22 posts tagged with "data-engineering"

A support engineer pings the on-call channel. A customer pasted a sentence the assistant retrieved last week, and the policy team replied: we don't say that anymore. They haven't said it for four months. The document in the CMS reads correctly. The embedded chunk in the vector index still reads the old way, with a confident similarity score, surfaced to the model on every relevant query. Nobody changed the retrieval code. Nobody changed the model. The source-of-truth changed, and the index never heard about it.

This is the failure mode of an ingestion pipeline that was designed for creates and grew into a system that also handles updates without anyone designing for updates. The "embed on create" job ran the day each document was first written. The CMS shipped an edit endpoint a quarter later, owned by a different team, who plumbed it into search and into the public-facing renderer and into the changelog feed — every consumer except the one that was a derived dataset hiding behind a different name. Months pass. The corpus drifts. Retrieval starts answering questions about a world the company has formally left behind, and the only signal is a confused customer.

Watch a support agent handle one conversation, and count how many times it computes "churn risk." First when it triages the ticket. Again when it decides whether to offer a discount. A third time when it drafts the escalation summary. Each time, it re-reads the raw orders table, re-runs an inline aggregation, and produces a number. The three numbers don't match. Nobody notices, because they were never written down next to each other.

This is feature engineering. The agent is doing it on every turn, in prose, and doing it worse than a pipeline you would have laughed out of code review a decade ago.

The machine learning world already solved this. The solution is called a feature store, and the discipline it enforces — compute a feature once, name it, version it, serve it consistently — is exactly the discipline an agent throws away the moment you hand it a database tool. Your agent didn't avoid building a feature pipeline. It built one. It just built the worst one in the building.

You shipped a better memory format on a Tuesday. The new schema splits a freeform summary string into structured fields — entities, preferences, last_verified_at — because the old blob was hard to retrieve against and impossible to update cleanly. The change is obviously correct. It passes review. It ships.

What you did not notice is that every memory written before Tuesday is now subtly wrong. Some records still have the old summary field and no entities, so the retrieval code that now keys on entities skips them. A few have a summary that the new parser interprets as an empty preference set. The agent didn't crash. It just quietly forgot a year of accumulated context, and nobody filed a bug because nothing looked broken — the agent still answered, just worse.

A vector index feels like a database. You write documents into it, you query it, it returns results. But it is not a database — it is a derived, denormalized copy of data that lives somewhere else. Your source of truth is a wiki, a ticket system, a CRM, a folder of PDFs. The embeddings are a projection of that truth, frozen at the moment you ran the ingestion job.

That makes your vector index a cache. And like every cache, it goes stale. The difference is that most teams build a caching layer on purpose, with a TTL and an invalidation hook, while almost nobody builds a vector index on purpose as a cache. They build it as a "knowledge base" and then act surprised when it serves knowledge that stopped being true three weeks ago.

Your RAG system has a bug that doesn't throw exceptions. It doesn't spike your error rate. It doesn't show up in your latency dashboards. Instead, it quietly delivers confident, plausible-sounding answers that are wrong — and nobody notices for weeks.

This is the data contract problem in RAG: your ingestion pipeline is the source of truth for everything downstream, but it has no schema enforcement, no freshness guarantees, and no alerting when the shape of the world changes underneath it. Every time an upstream data source adds a field, a chunking parameter shifts, or an embedding model gets updated, your retrieval quality silently degrades.

Eighty percent of enterprise RAG projects experience critical failures in production. The most insidious of those failures don't announce themselves.

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.

Two years ago, a team pointed their retrieval index at the wiki, the Zendesk export, and a snapshot of the public docs. Last week, that same index returned a deprecated runbook that told an SRE to restart a service that no longer exists. The runbook had been deprecated for eighteen months. Nobody owned its retirement, so nobody retired it. The agent confidently cited it. The model wasn't wrong; the corpus was.

This is the failure mode that doesn't show up in retrieval evals: the corpus is treated as a one-time engineering decision when it's actually an ongoing governance problem. The team that scoped the initial ingestion is long gone. The legal review that should have flagged the customer-confidential PDFs never happened, because nobody told legal there was a pipeline. The "freshness strategy" is a Slack message from someone who left in Q3. The retrieval index has become a shared inbox for every document anyone ever scraped, and the bar for inclusion has drifted to "whatever was easy to ingest."

The pitch is compelling: feed your legacy records into an LLM, describe the target schema, and let the model figure out the mapping. No hand-written parsers, no months of transformation logic, no domain expert bottlenecks. Teams have run this and gotten to 70–97% accuracy in a fraction of the time it would take traditional ETL. The problem is that the remaining 3–30% of failures don't look like failures. They look like correct data.

That asymmetry—where wrong outputs are structurally valid and plausible—is what makes LLM-powered data migrations genuinely dangerous without the right validation architecture. This post covers what the teams that have done this successfully actually built: when LLMs earn their place in the pipeline, where they silently break, and the validation layer that catches errors traditional tools cannot.

Your hand-coded ETL pipeline handles 95% of records correctly. The edge cases — the currency strings with commas, the inconsistently formatted dates, the inconsistent country codes — flow through to your data warehouse and quietly corrupt your dashboards. Nobody notices until a quarterly report looks wrong. You add another special case to the pipeline. The cycle continues.

LLMs can solve this. They infer schemas from raw samples, handle messy edge cases that no engineer anticipated, and transform unstructured documents into structured records at a fraction of the development time. Several teams have shipped this. Some of them have also had LLMs silently transform "$1,200,000" into 1200 instead of 1200000, flip severity scores from "high" to "low" with complete structural validity, and join on the wrong foreign key in ways that passed every schema check.

The problem isn't that LLMs are bad at data engineering. It's that their failure mode is exactly wrong for ETL: high confidence, no error thrown, structurally valid output.

Most teams building AI agents spend weeks tuning prompts and evals, benchmarking model choices, and tweaking temperature — while their actual bottleneck sits one layer below: the data access layer that was designed for human developers, not agents.

The mismatch isn't subtle. ORMs like Hibernate, SQLAlchemy, and Prisma, combined with REST APIs that return paginated, single-entity responses, produce data access patterns exactly wrong for autonomous AI agents. The result is token waste, rate limit failures, cascading N+1 database queries, and agents that hallucinate simply because they can't afford to load the context they need.

This post is about the structural problem — and what an agent-optimized data layer actually looks like.

The demo works every time. The LLM translates "show me last quarter's top ten customers by revenue" into pristine SQL, the results pop up instantly, and everyone in the room nods. Then you deploy it against your actual warehouse — 130 tables, 1,400 columns, a decade of organic naming conventions — and the model starts confidently generating queries that return the wrong numbers. No errors. Just wrong answers.

This is the schema boundary problem, and it's why text-to-SQL has the widest gap of any AI capability between benchmark performance and production reality. A model that scores 86% on Spider 1.0 (the canonical academic benchmark) drops to around 6% accuracy on Spider 2.0, which approximates real enterprise schema complexity. Vendors demo on clean, toy schemas. You're deploying on yours.

Your RAG pipeline is returning confident, well-formatted answers. The LLM response looks great. And yet users keep filing tickets saying the system is wrong. The product manager pulls up the document in question — the information changed six weeks ago, but the vector index still reflects the old version. No errors were thrown. No alerts fired. The system was just silently, invisibly wrong.

This is the embedding refresh problem, and it bites most production RAG systems eventually. Analysis across production deployments shows that over 60% of RAG failures trace back to stale or outdated information in the knowledge base — not bad prompts, not retrieval algorithm failures, but a simple mismatch between what's in the vector index and what's true in the source. Most AI engineers discover this the hard way. Most data engineers already know how to prevent it.