· 13 min
Round-Tripping an Agent Plugin with WIQD
Import an issue-triage Agent Plugin into WIQD, adapt it for Microsoft 365 Copilot, export it again, and measure what actually stays portable.
TAG
extensibility
16 items tagged with "extensibility"
· 9 min
Build Smarter Declarative Agents with Skills and WIQD
Build custom skills for declarative agents with WIQD, load focused expertise on demand, and give users more reliable, repeatable outcomes at work.
· 15 min
Generating Evals with WIQD: Setting a Quality Bar That Holds
Generate an eval suite from your agent manifest with WIQD, review it like a specification, diagnose failures, and set a quality bar you can defend.
· 17 min
Validating an Inherited Declarative Agent with WIQD
A manifest can be valid JSON and describe a dead agent. Use WIQD static and deep validation to triage, repair, and gate an inherited declarative agent.
· 9 min
The Declarative Agent Lifecycle, End to End with WIQD
Build, Improve, Preview, Publish. WIQD runs the whole declarative agent lifecycle as one conversation, from scaffolding through evals to store submission.
· 8 min
Building Reusable Plugins with WIQD: Skills and Connectors
WIQD makes plugins a first-class deliverable. Compose skills, MCP agent connectors, and declarative agents into one packageable, validatable unit.
· 9 min
Work IQ Developer Tools for Copilot Plugins and Agents
WIQD turns plugin work into a conversation: describe the MCP capability you want, and the tooling handles discovery, validation, provisioning, and evals.
· 6 min
Meeting Actions: Let Declarative Agents Run the Calendar
The MeetingActions capability in manifest v1.8 lets declarative agents schedule events, create time-finding polls, and surface calendar time insights.
· 6 min
Email Actions: Let Declarative Agents Manage the Inbox
The EmailActions capability in manifest v1.8 gives declarative agents write access to email: triage, supervised send, inbox rules, and folder management.
· 8 min
Conditional Conversation Starters for Declarative Agents
Manifest schema v1.7 adds depends_on to conversation starters, so prompts only show up when the capabilities they need are configured.
· 7 min
Editorial Answers Make Declarative Agents Predictable
Editorial answers in declarative agent manifest v1.7 let you reserve exact responses for known questions, with semantic matching catching natural language variations.
· 10 min
Agents Without Evals Are Just Vibes: Agents Evaluations CLI
The Agents Evaluations CLI turns declarative agent quality into repeatable tests, scored reports, and PR evidence using @microsoft/m365-copilot-eval.
· 6 min
Set a Default Response Mode for Your Declarative Agent
Use the new default_response_mode manifest property to control whether your declarative agent starts in Auto, Quick response, or Think deeper mode.
· 8 min
Localizing Declarative Agents: Multi-Language Agents That Actually Work
Build declarative agents that work across languages with tokenized manifests, localizationInfo, and culturally adapted instructions.
· 7 min
What Are Declarative Agents for Microsoft 365 Copilot?
Understand what declarative agents are, how they work, and when to use them: the foundational guide to building AI agents for Microsoft 365 Copilot.
· 4 min
Welcome to The Manifest: Why Declarative Agents Matter
Introducing The Manifest, a blog dedicated to Microsoft 365 Copilot extensibility, declarative agents, and the hidden gem of the M365 platform.