Abstracts

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

TagsSpeakerRatingsFiles
Agents in Production: Field Notes from Cloudreach LabsPendingApproved—Abstract—A field report on running AI agents safely in production, covering guardrails, rollback, and observability lessons learned at Cloudreach Labs.—————Sswyx+kms-0033-speaker2@ai.engineerSswyx+kms-0033-speaker2@ai.engineer—————
Your AI Pair Programmer Is Lying to You: Verification Patterns That ScalePendingApproved—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.—————PRPriya RamanSswyx+kms-0033-speaker@ai.engineer—————
Docs That Answer Back: Retrieval-Grounded Documentation SitesPendingApproved—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.—————PRPriya RamanSswyx+kms-0033-speaker@ai.engineer—————
Your AI Pair Programmer Is Lying to You: Verification Patterns That ScalePendingApproved—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.—————Ssbek-speaker2@example.comSsbek-speaker2@example.com—————
Claude - EventPendingIn Review—Abstract—Test—————Ffarishussain021@gmail.comFfarishussain021@gmail.com—————
Closing RemarksPendingApproved—AbstractAI-039Closing thoughts, thanks, and what we would like to see submitted next year.Talk (30 min)AdvancedEnglishEvaluationOpen SourceSecuritySRSofia RossiSOSam Organiser————0.9
Opening Keynote: Why NowPendingApproved—AbstractAI-040Why this conference, why now, and what we hope you take away from the next two days.Talk (30 min)BeginnerEnglishProductOpen SourceWCWei ChenSOSam Organiser————1.2
Panel: The Ethics of AutonomyPendingApproved—AbstractAI-038Autonomy raises questions the industry has been deferring. A panel on accountability, disclosure and the decisions we are quietly making on users' behalf.Talk (30 min)IntermediateEnglishInfrastructureCostSecurityIKIdris KhanSOSam Organiser————0.2
Edge Inference on a BudgetPendingApproved—AbstractAI-009Running models close to users without a GPU budget. Quantisation choices, the memory ceiling on commodity edge hardware, and an honest account of the quality we traded away and where it turned out to matter.Talk (30 min)AdvancedEnglishApplied AIOpen SourceSecurityGAGrace AdeyemiKMKofi MensahSOSam Organiser——2.13 (4)—1.2
Streaming UIs for Slow ModelsPendingApproved—AbstractAI-008When the model takes eleven seconds, the interface is the product. Streaming, skeletons, optimistic rendering and the moment users decide something is broken — with the abandonment numbers that changed our minds.Workshop (120 min)IntermediateEnglishProductCostWCWei ChenSOSam Organiser——2.88 (4) · 1.75–4.25—2.8
Prompt Injection in the WildPendingApproved—AbstractAI-007A field report on prompt injection attempts against a public-facing assistant: what was tried, what worked, and which mitigations were theatre. Includes the payload that got past three layers of filtering.Talk (30 min)BeginnerEnglishEvaluationAgentsCostSRSofia RossiSOSam Organiser——3.25 (3)—1.5
Observability for Nondeterministic SystemsPendingApproved—AbstractAI-006Traditional observability assumes the same input gives the same output. We cover the tracing schema we settled on, how we sample when every request is unique, and how to alert on quality drift without drowning in false positives.Talk (30 min)AdvancedEnglishInfrastructureRAGIKIdris KhanSOSam Organiser——3.31 (4) · 2.25–4.5—2.6
Fine-tuning Is Not the AnswerPendingApproved—AbstractAI-005Fine-tuning is the first thing people reach for and usually the wrong one. We compare it against retrieval, prompt work and routing on the same three tasks, with the training costs and the maintenance burden included honestly.Talk (30 min)IntermediateEnglishApplied AIOpen SourceRAGNFNaomi FischerWCWei ChenSOSam Organiser——4.00 (4)—0.6
The Cost Curve of InferencePendingApproved—AbstractAI-004Inference costs do not scale the way finance expects. A breakdown of where our spend actually went across a year — prefill versus decode, cache hit economics, and the surprising fraction consumed by retries and abandoned streams.Talk (30 min)BeginnerEnglishProductOpen SourceSecurityTBTomas BergSOSam Organiser——2.63 (4)—1.9
Vector Databases at a Billion RowsPendingApproved—AbstractAI-002Everything is fast at ten million rows. We walk through what actually broke between one hundred million and a billion: index build times, memory-mapped segment churn, and the recall cliff nobody warns you about when you quantise too aggressively.Talk (30 min)IntermediateEnglishInfrastructureAgentsLMLuis MoreauSOSam Organiser——3.06 (4)—1.2
Evaluating RAG: Beyond VibesPendingApproved—AbstractAI-003Most RAG evaluation is a demo and a feeling. We describe the offline harness we built, why we abandoned answer-similarity scoring, and how a small hand-labelled set of two hundred questions caught regressions our automated metrics happily approved.Talk (30 min)AdvancedEnglishEvaluationCostSecurityPRPriya RamanSOSam Organiser——3.00 (4) · 1–5—2.8
Shipping LLM Agents Without Losing SleepPendingApproved—AbstractAI-001We ran agents in production for eighteen months and most of what we believed at the start was wrong. This covers the retry semantics, the budget guards and the three incidents that shaped our current design, including the one that took a weekend to unpick.Workshop (120 min)BeginnerEnglishApplied AIRAGAOAda OkonkwoTBTomas BergSOSam Organiser——3.31 (4)—1.1
1–17 of 17
1 / 1
17 abstracts matching the current filters