# Automation & AI > We built 8 internal tools for our own operations: invoicing, SEO reporting, notifications and a lead qualification bot on the Claude API. Source: https://lastdoorsolutions.com/services/automation-ai ## Before: manual processes eating hours Invoices going out late. SEO reports taking hours to compile. Notifications scattered across five platforms. New enquiries sitting unanswered for hours. Meeting transcripts unread. HR data in spreadsheets. ## After: 8 tools running in production daily Each problem became a tool. Our invoicing tool generates proforma PDFs, sends them via SMTP, tracks payment status, and automates follow-up sequences. Our SEO reporting tool pulls data from GA4, Google Search Console and DataForSEO, runs 66+ content audit checks, and delivers monthly reports automatically. Our notification bridge routes events between Basecamp, Productive.io, Google Chat and Telegram. They run in production daily, managed by PM2 on our own servers, with encrypted credential vaults and audit logging. That same approach applies to your business. ## AI chatbots with production guardrails We ran one against our own enquiries before we offered it to anyone. It held multi-turn conversations with potential customers on the Claude API and captured structured data: service needed, timeline, existing website, company details, budget range. Qualified leads went to our business development team in Google Chat. We retired it in August 2026 when the channel it answered on went quiet. What we keep from it is the part that transfers. The guardrails were hardcoded safety defaults: - A kill switch that turns the model off from outside the code - A daily budget cap ($5 default) - Per-sender rate limiting (5 messages per hour) - A 10-second response timeout - A circuit breaker: 3 failures in 5 minutes triggers a 30-minute cooldown - Spam keyword filtering, scope violation detection, and escalation keyword detection, where asking for a human beats every other check - Every model call logged with token counts, cost, latency and status We also wrote down what we had not built, which is the more useful half: [the 11 checks, and the 4 gaps we never closed](/blog/ai-chatbot-guardrails). If you are putting a model in front of customers, that post is the checklist we would hand you. ## AI agents on our own backlog The useful question about an AI agent is not what it can do. It is what you are prepared to let it do without being asked. We run one against our own backlog. It reads a task off the tracker and works out what is being asked. It branches and writes the code across every repository the change touches, turning a design file into components where there is one. It fixes its own errors rather than stopping at the first, and opens a pull request. Then it stops. A person reviews what it wrote, the same as for anyone else on the team, and a person merges it. That last boundary is the whole design. An agent that can merge is a different risk from one that can only ask. The model, the framework and the integrations are all easier than deciding where that line sits. It is the first thing we work out with a client and the last thing we would let anyone skip. [Orkest](/products#orkest) is where this is heading: our orchestration and operational tooling with AI capabilities, connecting project management, timesheets and an agent in one place. Multi-tenant Laravel 12, React 19 and PostgreSQL with per-tenant database isolation. In active internal use and still in development. ## Model Context Protocol servers We implement the Model Context Protocol (MCP) for structured communication between AI agents and external services. Our MCP servers give our agents API access to Productive.io, GitHub and Figma, with bearer token authentication, rate limiting and data transformation. The agents depend on them every day. ## What's Included - **Custom internal tools:** Purpose-built CLI tools and web services for your specific operational bottlenecks - **AI chatbots:** WhatsApp, Telegram, or web-based bots with Claude API, multi-turn conversations, and production guardrails - **Notification bridges:** Route events across project management tools and chat platforms - **Invoice and billing automation:** PDF generation, SMTP delivery, payment tracking, automated follow-ups - **Reporting automation:** GA4, Search Console, DataForSEO integration with automated monthly delivery - **Meeting intelligence:** Fireflies.ai transcript processing and key insight extraction - **HR and team analytics:** Attendance tracking, performance scoring, check-in analysis - **AI agent development:** Agents that work a backlog and hand you something to review, with the boundary of what they may do on their own agreed before anything is built - **MCP server implementation:** Model Context Protocol servers for AI-to-service communication ## Tech Stack - **Claude API / Anthropic SDK:** LLM integration with structured output, guardrails, and cost tracking - **Claude Code SDK:** AI-powered code generation with file tracking and git operations - **Model Context Protocol (MCP):** Structured AI agent communication - **Node.js:** Runtime for all internal tools and automation services - **Express:** Webhook servers and API endpoints - **SQLite / PostgreSQL:** Data storage, audit logging, conversation state - **PM2:** Process management for production services - **WhatsApp Cloud API:** Business messaging with HMAC verification - **Google Chat API:** Bot integration with JWT verification, interactive cards - **Telegram Bot API:** Webhook-based bot with grammy framework - **GA4 / Search Console / DataForSEO:** SEO data pipeline - **Nodemailer:** SMTP email delivery - **Laravel 12 / React 19:** Full-stack SaaS development ## Who This Is For - **Businesses drowning in manual processes.** If your team spends hours on tasks that follow the same pattern every time, those tasks should be automated. We identify the bottleneck, build the tool, and deploy it. - **Companies wanting AI chatbots that work in production.** Bots with rate limiting, budget controls, an off switch outside the code, and an escalation path to a person from day one. - **Agencies needing operational automation.** Invoicing, reporting, notifications, client communication. The operational overhead that grows with every new client. - **Enterprises wanting custom internal tools.** Off-the-shelf SaaS does not fit your workflow. Custom tools built for how your team works. ## Proof - 8 production internal tools running daily, built over 3+ years. - A lead qualification bot on the Claude API, run against our own enquiries: multi-turn conversations behind 11 guardrail checks. Retired in August 2026, written up in full. - An AI agent working our own backlog daily: it picks up a task, writes the code and opens a pull request for a person to review. It never merges its own work.