Real-World Agents
Case studies: coding, support, research, ops.
26 posts · showing 1–10
-
The Analytics Agent Answered "What Was Q3 Revenue?" From a Deprecated Table. Make It Name Its Source Before Its Number.
The SQL was valid, the arithmetic was right, and the number was still wrong, because the agent picked the table whose name looked most like the question. Here is how to make a data agent commit to a source you can check before it hands anyone a figure.
-
The Analytics Agent's SQL Was Correct. It Answered a Different Question. Make It Print Its Definitions Before Its Number.
The query ran clean, the chart looked right, and the churn number went into the board deck. It counted trial accounts as customers. The fix is not better SQL; it is making the agent commit to what every word in the question means before it touches the warehouse.
-
The Analytics Agent Said Revenue Was Up 38%. The Join Had Counted Every Order Once Per Line Item.
A text-to-SQL agent that answers with a single number has hidden the one thing a reviewer needed to see. Here is how a fan-out join slipped through, and the grain checks that would have caught it before anyone got to the slide.
-
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.
-
Draining a Data Backlog: Should the Agent Batch Rows or Take Them One at a Time?
The ratio of preamble tokens to row tokens decides whether chunking a backlog saves an order of magnitude or nothing at all — and it's the alignment, retry amplification and blast radius that decide whether you should anyway.
-
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.
-
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 First Agent to Deploy in a Company That Has None
The first one shapes how much latitude every later one gets. Which means the right choice usually isn't the most valuable use case — it's the one most likely to succeed where people can see it.
-
How to Run an Agent Pilot That Produces a Decision
Most pilots end without a decision because they were designed to produce a demo. Write the threshold before you build — and sort the failures by cause, because "no-go" and "fix one thing" look identical in the average.
-
The Use Cases Everyone Tries and Nobody Ships
Six applications get attempted everywhere and stall at the same four points. Each has a narrower version that ships — and it's usually less exciting than the pitch that funded it.