Writing

Behind the scenes, tutorials, and work in progress from Lunch Pail Labs

What is an llms.txt and how do you write one?

What is an llms.txt and how do you write one?

An llms.txt file gives AI systems a clean source of truth about your product. This guide explains what it is, why it matters, and how to write one using the exact structure from PailFlow.

PailFlow is now sponsored by E2B for Startups

PailFlow is now sponsored by E2B for Startups

PailFlow is sponsored by E2B for Startups. Here is what that support unlocks for our agent infrastructure and delivery workflows.

Bring your own AI subscription: a practical approach to token costs

Bring your own AI subscription: a practical approach to token costs

I started by bundling AI usage, token metering, and workflow in one product, then realized token billing was becoming its own business. Here’s why I’m testing a bring-your-own-AI-subscription model for PailFlow.

Project scope process: how I cut rewrite loops in complex client delivery

Project scope process: how I cut rewrite loops in complex client delivery

My project scope process kept breaking when I treated scoping as "inputs in, draft out." This post explains the stage-gated method I now use to separate thinking from writing and produce more reliable client-ready artifacts.

How to turn a target account list into outreach-ready leads with a browser agent

How to turn a target account list into outreach-ready leads with a browser agent

Recently, I shared how I built a target account list with a browser agent. This follow-up shows how I turned that one-time list into a repeatable enrichment workflow I can trust for outreach.

How to build a target account list with a browser agent

How to build a target account list with a browser agent

I needed a reliable target account list for PailFlow, not a random pile of leads. This is the simple 4-step system I used to source, enrich, score, and rank 50 accounts while I worked on other priorities.