299 posts tagged with "observability"

When your AI feature ships a wrong answer, the first question is always: "Was it the model?" Most engineers reach for model evaluation, run a few test prompts, and conclude the model looks fine. They're usually right. The model is fine. The breakage happened somewhere else—at one of the invisible seams where your components talk to each other.

The evidence for this is consistent. Analysis of production RAG deployments shows 73% of failures are retrieval failures, not generation failures. In multi-agent systems, the most common failure modes are message ordering violations, state synchronization gaps, and schema mismatches—none of which show up in any per-component health check. GPT-4 produces invalid responses on complex extraction tasks nearly 12% of the time, not because the model is broken, but because the output format contract between the model and the downstream parser was never enforced.

The model gets blamed. The boundary is the culprit.

Three weeks into your quarter, a production alert fires. Accuracy on a core task dropped eight percentage points. You open the dashboard and immediately notice three things that all landed in the same deploy window: a context length increase from 8k to 32k tokens, a model version upgrade from gpt-4-turbo-preview to gpt-4o, and a batch size change your infrastructure team pushed to improve throughput. None of the three changes individually was considered high-risk. Combined, they've created a debugging problem no one can solve cleanly.

Welcome to the rollout sequencing problem.

A user reports the assistant gave them a wrong answer at 9:47 a.m. You open the trace. There are three hundred and forty spans. They are almost all named agent.run, llm.invoke, or tool.call. Some have a parent. Some are siblings. Three of them retried. One of them retried and then was cancelled. None of them tells you whether the bad output came from the planner, the worker, the critic, the reflection pass, or the second retry of the worker after the critic flagged it.

You spend the next hour grepping log lines for a UUID prefix you saw in a screenshot, cross-referencing timestamps against a Slack notification, and reconstructing the agent topology in your head from the indentation pattern in the trace viewer. Eventually you guess that the third worker invocation ran with a model alias that silently flipped to a different snapshot the night before. You cannot prove it from the trace alone.

The agent worked. The trace is intact. The hairball is the bug.

The AI feature has the dashboard. The prompt has the version control. The eval suite has the on-call rotation. And then there is the upstream cron job, written in 2022, owned by a team that rotated out of analytics two reorgs ago, that produces the CSV your retrieval index is built from. That cron job has no SLA. That CSV has no schema contract. The team that owns it does not know it feeds an AI feature. When it changes — and it will change — the AI team will spend three weeks debugging a prompt that did nothing wrong.

The AI quality regression you are about to chase is almost never an AI problem. It is an ETL problem wearing an AI costume. The discipline that has to land is the seam between the two — the contract, the lineage, the freshness signal, the paired on-call — and the team that does not formalize it ships an AI feature whose reliability is bounded by the least-loved cron job in the company.

The two-week canary is one of those practices that sounds disciplined enough to skip the harder question. Engineering imported it from microservices — ramp 1% for a few days, watch error rate, ramp to 100%, declare done — and grafted it onto AI features without asking whether the failure modes that matter for AI even surface in two weeks. They don't. The bill that kills the feature lands in week six. The customer cohort that exposes the long-tail intent onboards in week five. The eval drift that scored +3% on launch day starts costing real money in week four because the new prompt's chattier outputs have been compounding token spend the whole time, and nobody was watching for that because the dashboard was watching for crashes.

A canary built around p95 latency and HTTP 500s will tell you the LLM is up. It will not tell you the feature is working. AI features fail in shapes the deploy ceremony was never designed to catch — slow shape changes in user behavior, gradual cache erosion, retrieval quality collapse, refusal-rate creep, cost trajectories that bend the wrong way — and almost all of them take longer than two weeks to declare themselves. The team that ships by the microservice clock is shipping by a clock the failures don't run on.

A multi-agent system for market data research quietly burned through $47,000 in inference cost over four weeks before anyone noticed. The original weekly bill was $127. The cause wasn't a traffic spike or a model upgrade — it was two agents passing the same conversation back and forth for eleven days, each one confident the other was the right place for the request to live. Nothing errored. No alarm fired. The bot's "queue transferred" metric and the other bot's "task received" metric both went up in lockstep, and both dashboards looked healthy.

This is the closed-loop escalation bug. It is the multi-agent version of two helpful colleagues each insisting "no, you take it," except neither of them ever gets bored and walks away. The architecture diagram you drew at design time has each specialist owning a clean slice of the problem. The architecture the runtime actually executes has a routing cycle nobody in the room can see.

A user clicks the button. Ninety seconds later they get their first token. The team's response, almost reflexively, is to ask the model vendor for a faster TTFT — and the vendor's TTFT is 800 milliseconds. The model was never the slow part. The request waited 30 seconds for a tool registry to load, 20 seconds for a vector store client to negotiate its first connection, 15 seconds for the prompt cache to prime on a fresh container, and another 10 seconds for an agent framework to validate every tool schema in its registry against a JSON schema validator that was loading on first use.

This is the agent cold start, and it has almost nothing to do with the model. Teams that profile only the LLM call are optimizing the part of their request that wasn't slow. Worse, the cold start is invisible in steady state — load tests against a warm pool look great, dashboards plotted on the median look great, and the people who notice are the users who hit the first request after a deploy, an autoscaling event, or a low-traffic stretch where everything got recycled.

Your eval pipeline scores are trending up. Response quality is improving. The LLM judge is catching more bad outputs. Your dashboard is green.

Meanwhile, a support ticket trickles in: "The assistant keeps giving me long, formal answers when I asked a simple question." Then another: "It stopped suggesting next steps. Used to do that automatically." Then your product manager shows you a chart: user satisfaction down 12% over the last quarter, correlated almost perfectly with the stretch where your automated eval metrics were climbing fastest.

This is the eval automation trap. Your measurement apparatus became optimized for itself rather than for what your users value — and because the feedback loop was entirely automated, nobody noticed until the damage was already in production.

The bug count after an AI launch is not a quality problem. It is a discovery sequence — a sequence so predictable that you can sketch it on a whiteboard before the launch announcement goes out, week by week, ticket by ticket, and be embarrassingly close to right by the time the dashboards catch up. Every team that ships an AI feature runs this sequence. The only choice is whether you run it with a runbook or with a series of unscheduled all-hands.

I have watched enough launches now to believe the sequence is not really about engineering quality. It is about an information gap. Pre-launch, the team has a synthetic traffic mix, a curated eval set, a happy-path demo, and a board deck. Post-launch, real users arrive with intents the synthetic traffic never modeled, a marketing team that runs campaigns engineering hears about secondhand, a model provider that ships changes the team did not authorize, and a privacy reviewer who was on vacation when the feature shipped. The sequence below is the friction that happens when those two worlds collide.

The first time my team found out a model we depended on was being retired, we found out from a customer. The deprecation email had landed in a shared inbox three engineers had unsubscribed from. The provider's status page had a banner up. The webhook event had fired into a void because we never wired up the receiver. Sixty days of warning, used by us as zero days of warning, ending with an outage and a calendar full of "emergency migration" syncs.

Most teams I talk to are running this exact setup right now and don't know it. Every major LLM provider has been quietly building out a notification surface — webhooks for incidents, deprecation events in changelogs, account warnings sent by email, billing anomaly pings, region failover signals — and most teams have it disabled or routed to a mailing list nobody reads. The provider has been telling you the bad news in advance. You've been choosing not to listen.

A team I talked to last quarter had every dashboard green. Tool error rate flat at 0.3%. End-to-end success at 98%. SLO budget barely touched. They were also burning four times their projected token spend, and nobody could explain it. When they finally instrumented retry depth per trace, the picture inverted: the median successful request was making 2.7 tool calls instead of the 1.0 the architecture diagram promised. The agent was not failing. It was failing and recovering, over and over, inside the same span, and the success rate metric had no way to tell them.

This is the part of agentic reliability that the old reliability vocabulary cannot reach. MTBF — mean time between failures — assumes failures are punctuated, observable events you can count between. You measure the gap, you compute the mean, you alert when the gap shrinks. It worked for hard drives, networks, deterministic services. It does not work for systems that retry, reroute, fall back, and recover silently inside a single user-visible operation.

The user asked the agent to "let Karen know we're done." The agent called send_email with the recipient field set to karen-team@, the most plausible address its contact-lookup tool returned. The message — three paragraphs of internal-only project status, including a candid line about a customer's renewal risk — landed in forty inboxes. One of those inboxes belonged to the customer in question. The postmortem ran for two weeks.

There was no prompt injection. There was no model jailbreak. The tool worked exactly as specified. The contract the team wrote for send_email was "send a message to a recipient." The contract the world enforces is "broadcast to a group whose composition the sender did not audit." That gap — between what the tool is named and what the tool can actually do — is where most outbound agent incidents live.

Email is the obvious example, but the same hazard hides in every messaging tool an agent ever touches. The thirty years of muscle memory humans built for these channels did not transfer to the planner pattern-matching its way through a contact list.