Uncover emerging trends and practices from the world’s most innovative software professionals to help you validate your software roadmap. Celebrating 20+ years.
Joined March 2008
- Tweets12.2K
- Following674
- Followers7.4K
- Likes1.9K
Batch APIs can look attractive for background agent workloads, but batch latency applies to every request.
Meryem Arik, Co-Founder and CEO at Doubleword, on why an agent with 20 to 30 sequential prompts can take 20 to 30 days end to end.
More sessions like this are lined up for QCon London 2027, April 13-16.
Find out more about QCon London 2027 here: buff.ly/aBnAUeP
#QConLondon #AIAgents #AIInfrastructure
LinkedIn's first approach to agent memory had each application identify and store its own signals. Every new use case needed another bespoke integration.
Karthik Ramgopal, Distinguished Engineer at LinkedIn, on why the memory layer had to become shared infrastructure.
More sessions like this are lined up for QCon London 2027, April 13-16.
Find out more about QCon London 2027 here: buff.ly/U7LjaAc
#QConLondon #AIAgents #AIEngineering
How does Pinterest serve vision-language models efficiently?
Salina Wu and Cristian Lopez will discuss their NVIDIA Dynamo stack at QCon AI New York, Dec 15–16.
See the schedule: buff.ly/JysYDJz
Pinterest's session covers disaggregated inference, KV-aware routing, and cache offloading for multimodal workloads.
Datadog will examine how it cut cost per AI interaction to one-third while maintaining quality and latency.
LangChain enforces six distinct rules around lazy imports, at different levels of the repository, and very little of that is documented in one place.
Jeff Smith, CEO & Co-Founder at Neoteny AI, on why a coding agent working from general model knowledge can't know the rules that make a PR mergeable.
More sessions like this are lined up for QCon London 2027, April 13-16.
Find out more about QCon London 2027 here: buff.ly/SPwJhBf
#QConLondon #AIEngineering #CodingAgents
A registry turns agents into owned, versioned artifacts before governance adds controls.
Sahil Vashishat explains BlackRock's build order at QCon AI New York.
Read the abstract: buff.ly/gvlgCiS
The stack was built in dependency order: a shared model interface, then evals and guardrails, a common representation for canvas and SDK, an agent registry, governance, and a skills hub.
Agent reasoning loops can keep running without a useful result while the inference bill grows.
Meryem Arik, Co-Founder and CEO @Doubleword_, on a simple production guardrail: set a cost ceiling per task and flag anything that crosses it.
More sessions like this are lined up for QCon London 2027, April 13-16.
Find out more about QCon London 2027 here: buff.ly/bISxVox
#QConLondon #AIAgents #AIInfrastructure
The instinct when building agent memory is to preserve everything. It doesn't scale.
Karthik Ramgopal, Distinguished Engineer at LinkedIn, on why the harder problem is deciding what deserves to be remembered and when information is no longer worth keeping.
More sessions like this are lined up for QCon London 2027, April 13-16.
Find out more about QCon London 2027 here: buff.ly/qg1LjJc
#QConLondon #AIAgents #AIEngineering
Easier code generation doesn't remove production ownership.
Suhail Patel hosts QCon San Francisco's track on verification, code review, and who operates what gets built.
Explore the track: buff.ly/0wHN3ta
Repo-specific fine-tuning doesn't necessarily require a frontier-sized model or an enormous evaluation budget.
Jeff Smith, CEO & Co-Founder at Neoteny AI, on Allen AI's SERA approach, which uses softly verified execution to cut evaluation costs during training.
More sessions like this are lined up for QCon London 2027, April 13-16.
Find out more about QCon London 2027 here: buff.ly/rgInDF1
#QConLondon #AIEngineering #LLMs