01 / Agent runtime design
Who owns state when an agent runs for minutes, hours, or days?
State ownership, recovery, replay paths, durable execution, and approval boundaries for long-running agents.
QCon AI Boston 2027 · The AI conference for senior developers, architects & engineering leaders
Make your next production AI decision with the benefit of other teams’ experience.
Production is where you find out whether the system holds up, whether the trade-offs were right, and whether you can see what the agent actually did.
Learn how senior engineers approach state, context, evals, security, and inference once the work is in production, then use those reference points in the decisions you’re making.
Current pricing ends November 10th · $995
- Conference
- July 8–9, 2027 · 2 days
- Location
- Boston, MA
- Venue
- Boston University, George Sherman Union
- Format
- Senior practitioner-led · curated by a Program Committee
Past QCon AI attendees have included senior engineers from
Program
Explore the production AI decisions other teams are already making.
The 2027 program is being developed around these areas.
02 / Context engineering
How do you keep company context useful without flooding the prompt?
Memory, retrieval, context lifecycles, stale information, permissions, and deciding what belongs in context.
03 / Evals and observability
What do you need to see before deciding whether a change should ship?
Trace what the system saw, called, decided, and cost. Turn production behavior into checks that can inform release decisions.
04 / MCP and tool access
How much access should an agent have to internal systems?
Scoped permissions, tool ownership, audit trails, failure handling, and approval boundaries.
05 / Zero-trust agent security
Where do identity and permissions belong when an agent can take action?
Least privilege, bounded retrieval, sandboxing, approval points, and kill switches.
06 / Inference cost and latency
Which requests need the most capable model?
Routing, caching, batching, context size, token budgets, latency targets, and the cost of different model choices.
Get notified as speakers and sessions are announced
The 2027 program is being developed now. Sign up for updates as the program is published.
Roles
Find the production experience most relevant to the decisions you own.
Software architects
See how other teams decide where probabilistic behavior belongs, where deterministic code takes over, and how AI changes system boundaries.
Staff+ engineers
Compare approaches to recovery paths, degraded behavior, observability, and fitting agentic systems into the systems teams already operate.
ML and MLOps engineers
See how teams approach evals, model routing, context pipelines, inference, and monitoring in production.
Platform engineers
Compare approaches to shared model and tool access, eval infrastructure, observability, and cost controls.
Security engineers
See how teams define identity, permissions, data boundaries, tool access, and approval points.
Engineering leaders
See how other organizations approach ownership, shared standards, infrastructure choices, and reliability expectations across teams.
Attend as a team
Bring back shared production reference points.
Architecture, platform, security, ML, and engineering leadership can follow different parts of the program, then use the same production examples in the decisions they make together.
Split across the program. Compare what each person heard.
Bring the most useful examples back as shared context for the work already underway.
Make the case
Need approval to attend?
Connect QCon AI Boston to work already underway. Use the manager template or AI prompt to build a request around the sessions, production examples, and costs relevant to you.
Convince your managerThe QCon AI experience
See how production AI decisions play out in practice.
QCon AI sessions go beyond the final architecture. Hear what teams considered, what they chose, what changed once the system was running, and what they would approach differently now.
-
Alternatives
What else the team considered before choosing a direction.
-
Trade-offs
What they accepted, what they protected, and which constraints shaped the decision.
-
Production results
What held up, what changed, and what became important only after launch.
-
Hindsight
What the practitioner would keep, change, or approach differently now.
Different engineering teams may solve similar problems differently. Those differences give you more reference points for your own decisions.
You can ask speakers about the part that matters to your system and continue the technical discussion with other senior practitioners after the session.
Sponsored sessions are clearly identified separately from the editorial program.
Patterns and practices, not products and pitches.
Talks from QCon AI Boston 2026
Senior practitioners presented these talks at Boston University on June 1-2, 2026.
The 2027 speakers are still to be announced. These published QCon AI Boston 2026 sessions show the kind of first-hand production experience attendees can expect from QCon AI.
inference_cost_latency
Keeping ChatGPT Fast as AI Development Accelerates
Performance across client work, networking, authentication, CPU-side orchestration, context assembly, model routing, inference, streaming, and observability.
keynote
OpenAI
model routing
streaming
observability
context_engineering
Context Engineering at LinkedIn: How We Built an Organizational Context Layer for AI Agents with MCP
How LinkedIn built an organizational context layer for AI agents, including tool discovery and skills that encode institutional workflows.
LinkedIn
MCP
tool discovery
agent skills
inference_cost_latency
Building GenAI Platform at DoorDash
Shared infrastructure for routing, observability, fallbacks, batch inference, and multi-step AI workflows.
DoorDash
platform
fallbacks
batch inference
evals_observability
Building Reusable Evaluation Frameworks for Agentic AI Products
Tracing, evaluation datasets, offline evaluations, LLM-as-judge, rules-based checks, and ML metrics for production agents.
Elastic
tracing
LLM-as-judge
offline evals
Ask the follow-up question that matters to your system.
- 01 Ask why a team rejected an approach you are considering.
- 02 Hear another practitioner solve a similar constraint differently.
- 03 Continue the discussion with engineers working on related decisions in other companies.
The session gives everyone the same technical reference point. The conversation lets you follow the part that is relevant to your own system.
Why senior engineers trust QCon
What past QCon attendees say
QCon is a conference by engineers for engineers. I didn't feel like I was being sold something as part of the presentations, but rather like I was learning from what is actually happening in other companies.
QCon provides an opportunity to obtain new ideas and approaches to developing software. I have and would continue recommending QCon to anyone interested in keeping up with the latest trends by learning from those who are defining those trends.
QCon is a great place for industry leaders to share what they've learned, techniques they've discovered, and pitfalls to avoid without an overarching sponsor presence.
our attendees
Who attends
Senior engineering leaders, software architects, and team leads making decisions on production AI.
76%
are senior developers or higher: architects, leads, and engineering management
-
46%Eng. managers, senior management & architects
-
30%Senior developers & engineers
-
24%Developers
1:11
speaker : attendees
One speaker for every eleven attendees. Practitioners running production systems, close enough to reach between talks.
track record
20+ years of sharing what’s worth your team’s time
QCon and InfoQ have given major software technology shifts the same practitioner-led treatment: first-hand experience, technical depth, and the decisions behind production systems.
QCon AI applies that approach to production AI.
1M
read InfoQ every month
4,500+
attend QCon & Dev Summit each year
pricing
QCon AI Boston 2027 pricing
Early Bird: $995 through November 10th
The ticket price increases at the published dates below.
Price period
Price
- September 14th – November 10th Now $995
- November 11th – January 12th $1,095
- January 13th – February 9th $1,195
- February 10th – March 9th $1,295
- March 10th – April 13th $1,395
- April 14th – May 11th $1,495
- May 12th – June 15th $1,595
- June 16th – July 9th full price $1,695
All amounts are in USD. Pricing is subject to change without notice.
What you'd pay today
$995
Current price until November 10th
Register for QCon AI BostonThe price steps up at each deadline.
Group and alumni discounts
At launch
Groups of 10 or more receive $100 off each in-person ticket.
No other discounts apply during this period.
Regular group and alumni discounts begin in February.
From February 2027
Group size
Discount per ticket
- 3–6 attendees $50
- 7–10 attendees $75
- 11–15 attendees $100
- 16+ attendees $125
Group registration deadline: June 18, 2027
Alumni: $100 off from February.
Ask about team registrationPayment & deadlines
- Refunds: registration fees are non-refundable.
- Plans change: tickets can be transferred to a colleague. Email info@boston.qcon.ai.
- Only participants who have paid in full before the event start date are admitted or receive access credentials.
venue
Boston University, George Sherman Union
QCon AI Boston 2027 takes place at:
Boston University, George Sherman Union
775 Commonwealth Avenue
Boston, MA 02215
Accommodation for QCon AI Boston Participants
Book your stay through our official hotel portal for discounted group rates at hotels near the venue.
Find Your HotelQCon AI Boston is not affiliated with Boston University. The use of Boston University facilities does not constitute or imply endorsement or support by Boston University.
faq
Before you register
Are team discounts available?
Through February 9, 2027, groups of 10 or more receive $100 off each in-person ticket.
From February 10, group discounts are available for groups of three or more, ranging from $50 to $125 off per ticket depending on group size.
The group registration deadline is June 18, 2027.
Who is behind QCon AI?
QCon AI is produced by C4Media, the team behind QCon and InfoQ.
What is QCon AI Boston 2027?
QCon AI Boston is a two-day production AI conference for senior software engineers, architects, Staff+ engineers, ML/MLOps engineers, platform and security engineers, and engineering leaders.
It takes place July 8–9, 2027 at Boston University, George Sherman Union in Boston, MA.
Who should attend QCon AI Boston?
QCon AI Boston is for people responsible for how AI is designed, integrated, evaluated, secured, operated, or adopted inside production software systems.
That includes senior software engineers, architects, Staff+ engineers, ML/MLOps engineers, platform and security engineers, engineering managers, and technical leaders.
What will the 2027 program cover?
The program is currently being developed around agent runtime design, context engineering, evals and observability, MCP and tool access, zero-trust agent security, and inference cost and latency.
Speakers and sessions will be added as they are confirmed.
How is the QCon AI program built?
QCon hand-picks speakers for the first-hand production experience they bring to the engineering questions in the program.
Attendees hear the alternatives considered, the trade-offs behind a decision, what happened in production, and what the practitioner would approach differently now.
What will I take back from QCon AI Boston?
You will leave with production examples from other engineering teams: how they approached comparable decisions, which constraints shaped their choices, what changed after launch, and where they would take a different direction next time.
Those examples give you more reference points for the decisions in your own systems.
Is QCon AI Boston an introductory AI conference?
The program focuses on engineering decisions around running AI in production, including architecture, reliability, security, evaluation, infrastructure, and cost.
Why attend in person?
You can ask speakers why they chose one approach over another, hear different solutions to comparable constraints, and continue the technical discussion with engineers from other companies.
How much does QCon AI Boston cost?
See the full pricing schedule for later prices and deadlines.
When and where is QCon AI Boston 2027?
July 8–9, 2027
Boston University, George Sherman Union
775 Commonwealth Avenue
Boston, MA 02215
When will speakers be announced?
The 2027 program is currently being developed.
Bring more production experience to your next AI decision.
Spend two days with senior practitioners who have already made decisions around agents, context, evals, tool access, security, and inference in production.
Leave with more approaches, trade-offs, and production hindsight to draw on when making your own.
QCon AI Boston 2027
Early Bird: $995 through November 10th
Register for QCon AI Boston
July 8–9, 2027 · Boston University
Other QCon events
Unable to make it to QCon AI Boston?
Take a look at:
QCon San Francisco 2026
- when
- November 16-20, 2026
- where
- Hyatt Regency, San Francisco
QCon AI New York 2026
- when
- December 15-16, 2026
- where
- The Westin Jersey City Newport, New York
QCon London 2027
- when
- April 13-16, 2027
- where
- The QEII Centre, London
QCon AI Boston · Jul 8–9
$995 until November 10