New: outcomized services. Pay per result, with a monthly cap you set. See pricing →
Insights

Guides on rescue, agents, SaaS escape, and shipping

Notes from work we actually ship. Written to help you decide what to wrap, what to kill, and what to build.

AI Services

AI Services

Building a Shopify Mobile App in 2026: Builder or Custom?

App builder subscription or custom React Native app on the Storefront API? Cost drivers, push notifications, app store review, and when each fits.

AI Services

How Much Does an AI Receptionist Cost in 2026?

AI receptionist pricing in 2026: setup vs monthly vs per minute, DIY SaaS vs managed, what drives cost, and when a human answering service still wins.

AI Services

What a 15-Day AI MVP Costs (and What Fits in 15 Days)

A 15-day AI MVP for $4,500 fixed, then $1,500 per week. What is in scope, what gets cut, and the day-by-day shape of the build.

AI Services

Per-Resolution Pricing for AI Customer Service, Explained

How per-resolution pricing for AI support works, what counts as resolved, how to audit it, and how it compares to per-seat and outsourced per-ticket.

AI Services

Accounts Payable Automation with AI: A Practical Guide

How AI automates accounts payable: invoice capture, extraction, matching, approvals, sync to QuickBooks or Xero, exceptions to a human, and accuracy targets.

AI Services

AI Consulting vs AI Implementation: What to Buy First

AI consulting vs AI implementation: what each delivers, what to buy first, and why a paid one-week audit with fixed quotes beats a strategy deck.

AI Services

Building an Internal AI Assistant on Your Company Docs

How to build an internal AI assistant on company docs: RAG done right, permissions, freshness, evals, running cost, and Slack or Teams rollout.

AI Services

The AI Agent Audit: 12 Checks Before Your Agent Embarrasses You

A 12-point AI agent audit checklist: evals, prompt drift, tool failures, cost per task, permissions, PII, human review, and logging.

AI Services

AI Voice Agent vs Human Answering Service: Where Each Wins

AI voice agent vs human answering service: where each wins, how a hybrid with warm transfer works, and which metrics to track after launch.

AI Services

Hiring an AI Automation Agency in 2026: What to Buy

How to hire an AI automation agency in 2026: hours vs outcomes, questions to ask, red flags, and why per-unit priced AI services exist.

Engineering

Engineering

Why We Run Every Client Project on Basecamp

One Basecamp project per client: messages, to-dos, docs, files, and schedule in one place. How we borrow Shape Up ideas and what we leave out.

Engineering

Clients Get a Short Video Update, Not a Status Meeting

Why we replace status meetings with 2 to 4 minute video walkthroughs, how we record them with JiffyRecord, and the one weekly call we keep.

Engineering

Lovable, Cursor, Claude, and ChatGPT: How We Use Each

Lovable for day-one prototypes, Cursor in the codebase, Claude Code for agentic builds, ChatGPT for research. When each one is the wrong tool.

Engineering

How We Work: Build, Iterate, Grow, Run

Our four stages: a 15-day AI MVP, $1,500 weekly sprints you can pause, AI agents priced per outcome, and Agent Care. Plus what we say no to.

Engineering

The Four Rules We Give Every AI Coding Agent

Think before coding, simplicity first, surgical changes, verified goals. The rule file behind our 15-day MVPs, with before and after examples.

Engineering

Tauri v2 and Rust: The Compile Errors AI Agents Keep Making

AI agents still write Tauri v1 code and fight the Rust compiler in the same ways. The rule file we load to stop the repeat mistakes.

Engineering

Stop Parsing LLM Prose: Design AI Features as Typed Decisions

Prompt, then regex the answer, is fragile. Break AI features into small typed judgments: route, select, score, verify, escalate.

Engineering

How a Three-Person Studio Runs Seven Products on Claude Code Skills

Skills as SOPs, one task registry, research before planning, automate anything done twice, kill criteria. How a small studio stays small.

Engineering

Agents That Write to Your Tools Must Read Back

Two integration traps that cost us real work, and the rules we now enforce: replace vs patch, full objects, verify after write, plain-text contracts.

Engineering

The Review Checklist We Run on Every AI-Generated Pull Request

Structure, error handling, performance, strict security, tests on critical paths, debuggability, and severity levels. Our checklist for AI-written code.

Engineering

Cost Per Task: The One Number Every AI Feature Needs

How to measure cost per task for AI features, route simple steps to small models, cache, cap, and alert before the bill surprises you.

Book 20 minutes

Bring a URL, an app, or your lead flow. You leave with a free diagnostic and a written outcome price. The call is free either way.

Book a callFree lead test