured data like line items and totals using Anthropic’s Claude, and syncs to QuickBooks Online. It uses REAA’s hybrid‑rag stack for document ingestion and chunking, and includes a budget engine to cap per‑invoice LLM costs. Perfect for small businesses that spend hours on manual data entry.

Read the tutorial →
Download the code (zip)

Built with @reaatech/hybrid-rag, @reaatech/hybrid‑rag‑ingestion, @reaatech/hybrid‑rag‑evaluation, @reaatech/hybrid‑rag‑embedding, @reaatech/agent‑budget‑engine, on Anthropic · 51 tests / 95.86% coverage.

Databricks Security Guardrails for SMB Data Pipelines

A pluggable security layer that sits in front of Databricks model‑serving endpoints to redact PII, block prompt injections, and enforce content policies — no model retraining needed. It uses a chain of guardrails that scan incoming requests and outgoing responses, with all activity logged for audit. If you’re sending customer data to Databricks‑hosted LLMs, this can prevent costly data leaks.

Read the tutorial →
Download the code (zip)

Built with @reaatech/guardrail-chain, @reaatech/guardrail‑chain‑config, @reaatech/guardrail‑chain‑guardrails, @reaatech/guardrail‑chain‑observability, on Databricks · 111 tests / 100% coverage.

Mistral AI Lead Intake for Clio Legal Client Onboarding

A lead intake system for small law firms using Clio. A Mistral‑powered chat qualifies web leads, detects duplicates using hybrid RAG, processes uploaded documents, and creates contacts and matters in Clio through its REST API. It reduces manual data entry and prevents duplicate records.

Read the tutorial →
Download the code (zip)

Built with @reaatech/hybrid-rag, @reaatech/hybrid-rag‑retrieval, @reaatech/hybrid-rag‑embedding, @reaatech/hybrid-rag‑ingestion, @reaatech/agents-markdown, on Mistral · 115 tests / 100% coverage.

Anthropic Lead Intake for SMB Home Services Bookings

An AI‑powered lead qualification system for plumbers, electricians, and HVAC businesses. It uses Anthropic’s Claude to extract structured service requests from web forms and attachments, classifies intent, and routes high‑confidence leads to a booking webhook. Low‑confidence leads can be flagged for human review. Includes session continuity for multi‑turn conversations.

Read the tutorial →
Download the code (zip)

Built with @reaatech/confidence-router, @reaatech/structured-repair-core, @reaatech/agent-handoff, @reaatech/llm-cost-telemetry, @reaatech/session-continuity, on Anthropic · 105 tests / 99.27% coverage.

Perplexity Agent Mesh for SMB Competitive Intelligence

A multi‑agent mesh that continuously monitors competitors using Perplexity’s web‑grounded research. Specialized agents track pricing, news, and product changes, then surface insights in a dashboard. The mesh uses agent classifier, router, and handoff packages to coordinate tasks and control cost.

Read the tutorial →
Download the code (zip)

Built with @reaatech/agent-mesh, @reaatech/agent-mesh‑classifier, @reaatech/agent-mesh‑session, @reaatech/agent-mesh‑router, @reaatech/agent-handoff, @reaatech/llm-cost-telemetry, @reaatech/confidence-router, on Perplexity · 85 tests / 100% coverage.

xAI Grok Reliability Suite for SMB AI Operations

A CLI toolchain that auto‑generates runbooks, runs health checks, and manages circuit breakers for your AI agents. It uses xAI Grok to analyze logs and automatically trip breakers when error rates spike. No dedicated site reliability engineer required.

Read the tutorial →
Download the code (zip)

Built with @reaatech/agent-runbook, @reaatech/circuit-breaker-core, @reaatech/agent-runbook‑alerts, @reaatech/agent-runbook‑health‑checks, @reaatech/circuit‑breaker‑agents, @reaatech/structured‑repair‑core, on xAI Grok · 101 tests / 94.49% coverage.

Mistral AI Lead Intake for Housecall Pro Field Service Bookings

A voice‑powered lead intake system that answers after‑hours calls via Twilio, transcribes speech with Deepgram, and books jobs in Housecall Pro. It uses Mistral AI for structured extraction and includes spend tracking with an agent budget engine.

Read the tutorial →
Download the code (zip)

Built with @reaatech/voice-agent-core, @reaatech/create-voice-agent, @reaatech/voice-agent‑mcp‑client, @reaatech/voice-agent‑telephony, @reaatech/agent‑budget‑engine, @reaatech/structured‑repair‑core, @reaatech/session‑continuity, on Mistral · 105 tests / 99.54% coverage.

Vertex AI Multi‑Agent Handoff for ServiceTitan Dispatch Automation

A dispatch mesh that classifies incoming service requests, routes them via confidence gates, and dispatches technicians in ServiceTitan. It uses Vertex AI (Gemini) for language understanding and REAA’s agent‑mesh packages for coordination. Designed for home service companies juggling manual dispatching.

Read the tutorial →
Download the code (zip)

Built with @reaatech/agent-mesh, @reaatech/agent-mesh‑classifier, @reaatech/agent-mesh‑confidence, @reaatech/agent-handoff, @reaatech/agent‑handoff‑routing, on Vertex AI · 79 tests / 97.44% coverage.

xAI Grok Knowledge Agent for Buildium Property Management Queries

A knowledge agent that answers tenant and manager questions about leases, payments, and maintenance. It syncs Buildium data into a pgvector store and uses xAI Grok with hybrid‑rag retrieval for multi‑turn conversations. Cuts through support bottlenecks by providing instant answers.

Read the tutorial →
Download the code (zip)

Built with @reaatech/hybrid-rag, @reaatech/agent-mesh, @reaatech/llm-router-core, @reaatech/session-continuity, @reaatech/llm-cost-telemetry, @reaatech/hybrid-rag-ingestion, on xAI Grok · 116 tests / 99.28% coverage.

xAI Grok Cost Control for SMB Customer Support Agents

A budget guard that enforces per‑tenant daily spend limits for xAI Grok‑powered support agents. When budgets are hit, it automatically falls back to a cheaper OpenAI model via the llm‑router. Includes cost telemetry and a spend dashboard.

Read the tutorial →
Download the code (zip)

Built with @reaatech/agent-budget-engine, @reaatech/llm-router-core, @reaatech/llm-router-fallback, @reaatech/llm-cost-telemetry, on xAI Grok · 100 tests / 99.55% coverage.

Browse all solutions →

Every solution comes with a downloadable zip and a step‑by‑step walkthrough. Browse the full catalog at reaatech.com/solutions.