Abstracts

Applications to speak. These go through review and a decision.

TagsSpeakerRatingsFiles
Taming 40-Minute CI: Incremental Builds at Monorepo ScaleAccept QueueApproved—Abstract—Our monorepo CI took 40 minutes on a good day. This talk walks through how we cut it to 6 minutes with content-addressed caching, remote execution, and a test-selection model — including the two migrations that failed first. You'll leave with a decision framework for which incremental-build investments pay off at which repo sizes, and the graphs to convince your platform team.—————PRPriya RamanSswyx+kms-0033-speaker@ai.engineer—————
Docs That Answer Back: Retrieval-Grounded Documentation SitesAccept QueueApproved—Abstract—A 10-minute tour of turning a static docs site into one that answers questions with citations, stays honest when it doesn't know, and costs under $50/month to run. Live demo, real failure cases, and a checklist you can apply to your own docs this week.—————AOAda OkonkwoAOAda Okonkwo—————
Your AI Pair Programmer Is Lying to You: Verification Patterns That ScaleAccept QueueApproved—Abstract—Code generation is easy; trusting it is hard. This session covers verification patterns for AI-generated code — property tests, mutation coverage, snapshot judges, and CI gates — with data from 18 months of running them on a 200-engineer codebase. Includes what we stopped doing because it didn't catch anything.—————AOAda OkonkwoAOAda Okonkwo——5.00 (1 of 2)——
Multi-tenant Isolation for AI WorkloadsAccept QueueApproved—AbstractAI-014Serving many customers from shared model infrastructure without leaking context between them. Isolation boundaries, noisy-neighbour throttling, and the audit story that survived a security review.Talk (30 min)IntermediateEnglishInfrastructureOpen SourceSecuritySWSam WhitfieldSOSam OrganiserOct 10, 2026, 4:00 PMMain Hall3.25 (4)—1.7
Caching Strategies for Token SpendAccept QueueApproved—AbstractAI-013Semantic and exact caching in front of a production assistant. Hit rates by traffic type, the staleness bugs that followed, and the invalidation strategy we ended up with after two rewrites.Talk (30 min)BeginnerEnglishApplied AICostSecurityEPElena PetrovaADAmara DialloSOSam Organiser——2.31 (4) · 1.25–3.25—0.5
When to Say No to an AgentAccept QueueApproved—AbstractAI-012Not every problem deserves an agent. A decision framework drawn from six internal projects, three of which we cancelled, and what the cancelled ones had in common that we did not see at the time.Talk (30 min)AdvancedEnglishProductAgentsKMKofi MensahSOSam Organiser——3.13 (4)—2.9
Building an Internal Model GatewayAccept QueueApproved—AbstractAI-011We put every model call behind one internal service. This covers routing, per-team quotas, the audit trail that made compliance stop worrying, and the migration that let us swap a vendor in an afternoon.Talk (30 min)IntermediateEnglishEvaluationAgentsRAGMCMira CastellanosSOSam OrganiserMay 14, 2027, 5:00 PMOverflow Room2.88 (4)—3
Structured Output Without TearsAccept QueueApproved—AbstractAI-010Getting reliable JSON out of a model that would rather write prose. Grammar-constrained decoding, schema repair, and why we stopped asking the model to apologise for malformed output and started making it impossible.Talk (30 min)BeginnerEnglishInfrastructureOpen SourceJHJonas HalvorsenAOAda OkonkwoSOSam OrganiserMay 14, 2027, 4:00 PMOverflow Room2.44 (4) · 1.75–3.75—3
1–8 of 8
1 / 1
8 abstracts matching the current filters