7 use cases across 4 jobs · newest added Nov 3, 2026

Hand this to your AI agent. It does the boring part.

Step-by-step use cases for Claude Code and n8n. Pick a job and hand your agent the steps.

What do you want off your plate?

Invoices 2 Email 3 Research 1 Sales follow-up 1 Support 1 Reports 2

Salesintermediatefor people + agents

1 / 1

Research every inbound lead before the first call

When a lead arrives, an n8n workflow gathers public facts about the company, each with a source, and attaches a short brief to the CRM record.

Check you are allowed to do thisyou check
Trigger on new leads
Research the company with sourced web search
Save the brief to the CRM
+ 1 more step

5 stepssetup ~1 h2 human checksuses n8n

Not tested by CrimsonBot.

Copy .md for your agent Open use case .md

paused

Latest use cases

Every use case is available as a web page, a .md file, or a one-click copy.

All 7 use cases →

All 7 Invoices 2 Email 3 Research 1 Sales follow-up 1 Support 1 Reports 2

1 use case for Sales follow-up. Clear filter

Salesintermediate5 stepssetup ~1 h

Research every inbound lead before the first call

When a lead arrives, an n8n workflow gathers public facts about the company, each with a source, and attaches a short brief to the CRM record.

Uses: n8n

Not tested by CrimsonBot.

Added Oct 27, 2026Copy .md

See one in action

The whole use case, step by step.

This is what your agent gets. Open any step, then copy the whole thing as Markdown.

Salesintermediateagent: n8nevidence: Documented

Research every inbound lead before the first call

When a lead arrives, an n8n workflow gathers public facts about the company, each with a source, and attaches a short brief to the CRM record.

Check you are allowed to do thisyou check
Before building anything, confirm your lawful basis for researching leads and that your privacy notice says you do it. If you rely on legitimate interests, write down the three-part test. People whose data you collect from other sources must be told within a month.
Trigger on new leads
Add an n8n Webhook node and point your form or CRM's new-lead webhook at it. Pass only what you need: company name, company website, the person's name and job title.
Research the company with sourced web search
Use an HTTP Request node to call the OpenAI Responses API with the web search tool, which returns answers with source citations. Limit the research to the company's website, news and official sources. Set the web search tool's filters.blocked_domains to linkedin.com, x.com and twitter.com so results cannot come from LinkedIn or X.
Save the brief to the CRM
Use the HubSpot node (its 'Create an engagement' operation) to attach the brief to the lead.
Spot-check before the callyou check
Before relying on a brief, open two or three of its source links. Delete briefs you no longer need, in line with your retention policy.

At a glance

5 steps · 2 human checks · setup ~1 h
Added Oct 27, 2026

What you walk out with

A one-page brief on the lead's company, with a source link for every fact
The brief saved on the CRM record before the first call

Uses

Uses: n8n

CrimsonBot hasn't tested it and can't promise it will work for you. Check each step against the source before you run it.

What your agent receives

# Research every inbound lead before the first call

When a lead arrives, an n8n workflow gathers public facts about the company, each with a source, and attaches a short brief to the CRM record.

- Category: Sales
- Runs on: n8n
- Level: Intermediate
- Audience: both
- Setup time: about 60 minutes (estimate, not measured)
- Evidence: Documented (each step backed by official docs; not tested by us)
CrimsonBot hasn't tested it and can't promise it will work for you. Check each step against the source before you run it.
- Last updated: 2026-10-31
- Named sources: 8
- Canonical URL: https://crimsonbot.com/use-cases/inbound-lead-research

> **Warning:** Privacy and terms. This workflow processes
…

Copy .md for your agent Open on crimsonbot.com

New to agents?

Start here. Three use cases, one weekend.

Picked for beginners: the non-advanced use cases with the shortest setup, one per job. Do them in order.

Step 1

Monitor competitors and get a weekly digest

Watch competitors' public pricing pages, changelogs and blogs, and get a weekly email listing only what changed.

Uses: Firecrawl, n8n

Not tested by CrimsonBot.

5 steps · ~1 hCopy .md

Step 2

Research every inbound lead before the first call

When a lead arrives, an n8n workflow gathers public facts about the company, each with a source, and attaches a short brief to the CRM record.

Uses: n8n

Not tested by CrimsonBot.

5 steps · ~1 hCopy .md

Step 3

Triage a support inbox with an agent

An n8n workflow reads each new support email, tags it, and saves a draft reply. A person reviews and sends every reply.

Uses: n8n

Not tested by CrimsonBot.

7 steps · ~1 hCopy .md

Total listed setup time: 3 h

The tools behind the use cases

Every tool shows the use cases that use it.

Hover a use case anywhere on this page to light up the tools it uses.

Browse all 14 tools →

n8n

6 use cases

Workflow automation with AI agent nodes.

Use cases that use this

Free tier · MCP client and server

Cloudflare Agents SDK

1 use case

Stateful agents and MCP on Workers. v0.32 adds Agent Skills (breaking) and private-app browsing.

Use cases that use this

Build an MCP server for your internal data

Free tier · MCP client and server

Firecrawl

1 use case

Turn websites into clean data for agents.

Use cases that use this

Monitor competitors and get a weekly digest

Free tier · MCP server

OCRmyPDF

1 use case

Open-source command-line tool that adds a searchable OCR text layer to scanned PDFs, locally, so agents and LLM workflows get real text instead of images.

Use cases that use this

Scanned invoices in n8n: local OCR first, then a checked LLM extract

Free

Airbyte MCP

0 use cases

Hosted MCP server for Airbyte pipelines, job logs and optional read-only data access.

No use case uses this yet.

Free tier · MCP server

Browserbase

0 use cases

Headless browsers your agents can drive.

No use case uses this yet.

Free tier · MCP server

Claude Code

0 use cases

Coding agent for the terminal, IDE and desktop.

No use case uses this yet.

Paid · MCP client and server

CrewAI

0 use cases

Framework for teams of role-based agents.

No use case uses this yet.

Free tier · MCP client

No news items yet.

Personal AI gear

Devices that feed your agents

Hardware that captures meetings, notes, and paper so your agents have something to work with. Each card says how far we've checked it.

All 6 gear →

Not tested by CrimsonBot · Based on sourced reviews

A fast Wi-Fi document scanner that can save searchable PDFs straight to a Samba/NAS folder with no PC, which makes it a clean paper-to-folder front end for a self-hosted OCR + LLM pipeline. It has no AI of its own.

Pairs with: Scanned invoices in n8n: local OCR first, then a checked LLM extract

$380–$460price checked Oct 31, 2026Details →

Not tested by CrimsonBot · Based on sourced reviews

Plaud Note Pro

A card-style recorder for in-person meetings and phone calls, with 64 GB storage, long battery life and MCP access to ChatGPT or Claude. CrimsonBot has not tested it.

$189price checked Oct 30, 2026Details →

Round Omi pendant on a black cord with a small blue LED lit in the center

Not tested by CrimsonBot · Based on published specs

Omi AI Pendant

An open-source pendant notetaker whose memories and transcripts reach Claude, ChatGPT, Cursor and other clients through Omi's hosted MCP server. No independent hands-on review was opened. CrimsonBot has not tested it.

$169–$229price checked Oct 30, 2026Details →

Not tested by CrimsonBot · Based on published specs

Bee Frontier

A wrist- or clip-worn recorder that turns conversations into summaries in the Bee app. CrimsonBot has not tested it. Shipping in the US. Bee Pro is optional.

Details →

For agents (and the humans who build them)

Your agent can read this whole site. No scraping required.

Every use case, tool, and gear item is clean Markdown and JSON. Point your agent at llms.txt or the REST API and it gets the steps, the tools, and nothing else. No key is needed for read access while the API is in beta.

llms.txt REST API docs OpenAPI

# every use case, as JSON

$ curl https://crimsonbot.com/api/v1/use-cases

# filter by job

$ curl "https://crimsonbot.com/api/v1/use-cases?category=support"

# one use case as Markdown

$ curl https://crimsonbot.com/use-cases/scanned-invoices-ocr-n8n.md

# the site map for agents

$ curl https://crimsonbot.com/llms.txt

# MCP server: planned at /mcp, not shipped yet

Questions

What is CrimsonBot?

Step-by-step use cases you can hand to an agent, a directory of the tools they use, personal AI gear that works alongside you, and news about how agents are changing. A use case is published only after an editor approves it. Drafts are not listed.

How are use cases and tools sourced?

A use case is published only after an editor approves it. Tool facts are corrected from each vendor's own pages. Published use cases carry an evidence label, and named sources are listed when they were recorded. Listings can go out of date, and they are not rechecked on a fixed schedule. Sponsors and paid links do not change sort order.

How often is CrimsonBot updated?

There is no fixed schedule. Published use cases, tools and gear show up in the RSS feed at /feed.xml. Drafts are not included.

Hand this to your AI agent. It does the boring part.

Every use case is available as a web page, a .md file, or a one-click copy.

The whole use case, step by step.

Start here. Three use cases, one weekend.

Every tool shows the use cases that use it.

Devices that feed your agents

Your agent can read this whole site. No scraping required.

Get an email when the newsletter launches.

Questions

What is CrimsonBot?

How are use cases and tools sourced?

How often is CrimsonBot updated?