QCon AI Boston 2026
2026-06-01..2026-06-02
Boston, United States
as the organisers put it
QCon AI Boston, July 8–9, 2027. Bring more production experience to your AI decisions with senior practitioners sharing trade-offs, results, and hindsight.
who it's for
software architects, platform engineers, machine learning engineers, engineering managers, site reliability engineers, developer experience engineers, data engineers, security engineers
topics
deterministic context engines; semantic tool routing; checkpointed agent orchestration; skill store and executable skills; verification gates for agentic code; organizational context ingestion; MCP server catalog management; PII schema extraction and masking; end-to-end agent audit trails; agent trust lifecycle practices; real-time personalization with bandits
| title | author | length |
|---|---|---|
| From Prompt Hacking to Architectural Determinism: Engineering Reliable GenAI Systems | Hugo Guerrero | 50m |
Models fail when updates, context drift, and window compression change outputs, so the claim is to stop relying on prompts and instead make the LLM a router… | ||
| Beyond Sandboxes: Architecting Durable Runtimes for AI Agents | Viren Baraiya | 26m |
Argues production AI agents need an orchestration layer that persists state, checkpoints every step, and recovers from crashes — demonstrated by killing a run… | ||
| Solving Context Bloat: Semantic Tool Routing in Multi-Server MCP Environments | Hugo Guerrero | 49m |
Concrete setup: a TypeScript Volcano agent behind a Kong AI gateway calls OpenAI (GPT‑4) and registers MCP servers via a catalog. Adding one MCP server jumps a… | ||
| Making AI Reliable in the SDLC: The Role of Deterministic Context at Scale | Julien Godfroid, Max Kozinenko | 39m |
Claims concrete outcomes: grounding LLM coding agents in CAST’s deterministic, graph-based context cuts token use about 50%, doubles result accuracy and… | ||
| Leverage AI to Protect Your Data Assets... from AI | Daniyar Mussakulov | 31m |
Claim: flexible NoSQL data hides PII and AI-driven code changes speed leaks unless data is governed. Demonstrates schema extraction from live MongoDB/JSON… | ||
| Building the Context Engine AI Agents Need | Brandon Waselnuk | 31m |
Claim: agents fail from missing organizational context, not intelligence. A context engine built by Unblocked ingests Git, Jira/Linear, Notion/Confluence… | ||
| Make Quality Executable: Verification Gates for Agentic Engineering at Scale | Nnenna Ndukwe | 51m |
Claims that embedding verification gates at planning, implementation, local pre PR, CI and PR stages is the scalable way to keep code quality while using… | ||
| The Trust Lifecycle for Safe, Secure and Reliable AI Agents | Anuj Tambwekar | 38m |
Vizu presents an Agent Trust Lifecycle: build agents with deterministic tools for IDs and math, add a grounding guardrail to verify outputs, and run multi-pass… | ||
| From Demo to Production: Why Agentic AI Systems Fail - and How to Fix Them | Venugopal Jidigam | 39m |
Claim: agentic failures are a systems problem, not a model one. A platform built for 10M+ users hits four concrete failure patterns: context overload from… | ||
| Vibecoding your Own Multi-Agent Workstation | Robert Brennan | 46m |
Argues you should fork an open-source harness (Open Hands, OpenClaw, Hermes), deploy it in cloud VMs or isolated containers, and start with low-risk review… | ||
| Autonomous Marketing at Klaviyo: Architecting Composer and 1:1 Personalization at Scale | Liang Zhang | 10m |
Klaviyo runs on a real-time data platform that ingests 2.5 billion daily events from 350 integrations and 7.3 billion customer profiles to power autonomous… | ||
| The MCP Megalith: Surviving the 1,000-Tool Explosion and Auth Fragmentation | Neil Mansilla | 51m |
MCP adoption jumps from ~100 to 30,000 MCP servers in months, causing context‑window bloat, quarterly spec reversals, and OAuth fragmentation that breaks… | ||
| Klaviyo Customer Agent: Building Bi-Directional Conversational Commerce at Scale | Elliot Penson | 54m |
Klaviyo builds a real-time, bi-directional commerce agent that serves millions of queries across web, SMS and email by combining multi-tenant RAG pipelines… | ||
| nothing matches | ||