Less AI hype. More how it actually works.
Practical notes on AI and automation, written from the work, not a marketing deck.
Start with a guide
AI agents vs. chatbots: what actually reduces support load
Most support bots just deflect. An AI agent that can read your docs and take action is a different thing entirely. Here's where each one earns its keep.
AI Agents · 5 min
How to choose an automation partner (without getting locked in)
The cheapest quote often becomes the most expensive system. A short checklist for hiring someone to automate your business, ownership first.
Strategy · 6 min
AI invoice processing that actually ships
Most invoice-extraction demos look great and break in week two. Here's how we built a 14-supplier pipeline that runs unattended in production.
Automation · 6 min
Automating sensitive data without creating a compliance problem
When automation touches health, financial, or personal data, security can't be an afterthought. How to get the efficiency without the risk.
Engineering · 5 min
When automation is worth it (and when it isn't)
Not every manual task should be automated. A simple framework for deciding what to automate first, and what to leave alone.
Strategy · 5 min
Google Apps Script: the most underrated automation tool
Before you buy another SaaS subscription, look at what's already sitting inside your Google Workspace. It's more capable than people think.
Engineering · 5 min
The security review every AI integration needs before launch
AI integrations open new paths for data to leak that a standard security checklist doesn't cover. Here's what to check before anything touches production.
Engineering · 8 min
What AI agents can't do yet, and how to design around it
The gap between what agent demos show and what agents reliably do in production is real, specific, and worth designing for instead of ignoring.
AI Agents · 9 min
Data pipelines for teams without a data team
Most small and mid-size companies don't need a data warehouse. They need three reliable pipelines and a place to look at the numbers.
Automation · 8 min
Hiring an automation team vs. outsourcing it
The build-vs-buy question for automation isn't about cost. It's about which failure mode your organization can actually tolerate.
Strategy · 8 min
The handoff is the product
The code working on delivery day isn't the deliverable. Whether your team can run it without you six months later is the actual deliverable.
Strategy · 7 min
Monitoring AI systems like you monitor infrastructure
Most AI features ship with no observability at all. You find out they're broken when a customer complains, which is the same as not monitoring your servers.
Engineering · 8 min
CRM integrations break in the same five places
Every CRM integration project looks the same on the whiteboard and breaks in the same handful of spots once real data hits it.
Engineering · 8 min
Shopify order ops: where automation actually pays for itself
Most Shopify stores automate the marketing side first and leave the operational grind, the part that actually eats hours, completely manual.
Automation · 8 min
Document AI beyond invoices: contracts, forms, and the messy middle
Invoices get all the attention because they're structured. Contracts, intake forms, and scanned correspondence are where document AI actually gets hard.
Automation · 8 min
Evals are the part nobody wants to build
Everyone wants to ship the AI feature. Almost nobody wants to build the harness that proves it still works after the next change. That's the mistake.
Engineering · 8 min
Why your AI pilot never became a product
Pilots are optimized to impress a room, not to survive contact with real usage. Here's the gap that kills most of them before they reach production.
Strategy · 8 min
The real cost of running AI agents in production
Token pricing looks cheap in a spreadsheet. Multiply it by retries, context windows, and idle polling loops and the bill tells a different story.
Strategy · 8 min
What retrieval-augmented generation actually gets wrong
RAG demos work on ten clean documents and fall apart on ten thousand messy ones. The failure modes are predictable once you've seen them a few times.
Engineering · 9 min
What we learned shipping automation this year
A year of client automation work, distilled into the patterns that held up and the assumptions that didn't survive contact with production.
Strategy · 7 min
Monitoring automation you can't watch manually
The whole point of automation is that nobody has to watch it. That only works if the monitoring is actually good enough to replace watching it.
Engineering · 5 min
Idempotency: the boring fix that prevents the worst automation bugs
Most catastrophic automation failures trace back to one missing property: the pipeline wasn't safe to run twice. Here's how to build for it.
Engineering · 6 min
Reporting automation people actually read
An automated report nobody opens is worse than no automation at all, it's effort spent making noise. How to build reporting that gets read.
Automation · 5 min
Design agent permissions before you design agent capability
The instinct is to ask what an AI agent should be able to do. The better first question is what it should never be allowed to do unsupervised.
AI Agents · 6 min
The e-commerce back office nobody automates
Storefronts get all the design attention. The order-to-fulfillment plumbing behind them is where the real operational cost quietly sits.
Automation · 6 min
Cost control for AI pipelines before the bill surprises you
Token costs scale with volume in ways that are easy to miss until the first invoice. How to design AI pipelines with cost as a first-class constraint.
Engineering · 6 min
What a good handoff actually looks like
The build is the easy 80%. Handing off a system a client's team can actually run without you is the part most agencies skip.
Strategy · 5 min
Before you build a CRM integration, answer these five questions
CRM integrations look simple until you hit the field mapping, the dedup logic, and the sync direction nobody agreed on. A pre-flight checklist.
Engineering · 6 min
Document extraction beyond the happy path
AI can read a clean PDF in a demo every time. Production documents are scanned sideways, half-legible, and inconsistent. Here's what actually holds up.
Automation · 7 min
Scoping an automation project that won't balloon
The fastest way to blow a budget is an open-ended discovery phase. A concrete method for scoping automation work before a single line of code.
Strategy · 6 min
The real cost of a broken integration
A single silent failure in a data sync can cost more than the entire automation saved. Here's how to price the risk before you ship.
Engineering · 6 min
What 2023 actually taught us about shipping AI, not demoing it
A year of frontier models in the wild changed what 'automation' means for small businesses. Looking back at what held up, what didn't, and what we're carrying into next year.
Strategy · 6 min
128k context windows: what actually changes when the model can read more
This month's headline model release bumped the context window to 128k tokens at a much lower price. That's not just 'more room,' it changes which architectures make sense.
Engineering · 6 min
Prompt injection is the SQL injection of this generation, and most teams aren't ready
If your AI agent reads untrusted text, whether that's an email, a web page, or a customer message, it can be manipulated by that text. Here's what that risk actually looks like.
Engineering · 6 min
What code-running chat tools actually change for business reporting
The new breed of chat tools writes and runs Python against your data right in the conversation. Genuinely useful, with a genuinely narrow lane.
Automation · 5 min
RAG isn't optional anymore: why retrieval beats fine-tuning for most use cases
Everyone asking for a 'custom-trained AI' actually needs retrieval-augmented generation. Here's why that's the right answer for almost every business use case we've seen.
AI Agents · 6 min
What we learned putting frontier models in production this year
Frontier model API access opened up in March. Four months in, here's what actually breaks when you move past the playground and into a real pipeline.
Engineering · 6 min