When a codebase is predictable, agents can generate more correct code.

Jo Kelly-Fenton, Engineer at Spotify, explains the compounding effect: more correct code is cheaper to verify automatically, which reduces review load and creates more capacity to keep improving the codebase.

More sessions like this are lined up for QCon London 2027, April 13-16.

Find out more about QCon London 2027 here: buff.ly/pVUJ0dq

#QConLondon #CodingAgents #DeveloperExperience

Building an evaluation dataset can look like a large upfront investment, which is one reason teams defer it.

Lan Chu, AI Tech Lead and Senior Data Scientist, recommends starting with a small set of real user queries covering the key production cases. They can give more useful signal than large batches of synthetic examples.

More sessions like this are lined up for QCon London 2027, April 13-16.

Find out more about QCon London 2027 here: buff.ly/xwUuONW

#QConLondon #AIEvals #RAG

A question about dependency injection frameworks on the company Slack came back with 342 replies.

Jo Kelly-Fenton, Engineer at Spotify, explains how a five-person advisory board was given responsibility for the call, turning a company-wide debate into a smaller, explicit decision-making process.

More sessions like this are lined up for QCon London 2027, April 13-16.

Find out more about QCon London 2027 here: buff.ly/VUpDzcZ

#QConLondon #EngineeringLeadership #DeveloperExperience

Running an AI system a few times and getting reasonable-looking output isn't the same as evaluating it.

Lan Chu, AI Tech Lead and Senior Data Scientist, describes two phases: a controlled dataset to test quality before launch, then production signals to show where the evaluation set and the system need to evolve.

More sessions like this are lined up for QCon London 2027, April 13-16.

Find out more about QCon London 2027 here: buff.ly/bSrnDI4

#QConLondon #AIEvals #AIEngineering

Airplanes can largely fly themselves, yet pilots still monitor the system and judge when something isn't safe.

Aleksandar Mitic, Software Engineer at Spotify, uses that analogy for reviewing agent-generated PRs: the reviewer monitors the evidence and decides whether the change is safe to merge, rather than recreating every step.

More sessions like this are lined up for QCon London 2027, April 13-16.

Find out more about QCon London 2027 here: buff.ly/03ZPFBw

#QConLondon #CodingAgents #CodeReview

A production RAG query about Mexico's 2026 monetary policy returned perfectly relevant results. Every one was from 2020 or 2021.

Lan Chu, AI Tech Lead and Senior Data Scientist, explains the missing signal: recency wasn't part of the scoring, so the retrieval system never represented the query's time intent.

More sessions like this are lined up for QCon London 2027, April 13-16.

Find out more about QCon London 2027 here: buff.ly/XTqKgjh

#QConLondon #RAG #AIEngineering

Latency, consistency, partial failure, scaling, and observability shape whether a distributed system can be trusted.

Review the Distributed Systems in Production track at QCon San Francisco 2026: buff.ly/GAsOG54

The sessions cover Netflix’s key-value platform, 800 stateful Valkey clusters at Snapchat, object-storage-backed systems, distributed Postgres under agent workloads, and adaptive systems.

Aggregations such as sum and count don't depend on the order in which data is processed.

Nikhil Simha, Co-Founder & CTO at zipline.ai, explains how Chronon uses that property for rolling-window aggregations: split data across machines, aggregate independently, merge the results. The outcome doesn't change.

More sessions like this are lined up for QCon London 2027, April 13-16.

Find out more about QCon London 2027 here: buff.ly/2WdTBxa

#QConLondon #FeatureStore #DataEngineering