@QCon

Uncover emerging trends and practices from the world’s most innovative software professionals to help you validate your software roadmap. Celebrating 20+ years.

linktr.ee/qconferences
Joined March 2008
  • Tweets12.1K
  • Following673
  • Followers7.4K
6.8KMedia
Giving every engineer a coding agent does not create shared team capability. Read Brian Yang’s QCon AI New York session abstract: buff.ly/pT1T519
2
52
The session examines how teams make experimentation repeatable, share useful practices, and decide which discoveries deserve wider adoption.
13
At Spotify, running a coding agent across an entire fleet means dealing with Maven, Yarn, Bazel, and custom build scripts, all with different commands.
3
1
178
Jo Kelly-Fenton, Engineer at Spotify, explains how Spotify built a single verify tool that routes each repository to the right build and test system, giving the agent one interface for verification regardless of the underlying toolchain.
1
52
More sessions like this are lined up for QCon London 2027, April 13-16. Find out more about QCon London 2027 here: buff.ly/0Ut0uuP #QConLondon #CodingAgents #DeveloperExperience

QCon London 2027

Gain actionable insights from leading software developers on emerging trends and practices at QCon London 2027, April 13-15.

qconlondon.com
45
Chunking for RAG has two separate context-window constraints — and the embedding model can impose the tighter one.
1
99
Lan Chu, AI Tech Lead and Senior Data Scientist at Rabobank, explains: the largest embedding models top out at around 8,000 tokens, so chunking decisions need to account for the model creating the embeddings, not only the model generating the answer.
1
45
More sessions like this are lined up for QCon London 2027, April 13-16. Find out more about QCon London 2027 here: buff.ly/6cJwvMB #QConLondon #RAG #EmbeddingModels

QCon London 2027

Gain actionable insights from leading software developers on emerging trends and practices at QCon London 2027, April 13-15.

qconlondon.com
40
The longer a stateful Flink job runs, the more state it accumulates — eventually managing that state takes more CPU than the computation itself.
1
94
Giannis Polyzos, Principal Streaming Architect at Ververica, explains why compute-storage separation is a central design goal in Apache Fluss: separating growing state from the stream processor changes where the maintenance burden sits.
1
41
More sessions like this are lined up for QCon London 2027, April 13-16. Find out more about QCon London 2027 here: buff.ly/ohGB1Dr #QConLondon #ApacheFluss #StreamProcessing

QCon London 2027

Gain actionable insights from leading software developers on emerging trends and practices at QCon London 2027, April 13-15.

qconlondon.com
39
Recommendations at Airbnb were four orders of magnitude larger than fraud detection: each search ranked thousands of homes, each with thousands of features — roughly 1 trillion operations per request.
1
118
Nikhil Simha, Co-Founder & CTO at zipline.ai, explains how the Chronon engine was rewritten to pre-compute most of that work, while keeping the API identical so nothing upstream broke.

Agentic MLE | Zipline AI

Agentic improvement loops for your ML systems: agents run isolated experiments from backtest to production, with guaranteed online-offline consistency.

zipline.ai
1
50
More sessions like this are lined up for QCon London 2027, April 13-16. Find out more about QCon London 2027 here: buff.ly/hmdyzHB #QConLondon #FeatureStore #MLInfrastructure

QCon London 2027

Gain actionable insights from leading software developers on emerging trends and practices at QCon London 2027, April 13-15.

qconlondon.com
39
BlackRock’s Asimov separates data, intelligence/context, and applications/agents. Read the session abstract: buff.ly/dpVvgaF
1
64
It processes about 150,000 documents weekly across 10,000 companies. At QCon San Francisco 2026, Dan Wolf and Sri Annapurna Bhupatiraju will examine how permission-aware workflows move from experimentation to shared production capabilities.
34
Randy Shoup’s keynote at QCon London 2027 starts with a 9x gap between the highest-performing and median engineering organizations. Read the full abstract: buff.ly/cF4TStp
1
95
His argument comes back to fundamentals: fast inner-loop feedback, outer-loop flow, and modular architecture still shape how safely an organization can move faster.
31
Agent sessions can sit idle for 50–95% of their lifecycle while still holding state. See how AX and Agent Substrate avoid one always-on Pod per session: buff.ly/mEdfj2m
1
86
At QCon AI New York, Shruti Nair will share the architecture that followed Google’s internal agent deployments. Substrate snapshots memory and filesystem state, freeing 92% of RAM for 10x compute density, then restores sessions onto a warm pool in under 200 ms.
32
Load more