Automation: guides & tutorials

Zapier Pro costs $69/month for 2,000 tasks and 20 Zaps. Hit your task cap mid-month and your workflows stop running until the next billing cycle — or you upgrade to the $103/month Team plan. If your automation volume is growing or your workflows touch internal systems and proprietary data, a self-hosted alternative gives you unlimited executions, full control over credentials and API keys, and a fixed monthly VPS cost that doesn't scale with task count.

TL;DR

• One docker-compose.yml: n8n + LiteLLM + Twenty CRM + shared PostgreSQL + Redis + Caddy
• Measured idle RAM: ~1.7 GB; peak: ~2.5 GB (parallel workflow executions with live LiteLLM calls)
• Minimum Liquid Web tier: 8 GB Managed VPS (~$33–$40/mo)
• Zapier Pro + unmanaged OpenAI API + HubSpot Starter: ~$69 + variable + $50/mo vs ~$33/mo self-hosted

Most sales teams that want AI-augmented automation end up in one of two bad places: paying for Zapier Pro, a direct OpenAI API key they can't audit, and HubSpot CRM — three separate subscriptions that don't compose well and bill regardless of usage. Or they write fragile Python scripts that break on every API change and nobody wants to maintain.

This guide deploys the middle path: Twenty CRM for pipeline management, n8n for visual workflow automation, and LiteLLM as an OpenAI-compatible AI proxy — all on a single Liquid Web 8 GB VPS. n8n calls LiteLLM for every AI task (lead enrichment summaries, proposal draft generation, inbound form classification), and LiteLLM provides budget caps, model fallbacks, and a unified request log.

"Agentic AI" is not just for enterprise. In April 2026, small and medium businesses can deploy practical AI agents using no-code tools — agents that qualify leads, answer support questions, schedule content, chase invoices, and monitor inventory.

This playbook covers five agents built with tools you can set up without a developer: Claude, Make.com, n8n, Apify, and Google Sheets. For Model Context Protocol (MCP) setups that connect Claude to your tools (see the "Claude Desktop + MCP" guide in Next steps below), the same agent ideas apply once data and actions are wired in.

TL;DR:

Prerequisites:

• Make.com account (free tier available)
• Claude: Use Claude API for automation (pay-per-token billing via Anthropic Console — free tier includes limited credits). Claude Pro ($20/mo) is a chat subscription for claude.ai; it does not provide API access for Make.com or n8n HTTP calls.
• Google account (for Sheets, Gmail)
• No coding required for agents 1–4

Enterprise competitive intelligence tools — Crayon, Klue, Kompyte, Similarweb — charge $300–$2,000/month (quote-based, plan-dependent) for competitive monitoring dashboards. This same monitoring can be built with Apify for data collection, Claude for analysis, n8n for orchestration, and a free dashboard — for under $50/month (starting cost; scales with competitor count, Actor fees, and proxy usage).

This guide builds it step by step: from identifying what to monitor, to automated daily scrapes, to AI-powered change detection that alerts your team in Slack when competitors make moves that matter.

TL;DR:

The key is not just scraping data — it is building a complete pipeline that goes from raw web data to scored, enriched leads in your CRM, automatically.

This playbook covers the architecture, tool-by-tool setup, cost model, and compliance framework for building an AI lead generation system in 2026.

TL;DR:

Prerequisites:

• Apify account (Starter plan: $29/mo for production use)
• Claude API key or self-hosted Ollama (see Self-Host AI Stack)
• CRM account (HubSpot free, Clay, or Google Sheets)
• n8n or Make.com for orchestration

Claude Code now reaches well beyond the terminal: Remote Control, Routines (scheduled tasks that run on Anthropic infrastructure), Subagents, background agents, and Skills (sharable slash commands) all ship in the current release, documented in the Claude Code docs. What was once a developer-only terminal tool is now a legitimate business operations agent that handles CI/CD, content pipelines, reporting, and data enrichment.

This guide covers seven production-ready workflows that businesses use to replace manual operations, with setup instructions, architecture diagrams, and real cost breakdowns sourced from Anthropic's published pricing and platform documentation.

TL;DR:

Prerequisites:

• Claude Code installed. On macOS, Linux, or WSL run curl -fsSL https://claude.ai/install.sh | bash (Windows PowerShell: irm https://claude.ai/install.ps1 | iex). See the official install guide.
• A paid Claude subscription: Claude Pro ($20/mo) or Claude Max (from $100/mo). The Terminal CLI and VS Code extension can also run on an Anthropic Console (API) account or a third-party provider. New to Claude? You can try Claude free for a week.
• Basic terminal familiarity
• API keys for integrations (GitHub, Apify, Slack), as needed per workflow

Enterprise agentic AI is software that chains models, tools, and decisions under bounded autonomy: allowlisted actions, measurable task outcomes, and audit-grade logging—distinct from a generic “smarter chatbot” with no production guardrails.

In 2026, programs that win focus less on the model name and more on that operational bar. Analyst outlooks still sketch heavy global AI spend and fast growth in task-specific agents inside applications—yet most programs succeed or fail on governance, unit economics, and stage gates, not on whoever quotes the biggest macro number.

For headline-level context (models, chips, platforms), see Top 10 AI and tech stories this week (March 17–24, 2026). For the spending breakdown and how to read trillion-dollar totals, see Gartner’s AI spending 2026 forecast.

Gartner’s worldwide AI spending forecast (January 15, 2026) is an analyst estimate of how much organizations and vendors will spend across AI-related infrastructure, software, services, and adjacent categories in a given year—not a prescription for any one team’s budget.

Headline, decoded: Analyst forecasts are taxonomy + narrative, not a single “true” global bill. Gartner’s January 15, 2026 release is the anchor for every figure below—use it when someone asks where $2.52 trillion and 44% YoY come from.

Gartner forecasts about $2.52 trillion in worldwide AI spending for 2026 - 44% year-over-year growth from roughly $1.76 trillion in 2025. In Gartner's Table 1 (millions of dollars), the 2026 row sums to about $2.528 trillion, so $2.52T is rounded headline language, not a separate methodology. Most of the total is AI infrastructure (about $1.37 trillion in 2026), with material shares in AI software, AI services, and smaller lines (AI models, AI cybersecurity, etc.). For builders, the practical read is not "spend more because the market is huge," but to fund durable data pipelines, integration boundaries, and measurable workflows - the pieces enterprises keep paying for when pilots become production.

At a glance​

• What moved the number: Infrastructure-heavy spend (including provider “AI foundation” build-out) dominates the total; software and services are large but not the whole story.
• What Gartner says about buying behavior: In the release, Gartner cites ROI predictability and positions 2026 in a Trough of Disillusionment phase—enterprises leaning on incumbent vendors rather than greenfield “moonshot” deals (see the Lovelock quotes in the primary source).
• How to use the forecast: Treat it as directional market context; do not infer your required budget from a global total.
• What to implement first: Reliable data access, orchestration with failure handling, and constrained tool interfaces (for many teams, that means patterns like MCP), before chasing every new model drop.

We unpacked this headline alongside nine other major stories in our weekly roundup: Top 10 AI and Tech Stories This Week (March 17–24, 2026).

Gemini 3.1 Flash-Lite (March 2026) is Google’s preview Gemini 3–series API model positioned for high-volume, latency- and cost-sensitive workloads; Workspace AI updates in the same window push Gemini deeper into Docs, Sheets, Slides, and Drive for Google AI Ultra and Pro subscribers, with English-first rollout and region limits on some Drive features.

TL;DR: According to Google’s March 2026 announcement, Gemini 3.1 Flash-Lite is the Gemini 3–series option Google positions as fastest and most cost-efficient on the API for developers—listed at $0.25 / 1M input tokens and $1.50 / 1M output tokens, in preview through Google AI Studio and Vertex AI. On a separate track, Gemini in Docs, Sheets, Slides, and Drive is gaining beta capabilities for Google AI Ultra and Pro subscribers: English for Docs, Sheets, and Slides globally; Drive-related features first in the U.S., with more languages and product polish planned.

If you run high-volume LLM backends or spend your day in Workspace, both tracks matter: lower per-token cost for apps and APIs, and deeper Gemini inside the files teams already share. For surrounding news, see Top 10 AI and Tech Stories This Week (March 17–24, 2026).

GPT-5.4 native computer use (OpenAI, 2026) means the model drives GUIs the way a user would: it reads screen state (e.g. screenshots), issues clicks and keyboard input, and loops until a task completes—paired with a very large API context for long traces. It is not a drop-in replacement for structured web extraction at scale; pair it with scrapers when pages are stable data sources.

Vendor-reported highlights​

OpenAI reports 75% on the OSWorld-Verified benchmark versus a published 72.4% human baseline on that suite, and positions GPT-5.4 as one stack for reasoning, coding, and agentic flows across ChatGPT, the API, and Codex.

At a glance​

• What it is (vendor framing): GUI-grounded control: perceive screen state, propose actions, loop until done—not a universal substitute for structured data pipelines.
• Headline benchmark (vendor-reported): 75% OSWorld-Verified vs. 72.4% human baseline on the same benchmark; your internal apps still need their own validation.
• API scale (vendor-reported): Up to 1M tokens in the API (922K input / 128K output, per OpenAI)—useful for traces, not a reason to skip log compression.
• Where it usually loses to scraping: High-volume, repeatable HTML/JSON extraction; pair computer use with Apify Actors when the page is a stable data source.

Below: what “native computer use” implies operationally, how benchmarks map to production risk, a straight comparison to scraping, a loop teams actually ship, builder checklists, and compliance guardrails. For the week’s news context, see Top 10 AI and tech stories this week (March 17–24, 2026).