World Congress 2026 Europe • Jul 10, 2026 • Session details

How building with AI can double the throughput of your engineering team

Brian Scanlan

Facing plunging growth, Intercom didn't just launch a chatbot. They treated AI like a senior engineer with deep system access—and tripled their R&D throughput in 16 months.

Pause
Mute Enter Fullscreen
#1 about 6 min

Intercom's strategic pivot to an AI-first software company

How Intercom shifted its entire business model to focus on AI products following the release of ChatGPT.

#2 about 3 min

Setting the ambitious goal to double engineering throughput

Mandating a two-fold increase in production deployments and real feature changes without compromising quality or security.

#3 about 2 min

Achieving and sustaining three times engineering productivity

Reaching the productivity goal months early and maintaining the momentum across the entire research and development workflow.

#4 about 3 min

Driving organizational change through clear engineering mandates

How leadership enforced AI adoption by updating engineering expectations, offering rewards, and providing dedicated enablement teams.

#5 about 3 min

Committing to a unified foundational platform strategy

Choosing a single AI platform and integrating it deeply rather than fragmenting efforts across multiple tools and models.

#6 about 3 min

Integrating AI agents as senior engineering team members

Granting Claude full access to internal tools and onboarding it with coding standards, architecture rules, and testing guidelines.

#7 about 2 min

Focusing developer effort on durable evergreen skills

Prioritizing the unblocking of knowledge, context, and environment access over building transient tool-specific workflows.

#8 about 3 min

Prompting agents with high-level problems instead of tasks

Providing AI agents with broad problem contexts empowers them to autonomously determine the necessary skills and actions for resolution.

#9 about 2 min

Measuring developer experience and the cost of output

Tracking positive trends in developer satisfaction alongside a plunging total cost of ownership per code change.

#10 about 2 min

Eliminating legacy defect backlogs and accelerating feature delivery

Using AI to reach zero defects and significantly halve the time required to ship real features to customers.

#11 about 2 min

Composing small tasks into powerful open-source skills

Building composite automation skills for specific development tasks to create comprehensive workflows like thermonuclear code reviews.

#12 about 2 min

Capturing AI session telemetry for deep usage insights

Recording and analyzing agent session transcripts to identify gaps and improve AI integration across the engineering lifecycle.

#13 about 2 min

Expanding AI agents across workflows and team structures

Deploying dedicated agents for tasks like deployment monitoring while experimenting with manager-less, cross-functional engineering roles.

Matching moments

1:55 min

Shifting developer workloads and realistic AI productivity gains

Chris Heilmann Chris Heilmann +2 · LIVE

1:44 min

Summarizing developer experience and artificial intelligence companions

Robert Hoffmann Robert Hoffmann +1 · LIVE

2:04 min

Inspiration and challenges of scaling AI agent communication

diabhey diabhey · World Congress 2025

1:21 min

Using artificial intelligence to reimagine developer experience

Alexander Trusheim Alexander Trusheim +1 · World Congress 2025

1:23 min

Developer adoption of integrated AI chat features

Julia Kasper · Coffee With Developers

3:46 min

Leveraging AI efficiencies to scale development output

Daniel Gebler Daniel Gebler +2 · World Congress 2025