You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The Build //LOCALHOST event content kit is not yet available. You will be notified when it is ready.
8
-
:::
6
+
Everything you need to run Build //LOCALHOST in one place. This page brings together the workshop materials and breakout sessions that make up the event program, so chapter leads and speakers can plan their agenda, prepare delivery, and know exactly what to expect from each session. Browse the hands-on labs and talks below — each entry includes a description and a level rating to help you pick the right content for your audience.
9
7
10
-
## Recorded Opening
8
+
> [!NOTE]
9
+
> Links to the GitHub repos will be added soon.
11
10
12
-
*Coming soon*
11
+
> [!TIP]
12
+
> **Good news for your Build //LOCALHOST meetup!**
13
+
>
14
+
> We are offering pre-configured lab environments through Skillable, identical to what attendees used at Build. That means no setup work for you — you just pick the lab and run it.
15
+
>
16
+
> To get started, tell us which lab you want to use. Fill out the form below and the team from Microsoft and Skillable will connect with you directly to set up your environment.
17
+
>
18
+
> **Form:**[Build //localhost – Fill out form](https://forms.cloud.microsoft/e/V0uAYTBWWD)
19
+
>
20
+
> Please complete it **no later than 7 days before your event**, so everything is provisioned in time.
21
+
>
22
+
> Please note that only approved events can get lab support through Skillable. We also have Azure Credits available for everyone.
13
23
14
-
## Slide Deck
24
+
## Workshop Materials
15
25
16
-
*Coming soon*
26
+
### From zero to deployed on Azure with AI agents
17
27
18
-
## Workshop Materials
28
+
What happens when you let AI agents do the building? In this hands-on lab, you'll go from an empty terminal to a deployed app on Azure — with GitHub Copilot CLI and coding agents handling the scaffolding, coding, debugging, and deployment. You'll use the new Azure skills to provision resources and wire up services through natural language, no portal required. This isn't a demo you watch. You'll walk out with a real, working dev workflow you can take straight to your next project.
29
+
30
+
**Level:** (300) Advanced
31
+
32
+
**> [GitHub Repo](https://github.com/microsoft)**
33
+
34
+
----
35
+
36
+
### Get Started with Models in Microsoft Foundry to Build AI Apps
37
+
38
+
In this hands-on lab, you will build a production-ready AI application using Microsoft Foundry, with no fine-tuning or deep machine learning expertise required. You will discover and select models, provision a Foundry project, and connect to a hosted model using the OpenAI SDK. You'll implement a comment moderation workflow, compare model outputs, and package the solution as a hosted agent using Python, ready for real-world integration.
39
+
40
+
**Level:** (300) Advanced
41
+
42
+
**> [GitHub Repo](https://github.com/microsoft)**
43
+
44
+
----
45
+
46
+
### Observe, optimize and protect your hosted agents in Microsoft Foundry
47
+
48
+
Modern agents fail in ways traditional monitoring can't catch. In this hands-on lab, learn how Microsoft Foundry Observability helps you move from prototype → production with context-specific evaluation suites (auto-generated evaluators + test datasets) wired into developer workflows via skills/MCP tooling for hosted agents. Then scale quality with continuous evaluation, trace-linked analysis, and adaptive red teaming—and walk away with a sandbox to explore additional features on your own.
49
+
50
+
**Level:** (300) Advanced
51
+
52
+
**> [GitHub Repo](https://github.com/microsoft)**
53
+
54
+
## Breakout Sessions
55
+
56
+
### Developer Tools & Frameworks: GitHub Copilot in Visual Studio: Agents That Debug, Profile, and Test
57
+
58
+
Every IDE has agentic code generation now, but Visual Studio goes further with built-in agents that tackle what code generation can't. In this demo-heavy session, you'll see agents root-cause bugs using live runtime behavior, pinpoint performance bottlenecks and recommend targeted fixes, and build test coverage to catch regressions before they ship. These aren't just code-writing agents. They help enterprise C#, .NET, and C++ developers improve code quality with expert-level diagnostics.
59
+
60
+
**Level:** (300) Advanced
61
+
62
+
**> [GitHub Repo](https://github.com/microsoft)**
63
+
64
+
----
65
+
66
+
### Developer Tools & Frameworks: From CLI to PR: Automating the path to merged code
67
+
68
+
Everyone talks about agents, but the real challenge is applying them to daily sprints. Moving beyond chat, we'll show how GitHub Copilot functions as an agentic partner in your workflow by live-coding a full cycle—from planning in the terminal to delegating work to the cloud and automating PR reviews. No high-level abstractions here. Just technical mechanics: context management, advanced features with Copilot CLI, and the patterns that make agentic workflows actually stick.
69
+
70
+
**Level:** (400) Expert
71
+
72
+
**> [GitHub Repo](https://github.com/microsoft)**
73
+
74
+
----
75
+
76
+
### Developer Tools & Frameworks: Your agent, anywhere: MultiClient, MultiDevice with GitHub Copilot SDK
77
+
78
+
Agents are powerful on your machine, but what happens when you need them everywhere else? In this session, we'll show how GitHub Copilot SDK lets you build an agent, embed it in an app, and take it with you across devices and into the cloud. You'll see how to go from a local agent to one you can access on your phone, move between machines, and run across multiple clients. If you've been working with agents locally and wondering what the next step looks like, this is it.
79
+
80
+
**Level:** (300) Advanced
81
+
82
+
**> [GitHub Repo](https://github.com/microsoft)**
83
+
84
+
----
85
+
86
+
### Cloud Platform & Data: Idea to production-ready agent in seconds on AI-native runtime
87
+
88
+
Agentic apps behave differently from traditional services. They make decisions, coordinate steps, and react to changing inputs. This session shows how to run agentic workloads on a fast, AI native runtime on Azure Container Apps. The focus is on reliability and speed so you can move from idea to production‑ready agents. We'll cover patterns for deployment, configuration, safe scaling for bursty traffic, and observability so teams can run agentic systems in production without surprises.
89
+
90
+
**Level:** (300) Advanced
91
+
92
+
**> [GitHub Repo](https://github.com/microsoft)**
93
+
94
+
----
95
+
96
+
### Cloud Platform & Data: The honest practitioner's take on agentic AI on Kubernetes
97
+
98
+
Agentic AI workloads don't behave like normal services. They're stateful, bursty, multi-step, and often span more than a single cluster. Most teams figure this out the hard way. This session is for developers building agentic AI in production. We'll show you how to get the most out of Kubernetes for training, inference, and agent orchestration, covering purpose-built tooling, managed options, open-source inference at scale, and AI-assisted dev tools that support real-world AI operations.
99
+
100
+
**Level:** (300) Advanced
101
+
102
+
**> [GitHub Repo](https://github.com/microsoft)**
103
+
104
+
----
105
+
106
+
### Cloud Platform & Data: From rows to reasoning: Designing databases for AI apps and agents
107
+
108
+
AI applications and agents require data platforms designed for reasoning, not just transactions. Traditional architectures force developers to stitch data systems together, adding latency and complexity. In this demo‑rich session, we'll show the latest innovations in SQL Database and Cosmos DB, then build an app on Azure HorizonDB, Azure's new cloud‑native PostgreSQL service, to show how AI apps built directly in the database simplifies design and enables reasoning over operational data.
109
+
110
+
**Level:** (300) Advanced
111
+
112
+
**> [GitHub Repo](https://github.com/microsoft)**
113
+
114
+
----
115
+
116
+
### Working with Models: Confident model selection and integration with Microsoft Foundry
117
+
118
+
Discover how to quickly choose, integrate, and validate AI models inside Microsoft Foundry. Learn techniques for navigating thousands of model options, benchmarking performance, and streamlining your workflow with deep IDE support. Build faster, ship smarter, and stay on top of the evolving AI landscape.
119
+
120
+
**Level:** (300) Advanced
121
+
122
+
**> [GitHub Repo](https://github.com/microsoft)**
123
+
124
+
----
125
+
126
+
### Working with Models: Deploy. Observe. Learn. Reinforcement learning for production agents
127
+
128
+
Agents don't fail in demos — they fail in production. In this breakout, see how teams use fine-tuning and reinforcement learning on Microsoft Foundry to improve production agents using real usage signals. We cover when fine-tuning reduces cost and latency, when RL delivers deeper gains, and how Foundry makes it easy to train, evaluate, and redeploy safely. Johnson & Johnson shares their journey from RL experiments to production.
129
+
130
+
**Level:** (200) Intermediate
131
+
132
+
**> [GitHub Repo](https://github.com/microsoft)**
133
+
134
+
----
135
+
136
+
### Working with Models: Get Started with Models in Microsoft Foundry to Build AI Apps
137
+
138
+
In this hands-on lab, you will build a production-ready AI application using Microsoft Foundry, with no fine-tuning or deep machine learning expertise required. You will discover and select models, provision a Foundry project, and connect to a hosted model using the OpenAI SDK. You'll implement a comment moderation workflow, compare model outputs, and package the solution as a hosted agent using Python, ready for real-world integration.
139
+
140
+
**Level:** (300) Advanced
141
+
142
+
**> [GitHub Repo](https://github.com/microsoft)**
143
+
144
+
----
145
+
146
+
### Agents & Apps: Build context‑aware agents at scale with Microsoft IQ
147
+
148
+
High performance agents are built on intelligence that brings together context, enterprise data, orchestration, and governance. Learn how Foundry IQ, Fabric IQ, and Work IQ provide the enterprise intelligence layer for AI agents. Design agents that can search across organizational knowledge, reason over business data, and operate with awareness of people and work signals. Take action within trusted boundaries, providing a practical foundation for building scalable and reliable agents.
149
+
150
+
**Level:** (200) Intermediate
151
+
152
+
**> [GitHub Repo](https://github.com/microsoft)**
153
+
154
+
----
155
+
156
+
### Agents & Apps: Build and host enterprise-grade AI agents with Microsoft Foundry
157
+
158
+
AI agents are transforming how developers build software—but shipping production-grade agents demands more. This session walks through the end-to-end lifecycle of building AI agents with Foundry Agent Service and Microsoft Agent Framework. See how to go from local prototyping to enterprise-grade hosted deployment with identity, secure networking, evaluations, and lifecycle management. Learn how coding agents like GitHub Copilot integrate directly into the workflow.
159
+
160
+
**Level:** (300) Advanced
161
+
162
+
**> [GitHub Repo](https://github.com/microsoft)**
163
+
164
+
----
165
+
166
+
### Agents & Apps: Claw agents and multi-agent systems on Foundry
167
+
168
+
Go deep on multi-agent systems built on Microsoft Foundry, featuring Claw agent patterns and the hosted agents architecture. Explore long-running agents with triggers, state management, and file access—all natively supported on Foundry. See how coding agents built with GitHub Copilot SDK and Claude Agent SDK integrate into multi-agent workflows using Microsoft Agent Framework. Learn how to coordinate, host, and operate these systems with observability and continuous evals.
169
+
170
+
**Level:** (400) Expert
171
+
172
+
**> [GitHub Repo](https://github.com/microsoft)**
173
+
174
+
----
175
+
176
+
### Responsible AI: Observability for AI agents on any framework
19
177
20
-
*Coming soon*
178
+
Nondeterministic, multi-agent systems break traditional monitoring. As agents move into production, developers need observability built into the workflow, not bolted on after failures. This session explores what modern observability looks like for AI agents: how tracing and evaluation must work across any framework, why the inner loop deserves the same rigor as the outer, how context-specific evals evolve with your agent, and how always-on signals tie behavior to business outcomes.
Copy file name to clipboardExpand all lines: build/organize.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -26,12 +26,12 @@ To register your event as part of Microsoft Build //localhost, follow th
26
26
27
27
## 2. What You Receive
28
28
29
-
-**Event in a box content** — recorded opening, slide deck, branding assets, workshop materials, and talking points - [Event Content](/build/content.md)
29
+
-**Event in a box content** — slide deck and workshop materials - [Event Content](/build/content.md)
30
30
-**Azure Subscriptions** for hands-on labs — [request credits here](/chapter-benefits/azure.md)
31
31
-**F&B credit ($600 USD)** — reimbursement (the amount depends on the number of attendees and location.)
32
32
33
33
::: tip
34
-
The content kit will be available on the [Event Content](/build/content.md) page. You will get notified when it is ready.
34
+
The content kit is available on the [Event Content](/build/content.md) page.
0 commit comments