Blog

Blog

Notes on running data work through an AI agent with looot: what an agent can replace, what it costs and how to set it up.

  • 35 posts
Costs

AI agent cost: model tokens plus data calls

AI agent cost has two meters, model tokens and data calls. How to estimate each, why the data side is easier to cap, and how to read per-call prices first.

The looot team · · 7 min read

Product

AI agent tools: the data and APIs an agent needs

The AI agent tools that matter most fetch real data. A plain map of the jobs agents call tools for, and how to connect them without a dozen keys.

The looot team · · 7 min read

Product

AI sales agent: the data jobs it can do today

What an AI sales agent can do with live data today: find companies, find and verify emails, enrich lists and research accounts, and where a human decides.

Walid Boulanouar · · 8 min read

Product

Build your own CRM with an agent and Supabase

Let an AI agent build a small CRM in your own Supabase project. The five tables, the loop, seven rules, the exact prompt and one step not available yet.

Walid Boulanouar · · 5 min read

Setup

Claude RAG with live data from an API

Claude RAG usually means a vector store. For facts that change, retrieving from a live API works better. How the two differ and how to wire Claude to live data.

Walid Boulanouar · · 7 min read

Setup

How to build an MCP server, and when to skip it

Build a small MCP server in about thirty lines of JavaScript, connect it to Claude Code, and learn when an existing server or gateway is the better choice.

The looot team · · 7 min read

Product

LLM router: what it routes and what it leaves out

An LLM router picks a model for each request. It does not route the data and tool calls an agent makes. Where each kind of routing fits, and how fallback works.

Walid Boulanouar · · 7 min read

Setup

LLM tool calling: how an agent calls a real API

LLM tool calling lets a model ask your code to run a function and read the result. How the loop works, what breaks with real APIs, and how to keep it simple.

The looot team · · 8 min read

Comparisons

MCP vs API for agents: when each one fits

MCP and a plain API both let an agent reach outside data. What the agent handles in each, when to pick which, and a prompt to test both on your job.

Walid Boulanouar · · 5 min read

Product

Scrape Google Maps for leads with an agent

How an agent builds a local lead list from Google Maps: search, details, website, email. The steps, a prompt to paste and what to check first.

Walid Boulanouar · · 5 min read

Product

Vibe marketing with an agent: a setup that works

What vibe marketing means in practice, a four step workflow for an AI agent with live data, the jobs it does well, and the checks that keep it from guessing.

Walid Boulanouar · · 8 min read

Setup

What is an MCP server? A plain explanation

An MCP server gives an AI agent tools it can call. What a tool call looks like, and how one connection can reach many providers.

Walid Boulanouar · · 5 min read

Setup

Set up looot with one line: skill.md and llms.txt

Give your agent one URL and it can set up looot itself. What skill.md and llms.txt are, what each one tells an agent, and a prompt you can paste today.

The looot team · · 3 min read