Presentations
Technical deep-dives for practitioners on specific capabilities
Context mastery for AI collaboration. Master #file, @workspace, #codebase, and #fetch for codebase-specific responses.
Under the hood diagnostics. Chat Debug View, customization diagnostics, and extension logs for systematic troubleshooting.
AI assistance at the terminal. Natural language to shell commands, git operations, and scripting workflows.
AI assistance beyond the IDE. PR reviews in browsers, issue triage on mobile, with full repository customizations.
Cross-session context persistence. Store preferences, project context, and workflow patterns that persist across all conversations.
Safe agentic execution. Network restrictions, filesystem limits, and execution controls for secure AI-assisted development.
Latest Copilot features in VS Code v1.107-v1.109. Agent sessions, Claude integration, terminal sandboxing, and productivity enhancements.
Programmable governance for AI agents. Real-time prevention, audit trails, and compliance enforcement at execution time.
Embedding AI agents in your applications. Build custom tools, bots, and automation with programmatic Copilot access.
The 4 configuration primitives. Instructions, prompts, skills, and agents — make Copilot understand your codebase better.
Rich UI in chat responses. Transform chat from text-only to interactive visual experiences with component-based MCP tools.
The Agent Client Protocol for universal AI integration. Use Copilot's agentic capabilities in any editor, tool, or workflow — not just VS Code.
Coordinated specialists working together. When you need multiple specialized roles like planners, reviewers, and testers collaborating.
Context isolation for complex workflows. Break work into focused phases using subagents—parallel execution without context pollution.
When agents work simultaneously. Run multiple agents on different branches without conflicts using Git worktree isolation.
From "assign to copilot" to full SDLC transformation. The 5-phase incremental path with 4-workflow architecture and historical context search.
Infrastructure for AI velocity. Rewire repositories, PR workflows, and CI/CD for AI-as-labor delivery agents (Gen-4 SDLC).
Scaling Copilot across organizations. From team silos to standardized foundations with measurable ROI.
Strategic thought leadership for technical decision-makers
No instruments, no delivery. Why enterprises can't fly on AI autopilot without governance, compliance, and audit trails.
The $2/hour engineer. Making the business case for AI agents—what work moves to $2/hour labor?
The invisible 80%. Beyond code generation—how agents transform issue triage, compliance, documentation, and knowledge transfer.
Hands-on training modules with personas, exercises, and metrics
The Challenge: Build FanHub in 8 hours. Meet the team, understand the messy codebase, embrace the constraint.
The magic file. Stop Copilot from guessing—document your architecture and patterns so AI suggestions are consistent.
From implementation to orchestration. Let AI research dependencies and plan multi-file features before coding.
Stop repeating yourself. Turn your best prompts into reusable, team-wide functions with built-in standards.
Teach Copilot what it doesn't know. Create domain-specific capabilities for APIs, templates, and infrastructure.
Beyond static files. Connect Copilot to live databases, APIs, and external tools as first-class context sources.
End context-switching overhead. Bundle tools, skills, and instructions into role-based presets you switch instantly.
Previous talks — content folded into other modules or superseded
Multi-agent workflows in VS Code. Design coordinated agent systems where specialized agents collaborate.
Autonomous agents with isolated context windows. Solve context bloat and parallelize research.
The Trust Factory. How AI agents transform CI from quality gate to trust manufacturing at scale.
Intent-based governance for large AI-generated diffs. When AI generates feature-scale code, how do you review it?
Rewiring repository topology for AI-as-labor. From quarterly releases to daily agent-driven delivery.
Multi-environment agent orchestration. Delegate, monitor, and switch between local, background, and cloud agents.
The foundation that unlocks everything. Master context primitives, persistent layers, and enforcement patterns for expert-level AI assistance.