#case-study
Every post tagged "case-study".
17 posts · showing 1–10
-
Your First Production Agent Should Be Invoice Reconciliation — Because the Ledger Grades It for You
The best first agent isn't the most impressive one — it's the one whose environment tells you when it's wrong. Here's how to score candidate tasks for a built-in oracle, and the two ways that oracle quietly lies to you.
-
Extraction Was Never the Hard Part: An Invoice Agent, Rebuilt
The first version had the model read invoices and type the numbers. The rebuild started after the numbers were already read — which is where the actual work in accounts payable has always been.
-
Four Tool Calls to One Answer: A Research Run, Annotated
A research agent answers one question in four steps. Reading what changed in the transcript between each step explains more about how agents work than any diagram of the loop.
-
The Screening Agent That Could Only Be Right
Every available metric said it was working — and every one of them was computed only from the candidates it advanced. The decision destroys the evidence needed to evaluate the decision.
-
The Support Org After Agents: Fewer Tickets, Harder Tickets
The residual isn't a random sample of the old work — it's specifically the hardest cases, with the easy ones that used to provide pacing and training removed. Support got here first.
-
What an Agent-Run Sprint Actually Looks Like
Not the same sprint faster — an inversion. Most of the week becomes specifying and reviewing, review becomes the constraint, and integration becomes the new time sink.
-
The Ticket-to-PR Agent: Which Half of the Job It Does Well
The split wasn't by difficulty — some intricate tickets went fine and some trivial ones went badly. One question predicts it, and acting on it improves something other than your agent.
-
The Inbox Agent That Filed Everything Correctly and Lost Two Questions
Every filing decision was defensible, and two unanswered questions still vanished into the archive. The bug wasn't the prompt — it was that the agent judged messages while acting on conversations.
-
The QA Agent That Wrote Tests That Always Passed
Coverage climbed, the build stayed green, and a real regression sailed through. An agent asked for passing tests writes passing tests — and the easiest passing test verifies nothing.
-
The Sales-Research Agent and the Problem of Stale Facts
Every fact in the brief had been true. None was labelled with when — so someone opened a call congratulating a person on a role they'd left a year ago.