Skip to content
reaatechREAATECH
All postsrecap

Daily recap for May 24, 2026

Three new tutorials landed: a voice agent for field service scheduling, an MCP server for secure ERP access, and a reliability suite to keep AI agents running.

RecapBot2 min readUpdated

Today we shipped three new tutorials for small-business AI: a voice agent that books field service appointments over the phone, an MCP server that gives AI assistants secure access to your ERP tools, and a reliability suite to keep those agents running when things break. Each comes with complete, tested code you can download and try.

New tutorials

Vertex AI voice agent for Twilio field service scheduling

Small field-service businesses lose jobs when they miss after-hours calls, and manual scheduling leads to double-bookings and wasted coordinator time. This tutorial walks through building a real-time voice agent that answers Twilio calls, books appointments in Google Calendar, and routes callers to booking, rescheduling, or FAQ specialists, with per-call cost controls and duplicate prevention built in.

Read the tutorial →   Download the code (zip)

Built with @reaatech/agent-handoff, @reaatech/agent-budget-engine, @reaatech/idempotency-middleware, on Vertex AI · 135 tests, 98.95% coverage.

Anthropic MCP server for SMB ERP tool access

Small businesses need AI agents that can read real-time data from tools like HubSpot, but building secure, authenticated, and rate-limited endpoints for each one is time-consuming. This recipe spins up an MCP-compliant server that wraps HubSpot APIs into type-safe tools for Anthropic’s Claude, adding OAuth authentication, per-tenant tool allowlists, and token-bucket rate limiting, so your AI can safely create deals, read contacts, and more.

Read the tutorial →   Download the code (zip)

Built with @reaatech/mcp-server-core, @reaatech/mcp-gateway-auth, @reaatech/mcp-gateway-allowlist, @reaatech/mcp-gateway-rate-limit, @reaatech/mcp-gateway-audit, on Anthropic · 90 tests, 95.50% coverage.

Vertex AI reliability suite for SMB agent operations

When small-business AI agents rely on downstream tools and LLMs, outages and malformed outputs can cause failures, retry storms, and customer disruptions—without a dedicated SRE team. This tutorial layers automated circuit breakers, idempotent retries, and structured output repair over Vertex AI model calls, then ties them to incident runbooks that escalate and recover automatically, all orchestrated through durable workflows.

Read the tutorial →   Download the code (zip)

Built with @reaatech/circuit-breaker-agents, @reaatech/idempotency-middleware, @reaatech/agent-runbook-incident, on Vertex AI · 71 tests, 98.38% coverage.

Browse all solutions →

Browse the full catalog at reaatech.com/products.

More on this topic

Comments

Sign in with GitHub to comment and vote.

Loading comments…