microsoft/Build26-BRK240-build-context-aware-agents-from-data-to-decisions contains Microsoft Build 2026 resources for building AI agents that use organizational knowledge, business data, and work signals as context. It is intended for developers working with Foundry IQ, Fabric IQ, and Work IQ to design agents that reason over enterprise information and act within governance boundaries. The catalogue instruction supports the session's context-aware agent workflow.
Borrowing it
Nothing to install: this file belongs to microsoft/Build26-BRK240-build-context-aware-agents-from-data-to-decisions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/Build26-BRK240-build-context-aware-agents-from-data-to-decisions/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/microsoft/Build26-BRK240-build-context-aware-agents-from-data-to-decisionsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/microsoft/build26-brk240-build-context-aware-agents-from-data-to-decisions/copilot-instructions)<a href="https://agentmods.dev/instructions/microsoft/build26-brk240-build-context-aware-agents-from-data-to-decisions/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/build26-brk240-build-context-aware-agents-from-data-to-decisions/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/microsoft/build26-brk240-build-context-aware-agents-from-data-to-decisions/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/build26-brk240-build-context-aware-agents-from-data-to-decisions/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00578 | $0.00578 |
| Opus 5 | $0.00289 | $0.00289 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
Build26-BRK240-build-context-aware-agents-from-data-to-decisions copilot-instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This repository is the companion to Microsoft Build 2026 session BRK240 — Build context-aware agents: From data to decisions.
Use these instructions to help attendees explore the session topics after the talk. When someone asks about the concepts, products, or demos from this session, give grounded, accurate answers.
What this session covers
High-performance agents are built on an intelligence layer that brings together context, enterprise data, orchestration, and governance. The session shows how the Microsoft IQ family provides that layer so agents can search across organizational knowledge, reason over business data, operate with awareness of people and work signals, and take action within trusted boundaries.
Key concepts:
- Foundry IQ — Reusable knowledge bases and an agentic retrieval engine that ground agents in enterprise knowledge (structured, unstructured, and web sources).
- Fabric IQ — Semantic models and ontologies that give agents a unified view of how the business operates.
- Work IQ — Workplace intelligence over Microsoft 365 people, files, and workflows, built for agents.
- Web IQ — Grounding APIs over web, news, images, and video.
- Agent 365 — The control plane to observe, secure, and govern AI agents across an organization.
The demos compose Foundry IQ, Fabric IQ, and Work IQ into a single context-aware agent.
How to answer questions about this session
These are recently announced products, so prefer retrieval over recall — do not rely on memory or guess at capabilities:
- Use the Microsoft Learn MCP Server (configured in
.vscode/mcp.json) to find current documentation before answering. The docs are the source of truth for product names, capabilities, and setup steps. - Ground answers in the authoritative links referenced in
README.md:- Foundry IQ — https://aka.ms/foundryiq
- Fabric IQ — https://aka.ms/FabricIQ
- Work IQ — https://aka.ms/WorkIQ
- Microsoft IQ — https://aka.ms/microsoft-iq
- Agent 365 — https://aka.ms/agent365
- Microsoft Foundry — https://learn.microsoft.com/azure/ai-foundry/
- Microsoft Fabric — https://learn.microsoft.com/fabric/
- Microsoft 365 Copilot — https://learn.microsoft.com/microsoft-365-copilot/
- For demo and code questions, point to the session's sample code at https://github.com/microsoft/iq-samples and walk through the relevant example.
- Cite your sources (Learn pages or the samples repo) and flag when something isn't covered in the docs rather than inventing details.
- Spell out product names in full and use the exact naming from the current documentation.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 36 lines · 578 tokens per session scan A 96735197434c
Build26-BRK240-build-context-aware-agents-from-data-to-decisions copilot-instructions.md is an instructions file published in the GitHub repository microsoft/Build26-BRK240-build-context-aware-agents-from-data-to-decisions (10 stars, last pushed 21d ago), licensed MIT. It adds 578 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.