13 posts tagged with "experimentation"

A team I worked with shipped a prompt change that reduced output tokens by 22%. The experiment dashboard lit up green — variance was tight, the p-value was clean, and the cost savings extrapolated to six figures a year. Two weeks later, a product analyst poking at conversion funnels flagged that the downstream task completion rate had dropped 11% in the same window. The shorter outputs were leaving out a clarifying step that users had been quietly relying on to know what to click next.

The experiment platform had not lied. It had reported the exact metric the team configured as primary, and that metric had moved in the right direction. The problem was that the metric measured something the team did not actually care about. Tokens were cheap to count, the experiment infra had a turnkey integration for them, and outcomes were hard to instrument — so the team picked what the platform made easy. The result was a clean win on the dashboard and a regression in the product.

You ran the experiment cleanly. Two arms, one feature flag, a clear metric, the stats team blessed the design. Twelve weeks later you ship the winner, and the lift quietly evaporates within a sprint. The post-mortem turns up nothing in the code, nothing in the flag rollout, nothing on the analytics side. The thing that moved was something nobody on your experimentation list owned: the hosted embedding model behind your retrieval call returned a slightly different vector for the same query in week three, in week seven, and again on the morning your readout meeting happened. Your A/B test was real. The substrate it ran on was not.

This is the failure mode every team running retrieval-augmented generation eventually walks into and the one almost nobody designs against. The embedding endpoint is treated as a stable substrate the way Postgres is treated as a stable substrate. It is not. It is a model with a release cadence the vendor controls, a changelog you do not read, and a behavior surface that can shift without changing the dimension count, the SLA, or the API contract you signed against. The experiment you thought was measuring a feature change was measuring a retrieval regime change with the feature flag noise on top.

The treatment arm shipped because the dashboard said "+4% conversion, p < 0.01, n = 2.3M." Six weeks after the global rollout the lift was gone, and the team filed the post-mortem under "scale effects" because nothing else fit. The actual cause was sitting in the prompt assembler the whole time: the routing hash that decided arm assignment was derived from a user-tier attribute, and the same attribute was being interpolated into the prompt template three lines later. The model was reading the assignment in band. The "treatment" wasn't the prompt change. The treatment was the population the prompt change happened to attract.

This is a failure mode that doesn't exist in the experimentation playbooks teams inherit from the web era. A button color does not read the user's tier and decide to behave differently. A prompt does. Once your treatment is a string that the model interprets, every input that touches the routing decision and also touches the prompt becomes a back channel the experiment cannot close.

You ran the cleanest A/B test of your career. Traffic split was 50/50, the hash function looked fine, the metric pipeline did not lie, the holdout was preserved, and after three weeks the analysis converged on a clear winner: variant B improved task completion by four points, with a p-value the stats team had no objections to. You shipped it to 100%. Two weeks after the rollout, the topline metric you launched on had drifted back toward the baseline, and nobody could explain why.

Here is the part that took a while to see. Both variants were writing to and reading from the same long-term memory store. Users in variant A wrote a memory like "this customer prefers blunt summaries" and the next day, when the same user happened to be on variant B, the variant B agent loaded that memory and read it into its prompt. The reverse happened in the other direction. The experiment was not comparing prompt A against prompt B. It was comparing "prompt A reading prompt-B-shaped memories" against "prompt B reading prompt-A-shaped memories." The result was an average over a contaminated joint distribution, and the launch was a regression to a different point on the same surface.

You shipped a model swap behind an experiment. Two weeks pass, the dashboard moves a tenth of a percent, and the readout says "no significant difference." You conclude the new model is roughly the same as the old one and move on.

It is not the same. Your metric was never sensitive enough to tell.

Your AI feature shipped with confidence. The A/B test showed a statistically significant 12% lift in user engagement. The confidence intervals didn't overlap. The sample size was right. The p-value was comfortably under 0.05. Six weeks later, the metric has flat-lined back to baseline. Three months in, it's actually below baseline. The experiment told you the feature worked. The experiment lied.

This isn't a bug in your statistical tooling. It's a fundamental mismatch between what standard A/B testing measures and what happens when humans interact with probabilistic AI systems over time. Three specific biases — novelty inflation, anchoring, and carryover — conspire to inflate every AI feature experiment, and the standard remedy of adding a holdout group doesn't fix any of them.

You ship an AI-powered feature, run a clean two-week A/B test, see a 4% lift in engagement, and call it a win. Six months later, the feature is fully rolled out and engagement is flat or declining. The test wasn't noisy — it was measuring the wrong thing entirely.


A/B tests were built for a world where users in a treatment group and users in a control group are statistically independent. AI features routinely violate that assumption. Users talk to each other, learn from each other's behavior, and share the outputs of AI tools. Treatment effects don't stabilize in two weeks when the real mechanism is long-horizon behavioral adaptation. When you ignore this, your experiment gives you a number that's internally consistent but causally meaningless.

A team ships an improved LLM prompt. The A/B test runs for two weeks. The metric ticks up 1.2%, p=0.03. They call it a win and roll it out to everyone. Six months later, a customer audit reveals the new prompt had been producing subtly incorrect summaries all along — the kind of semantic drift that click-through rates and session lengths can't see. The A/B test didn't lie exactly. It measured the wrong thing with a methodology that was never designed for what LLMs do.

Standard A/B testing was built for deterministic systems: a button changes color, a page loads faster, a recommendation algorithm shifts a ranking. The output is stable given the same input, variance is small and well-understood, and your sample size calculation from a textbook works. None of those properties hold for LLM-powered features. When teams don't account for this, they're not running experiments — they're generating noise with statistical significance attached.

The model team can demo the new feature and show ten convincing wins side by side. The growth team runs it as a two-week A/B test, gets p = 0.31, and the readout says "no significant effect." Both teams are right. The experiment is wrong.

This pattern repeats across every org that has bolted an LLM onto a product without rebuilding its experimentation stack. The math the growth team is using was designed for button colors, ranking changes, and pricing pages — features whose outputs are deterministic given a user and a context. LLM features break the two assumptions that math leans on, and the standard 80%-power, 5%-significance, two-week-ramp template ships systematically wrong calls in both directions: real wins read as null results, and noise reads as confident wins.

Look at the last six experiment readouts your team shipped on an AI feature. What were the arms? Odds are good you tested "new prompt vs. old prompt," or "GPT-5 router vs. GPT-4 fallback," or "reasoning model vs. fast model," or "with retrieval vs. without retrieval." You reported lift on engagement, task completion, or session length. You called it product impact. A quarter rolled by. Inference spend climbed. Nobody paused to ask the question the CFO eventually will: what would have happened if the feature simply weren't there?

That question is the missing arm. The lift your experiments keep measuring is "better AI vs. worse AI," but the one your business runs on is "AI vs. nothing" — or more uncomfortably, "AI vs. the three-line heuristic we never wrote down." These are different experiments with different conclusions, and most AI product programs in 2026 have only ever run the first one. The second is the one that tells you whether the feature is earning its inference bill.

Your team ships a new LLM-powered feature, runs a clean A/B test for two weeks, and sees a statistically significant improvement. You roll it out. Three weeks later, retention metrics are flat and support tickets are up. What went wrong? You ran a textbook experiment on a non-textbook treatment — and the textbook assumption that "the treatment is stable" broke silently.

Standard A/B testing was designed for deterministic or near-deterministic treatments: a button color change, a ranking algorithm with fixed parameters, a checkout flow. LLM features violate almost every assumption that makes classical frequentist experiments reliable. The treatment variance is high, the treatment itself mutates mid-experiment when providers push model updates, success is hard to operationalize, and novelty effects are strong enough to produce results that evaporate after users adapt.

This post is about the adjustments that make experimentation work anyway.

Your AI feature shipped. The A/B test ran for two weeks. The treatment group looks better — 4% lift in engagement, p-value under 0.05. You ship it to everyone.

Six weeks later, the gains have evaporated. Engagement is back where it started, or lower. Your experiment said one thing; reality said another.

This is not a corner case. It is the default outcome when you apply standard two-sample A/B testing to AI-powered features without accounting for the ways these features break the assumptions baked into that methodology. The failure modes are structural, not statistical — you can run your experiment perfectly by the textbook and still get a wrong answer.