EP 010

Behind the Work

Inside the Editorial Stack

We open our own machinery. The agents that draft, the editors that cut, the fact-checking pass that catches what the drafts invent, and the places where a human still has to sit down and decide.

0:0053 min

Audio for this episode is not attached yet — add an `audioUrl` to the episode file to enable playback

We open our own machinery. The agents that draft, the editors that cut, the fact-checking pass that catches what the drafts invent, and the places where a human still has to sit down and decide.

In this episode

The pipeline, end to end

Brief, draft, edit, verify, design. Which stages a machine handles and which it demonstrably cannot.

Where the fact-checker earns its keep

The categories of error it reliably catches, and the one category it never does.

Voice is a human problem

Why every attempt to automate the final edit made the writing worse in ways readers noticed.

What we would not do again

Two automations we removed, and the reasoning for pulling them.

The machines got us to a solid draft much faster. Everything that makes it worth reading still happens after that.

Mentioned


Beyond the Prompt publishes a new episode most weeks. Subscribe wherever you listen, or read the written edition first — both cover the same ground, at different speeds.

Keep listening

More episodes.

Short Stuff

Short Stuff: Evals

The least glamorous idea in applied AI and the one that separates systems that ship from systems that demo. What an evaluation set is, why twenty examples beats zero, and how to build one this afternoon.

Jul 8, 2026·19 min
Listen
Share Short Stuff: Evals
Ideas

Learning Versus Laundering

There is a version of using AI that makes you sharper and a version that quietly hollows you out. They look identical from the outside and produce nearly identical documents. The difference is what you can do next week.

Jul 1, 2026·49 min
Listen
Share Learning Versus Laundering
Systems/with Daniel Okafor

Multi-Agent Systems, and When Not to Build One

Splitting a hard problem across specialised agents is genuinely powerful and usually premature. Daniel Okafor on coordination cost, the failure modes nobody warns you about, and the far simpler thing to try first.

Jun 24, 2026·56 min
Listen
Share Multi-Agent Systems, and When Not to Build One

The dispatch

One letter a week. Nothing else.

New essays, new episodes, and the occasional note about something we got wrong. No launch announcements, no course upsells, no breathless takes on last night's model release.

Unsubscribe in one click · We never sell the list