#reliability
Every post tagged "reliability".
124 posts · showing 71–80
-
Code Review When Most Code Is Agent-Written
Review practices assumed an author who had reasons, understood the system, and made idiosyncratic mistakes. Agent output breaks all three — and the bugs that survive are the ones that look correct.
-
Autonomous Refactors: What Makes One Safe Enough to Merge
Refactoring is what agents do best and what most easily produces an unreviewable disaster — for the same reason. One property separates the two, and it isn't how hard the change looks.
-
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.
-
Upgrading One Agent in a System of Six
A contained improvement to one classifier made the supervisor above it drop half its escalations. No error, no failing test — because each agent's own tests passed against its own version.
-
Raw SQL or Curated Queries? Giving an Agent Your Database
A two-line tool description can hand an agent unbounded access to your data and your query planner. The guardrails matter more than the choice — and one cheap planner call prevents most of the damage.
-
Half the Job Is a Real Answer: Designing for Partial Success
Thirty-one of forty invoices reconciled. Reporting success hides nine; reporting failure throws away thirty-one. The middle is where most runs land, and most designs can't express it.
-
Which Agent Alerts Should Wake Someone Up?
An agent can be green on every service metric while doing the wrong work at ten times the cost. One rule sorts the alerts — and the highest-value one is the one almost nobody has configured.
-
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.
-
How Many Eval Cases Do You Actually Need?
18/20 versus 19/20 is not an improvement — it's noise wearing a number. What your suite size can and cannot detect, and the paired design that makes a hundred cases behave like seven hundred.
-
Computer Use: When the Agent Drives a Whole Desktop
Clicking is easy; knowing what to click is a perception problem solved from a screenshot. The failures are modals, focus loss, and scroll state — and an agent that assumes its click landed compounds errors silently.