DevFlow Conf 2027

A rapid-fire Q&A session on running AI agents in production: reliability, guardrails, and what breaks first when agents meet real users.

• MO Marcus Okafor Staff Developer Advocate, Cloudreach Labs

A first-time speaker walk of the live call. What a person sees from the street to the receipt, then back to their own proposal after the organizers decide.

• AB Ada Bennett

What actually breaks at that size, in the order it breaks: code ownership, CI queueing, and the review culture nobody wrote down. Two things we would do again and one we would not.

• Dmitri Sokolov Infrastructure Architect, Ravenline

A working account of cutting inference cost by an order of magnitude without giving up latency: continuous batching, speculative decoding, and the three quantisation choices that actually mattered. Includes the two approaches that lost us a month.

• Priya Raman Principal Engineer, Northwind Labs

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.

• PR Priya Raman Principal Engineer, Latticework Systems
• MO Marcus Okafor Staff Developer Advocate, Cloudreach 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.

• PR Priya Raman Principal Engineer, Latticework 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.

• PR Priya Raman Principal Engineer, Latticework Systems

Build times decay for boringly consistent reasons. We instrumented ours for a year; this is what we found, in order of how much time each cost, and what fixing them actually took.

• Marcus Okafor Staff Platform Engineer, Meridian Systems

Every flag system starts as a boolean and ends as a query planner. How we cut evaluation latency to microseconds, and why the interesting part turned out to be deletion, not rollout.

• Nadia Farouk Senior Software Engineer, Ostmark
• AN Amara Nwosu Product Engineer, Ostmark

Six months of attempts against a customer-facing assistant, what got through, and the four mitigations that survived contact. No threat-model diagrams — just the payloads and what they cost us.

• Tomiwa Adeyemi Security Engineer, Northwind Labs

We put a stopwatch on the first merged pull request and treated every hour as a bug. Eleven days down to one, and the three fixes that did most of it.

• JP Joon-ho Park Engineering Manager, Harbour

A paved road only works if leaving it is allowed. How we measured which teams stepped off ours, why they did, and what we changed instead of enforcing compliance.

• Elena Vasquez Principal Designer, Cascade