A rapid-fire Q&A on running AI agents in production: what breaks, what monitoring actually catches problems, and the guardrails that matter most when agents touch real systems. 2027-05-11T16:00:00.000Z 2027-05-11T16:10:00.000Z Workshop Loft Lightning Talk Intermediate AI Engineering Marcus OkaforStaff Developer AdvocateCloudreach Labs 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. 2027-05-11T16:00:00.000Z 2027-05-11T16:30:00.000Z Embarcadero Studio Talk Advanced AI Engineering Priya RamanPrincipal EngineerLatticework Systems Longer context is not free. A cost model for context spend, with the break-even points where retrieval beats stuffing the window. 2027-05-11T16:00:00.000Z 2027-05-11T16:30:00.000Z Presidio Room Talk Intermediate AI EngineeringInfrastructure & Scale Jonas WeberInfrastructure LeadKestrel Compute Unglamorous optimisations with outsized effects, benchmarked on production traffic rather than a synthetic loop. 2027-05-11T16:00:00.000Z 2027-05-11T16:30:00.000Z Mission Hall Talk Intermediate Infrastructure & Scale Kwame BoatengStaff EngineerAnansi Systems 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. 2027-05-11T16:30:00.000Z 2027-05-11T16:40:00.000Z Mission Hall Lightning Talk Beginner Developer Experience Priya RamanPrincipal EngineerLatticework Systems 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. This session now includes a live demo of remote build caching. Attendees should bring a laptop. 2027-05-11T17:00:00.000Z 2027-05-11T17:30:00.000Z Room 2A Talk Intermediate Platform & Infra Priya RamanPrincipal EngineerLatticework Systems Marcus OkaforStaff Developer AdvocateCloudreach Labs A migration story across four teams: the ownership model, the CI that made it safe, and the two rewrites we would skip if we did it again. 2027-05-11T17:00:00.000Z 2027-05-11T17:30:00.000Z Golden Gate Ballroom Talk Intermediate Infrastructure & ScaleProduct & Practice Elena VasquezDirector of EngineeringHalcyon Data Review queues, escalation and undo, designed so the humans in the loop stay willing to be in it. Patterns, anti-patterns and measured throughput. 2027-05-11T17:30:00.000Z 2027-05-11T18:15:00.000Z Presidio Room Panel Beginner Product & Practice Grace OyelaranProduct EngineerFernwood Sofia BianchiEngineering ManagerVantage Grid Elena VasquezDirector of EngineeringHalcyon Data A field report on running long-lived agents in production: timeouts, retries, poison inputs, and the runbook that finally made the pager quiet. We started with one agent that could file a support ticket and ended up with a fleet of them touching billing, inventory and customer email. Everything that broke, broke at night — a tool call that hung for nineteen minutes, a retry loop that re-sent the same refund four times, and a prompt change that quietly doubled token spend on the busiest queue of the week. This keynote walks through the three incidents that reshaped our architecture and the guardrails we shipped after each one: hard per-step deadlines, idempotency keys on every side effect, a spend ceiling enforced outside the model, and a replay view that lets an on-call engineer see exactly what the agent believed at the moment it went wrong. You will leave with the runbook we now hand to every team before their agent gets production credentials, the four dashboards we page on, and an honest account of which safeguards were worth the engineering time and which ones we deleted six weeks later. 2027-05-12T16:00:00.000Z 2027-05-12T16:45:00.000Z Golden Gate Ballroom Keynote Advanced Agents & ToolingInfrastructure & Scale Samuel AdeyemiCTOPathfinder Robotics Evaluations are usually treated as an internal chore. We shipped ours to customers instead, and it changed how the whole team argued about quality. 2027-05-12T17:15:00.000Z 2027-05-12T17:40:00.000Z Mission Hall Talk Intermediate AI Engineering Diego FerreiraStaff ML EngineerCartograph AI Three years of retrieval architectures, what survived, what did not, and why the boring parts (chunking, freshness, permissions) still decide the outcome. 2027-05-12T18:00:00.000Z 2027-05-12T18:25:00.000Z Presidio Room Talk Intermediate AI Engineering Amara OkonkwoSecond BaseNorthwind Labs A twenty-minute look at how Kestrel Compute schedules mixed CPU/GPU workloads, presented by our platinum sponsor. 2027-05-12T19:30:00.000Z 2027-05-12T19:55:00.000Z Golden Gate Ballroom Talk Infrastructure & Scale Jonas WeberInfrastructure LeadKestrel Compute Caching, batching, routing and quantisation, measured end to end on a real workload. Includes the changes that looked clever and made things worse. Our inference bill grew faster than our traffic for two quarters straight, and the obvious answers — a smaller model, a cheaper provider — were off the table for quality reasons. So we went looking for the money everywhere else: in the cache we were not reusing, in the requests we were sending one at a time, and in the long tail of prompts nobody had read since launch. In this hands-on session we rebuild that programme from scratch against a live workload. You will add a prompt cache and measure the real hit rate rather than the hoped-for one, batch a stream of requests and watch the latency percentiles you just traded away, route by difficulty so the expensive path only handles the requests that need it, and trim context that has been dead weight since the second sprint. We finish with the cost model we now review monthly — cost per resolved request rather than cost per token — plus the two optimisations we rolled back and the graphs that told us to. Bring a laptop; every exercise ships with a workload you can run locally. 2027-05-12T20:30:00.000Z 2027-05-12T22:00:00.000Z Workshop Loft Workshop Advanced Infrastructure & Scale Jonas WeberInfrastructure LeadKestrel Compute Priya RamanathanHead of PlatformLumen Systems Schema drift, partial responses and retries: why validating model output belongs in the same mental model as any other unreliable network call. 2027-05-13T16:30:00.000Z 2027-05-13T16:55:00.000Z Golden Gate Ballroom Talk Advanced AI EngineeringAgents & Tooling Mei-Lin ChaoFounding EngineerTessellate Live-coded from an empty file: a minimal, debuggable tool-calling loop with cancellation, tracing and a sandbox, and what each abstraction buys you. 2027-05-13T18:00:00.000Z 2027-05-13T19:30:00.000Z Embarcadero Studio Workshop Intermediate Agents & Tooling Tobias AnderssonDeveloper AdvocateRivergate OSS Traces, spans and sampling when the same input legitimately produces different output. What to log, what to redact, and how to make it searchable. 2027-05-14T17:00:00.000Z 2027-05-14T17:25:00.000Z Mission Hall Talk Advanced Infrastructure & Scale Yuki TanakaApplied ScientistOrinoco Labs