#monitoring
Every post tagged "monitoring".
21 posts · showing 11–20
-
Queueing and Backpressure for Agent Workloads
A run can take four seconds or four minutes, and you can't tell in advance. Size the pool to the provider's rate limit, split queues by shape — and check the one timeout relationship that silently runs your task twice.
-
Observability for Agents: What to Log Beyond the Trace
A trace explains one run and nothing about your system. The two layers above it — run records and aggregates — plus three agent-specific signals that standard APM will never suggest.
-
Canary Releases for Prompt Changes
A sentence added to fix one behavior routinely changes three others. Ship prompts like behavior: versioned by rendered hash, split by stable key, and compared on tool distribution — the row nobody collects.
-
Designing a Kill Switch That Works Mid-Run
Killing the process leaves side effects in an unknown state. A stop that works checks between steps — before every model call and before every tool call — and the difference matters most at 2am.
-
The Escalation Path Is Part of the Design
An agent with no defined way to stop will improvise one, and its improvisation is a confident answer. Escalation deserves a tool, a destination, and a metric — and one field that stops the human starting over.
-
Cost Attribution: Finding Which Feature Is Eating Your Token Budget
Agent spend is dominated by a tail of expensive runs, so every averaged chart hides the cause. Five tags on each model call, one table of your twenty priciest runs, and the mystery usually resolves in an afternoon.
-
The On-Call Agent: What It Should and Shouldn't Touch During an Incident
An incident is when your system is least understood — a poor moment for an autonomous actor, an excellent one for an autonomous investigator. The line between them is read access and write access.
-
Rate Limits Are an Agent Design Constraint, Not an Ops Problem
Backoff assumes a predictable call count. Agents burst, retry at three layers, and generate more traffic the more they're throttled — which makes rate limits an architecture question, not an ops ticket.
-
Where to Put the Approval: Human-in-the-Loop Is a Design, Not a Checkbox
A confirm dialog nobody reads has all the latency of oversight and none of the protection. Four placements, a routing rule based on reversibility, and the metric that tells you your gate has become a rubber stamp.
-
Streaming an Agent's Progress Without Lying About It
Token streaming goes quiet exactly when an agent gets slow — inside the tool call. The fix is an event stream from the loop, and the hard part is not inventing certainty the loop doesn't have.