Daily recap for June 4, 2026

Today we shipped 11 new step-by-step tutorials for small-business AI, covering intake automation, voice agents, document pipelines, observability, and more. Each one includes a downloadable project and a guide that walks you from pnpm install to a running system.

New tutorials

Intake Automation Agent for Solo Immigration Attorney

This agent automates the intake process for a solo immigration attorney. It screens prospective clients, checks for conflicts, classifies their legal need, and generates a case summary in minutes instead of half an hour, so the attorney can respond faster and spend more time on billable work.

Read the tutorial → Download the code (zip)

Built with @reaatech/agent-mesh, @reaatech/hybrid-rag, @reaatech/agent-memory, @reaatech/guardrail-chain, @reaatech/agent-handoff, @reaatech/llm-cache, on agnostic · 139 tests / 99.11% coverage.

Deposition Prep Summarizer for Plaintiff Litigation Paralegal

This tool ingests deposition transcript PDFs, extracts key facts and contradictions, and produces a structured, citable summary—cutting down the paralegal's research time from hours to minutes.

Read the tutorial → Download the code (zip)

Built with @reaatech/hybrid-rag, @reaatech/agent-eval-harness-suite, @reaatech/agent-memory, @reaatech/llm-cost-telemetry, @reaatech/context-window-planner, @reaatech/agent-replay, on agnostic · 76 tests / 96.93% coverage.

Google Gemini Voice Agent for Clinic Appointment Scheduling

A voice AI receptionist that answers phone calls for clinics, transcribes speech with Deepgram, understands intents with Gemini, and books appointments via EHR integration—reducing missed calls and freeing staff for in-clinic care.

Read the tutorial → Download the code (zip)

Built with @reaatech/voice-agent-core, @reaatech/voice-agent-mcp-client, @reaatech/voice-agent-telephony, @reaatech/session-continuity, on Google Gemini · 155 tests / 97.70% coverage.

Mistral AI Document Pipeline for Xero Expense Report Processing

This pipeline extracts expense data from PDF receipts and Excel sheets, uses Mistral AI to parse line items, and pushes them into Xero as invoices—eliminating manual data entry and reducing errors.

Read the tutorial → Download the code (zip)

Built with @reaatech/structured-repair-core, @reaatech/llm-cost-telemetry, @reaatech/context-window-planner, @reaatech/agent-budget-engine, on Mistral · 60 tests / 100.00% coverage.

Google Gemini Runbook Automation for PagerDuty SMB Incidents

A CLI tool that pulls PagerDuty service and incident data, uses Google Gemini to generate narrative runbooks, and outputs markdown files—so small DevOps teams always have a recovery plan when incidents strike.

Read the tutorial → Download the code (zip)

Built with @reaatech/agent-runbook, @reaatech/agent-runbook-analyzer, @reaatech/agent-runbook-alerts, @reaatech/agent-runbook-health-checks, @reaatech/agents-markdown, @reaatech/confidence-router-core, on Google Gemini · 73 tests / 95.90% coverage.

OpenAI Lead Intake for BigCommerce Small Business Sales

This Express server receives BigCommerce contact-form webhooks, classifies inquiry intent with OpenAI, routes high-confidence leads to auto-replies or Slack notifications, and escalates low-confidence ones—ensuring every customer gets a quick response.

Read the tutorial → Download the code (zip)

Built with @reaatech/confidence-router, @reaatech/agent-handoff, @reaatech/agent-handoff-routing, @reaatech/session-continuity, @reaatech/structured-repair-core, on OpenAI · 79 tests / 96.74% coverage.

Cohere Agent Mesh for Multi-Channel Customer Support Triage

This agent mesh uses Cohere's classification to route support tickets from email, chat, and social channels to the right specialist agent, with confidence thresholds that escalate uncertain cases to humans—keeping triage costs in check.

Read the tutorial → Download the code (zip)

Built with @reaatech/agent-mesh, @reaatech/agent-mesh-router, @reaatech/agent-mesh-confidence, @reaatech/confidence-router-core, @reaatech/llm-cost-telemetry, on Cohere · 99 tests / 95.04% coverage.

OpenAI Guardrail Layer for SMB Customer Chat Safety

A drop-in shim over the OpenAI SDK that adds a configurable chain of guardrails—detecting prompt injection attacks, redacting PII, and filtering toxic content—so small businesses can deploy chatbots safely without a security team.

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 OpenAI · 55 tests / 99.13% coverage.

OpenAI Voice Agent for Aircall Small Business Support

This voice agent answers Aircall calls, handles FAQs about hours and pricing using OpenAI, and hands off to human agents when it can't resolve—catching after-hours calls and reducing peak-time hold times.

Read the tutorial → Download the code (zip)

Built with @reaatech/voice-agent-core, @reaatech/voice-agent-stt, @reaatech/voice-agent-tts, @reaatech/agent-handoff, @reaatech/llm-cost-telemetry, @reaatech/structured-repair-core, on OpenAI · 70 tests / 97.40% coverage.

Anthropic Document Pipeline for Klaviyo SMB Email Campaigns

This pipeline loads product catalogs and customer segments, drafts personalized email content with Claude, repairs any malformed JSON, and pushes campaigns to Klaviyo—automating email marketing for small teams.

Read the tutorial → Download the code (zip)

Built with @reaatech/hybrid-rag, @reaatech/structured-repair-core, @reaatech/agent-budget-engine, @reaatech/llm-cache, @reaatech/prompt-version-control, @reaatech/llm-cost-telemetry, on Anthropic · 92 tests / 99.55% coverage.

Anthropic LLM Observability for SMB AI Operations

This instrumentation layer wraps Anthropic API calls with OpenTelemetry spans, tracks token costs per request, enforces daily budgets, and exports telemetry to Langfuse or Phoenix—giving small businesses visibility into their AI spend without a custom stack.

Read the tutorial → Download the code (zip)

Built with @reaatech/otel-genai-semconv-anthropic, @reaatech/llm-cost-telemetry, @reaatech/otel-genai-semconv-core, @reaatech/otel-genai-semconv-exporters, @reaatech/agent-budget-otel-bridge, on Anthropic · 85 tests / 100.00% coverage.

Browse all solutions →