microsoft/hve-core

Public

mirrored fromhttps://github.com/microsoft/hve-coreAvailable

CodeCommitsIssuesPull requestsActionsInsightsSecurity
dabed001c8ac7da3f2e4368ae1f279080c627cbd

Branches

Tags

  • No tags available.
0Branches0Tags
Go to file
Add file
Code

Clone

HTTPS

Download ZIP

docs/agents/README.md

81lines · modecode

1---
2title: Agent Systems Catalog
3description: Overview of all hve-core agent systems with workflow documentation and quick links
4author: Microsoft
5ms.date: 2026-02-12
6ms.topic: overview
7keywords:
8 - github copilot
9 - agents
10 - agent catalog
11estimated_reading_time: 5
12---
13
14hve-core organizes specialized agents into functional groups. Each group combines agents, prompts, and instruction files into cohesive workflows for specific engineering tasks.
15
16| Group | Agents | Complexity | Documentation |
17|-------------------------------------|----------|-------------|---------------------------------------------|
18| RPI Orchestration | 5 | High | [RPI Documentation](../rpi/README.md) |
19| GitHub Backlog Management | 1 active | Very High | [Backlog Manager](github-backlog/README.md) |
20| ADO Integration | 1 | Medium-High | Planned |
21| Document Builders | 4 | Medium-High | Planned |
22| Data Pipeline | 4 | Medium | Planned |
23| DevOps Quality | 2 | High | Planned |
24| Meta/Engineering | 1 | High | Planned |
25| Infrastructure | 1 | Very High | Planned |
26| Utility | 1 | Low-Medium | Planned |
27| [Design Thinking](#design-thinking) | 2 | High | Active |
28
29## RPI Orchestration
30
31The Research, Plan, Implement methodology separates complex tasks into specialized phases. Five agents (task-researcher, task-planner, task-implementor, task-reviewer, and the RPI orchestrator) coordinate through planning files to deliver structured engineering workflows. See the [RPI Documentation](../rpi/README.md) for the full guide.
32
33## GitHub Backlog Management
34
35Automates issue discovery, triage, sprint planning, and execution across GitHub repositories. The backlog manager agent orchestrates five distinct workflows with three-tier autonomy control. See the [Backlog Manager Documentation](github-backlog/README.md) for workflow guides.
36
37## ADO Integration
38
39Bridges Azure DevOps work items with local Copilot workflows. The ADO integration agent handles work item discovery, planning file creation, pull request generation, and build status monitoring.
40
41## Document Builders
42
43Four specialized agents for creating structured documents. Includes builders for Architecture Decision Records, Business Requirements Documents, Product Requirements Documents, and security plans.
44
45## Data Pipeline
46
47Processes and transforms data across formats and systems. Four agents handle data extraction, transformation, validation, and loading workflows.
48
49## DevOps Quality
50
51Two agents focused on code quality and deployment reliability. Covers PR review automation and build pipeline analysis.
52
53## Meta/Engineering
54
55The prompt builder agent creates and validates prompt engineering artifacts. Supports interactive authoring with sandbox testing for prompts, instructions, agents, and skills.
56
57## Infrastructure
58
59Manages cloud infrastructure provisioning and configuration. Handles Bicep and Terraform deployments with validation and drift detection.
60
61## Utility
62
63General-purpose agents for common development tasks such as file organization, content transformation, and small automation helpers.
64
65## Design Thinking
66
67The Design Thinking agents provide AI-assisted coaching through a nine-method, three-space framework for human-centered design.
68
69| Agent | Purpose |
70|---------------------|--------------------------------------------------------------|
71| `dt-coach` | Coaches teams through all 9 DT methods with session tracking |
72| `dt-learning-tutor` | Teaches DT curriculum with exercises and assessments |
73
74> Brought to you by microsoft/hve-core
75
76---
77
78<!-- markdownlint-disable MD036 -->
79*🤖 Crafted with precision by ✨Copilot following brilliant human instruction,
80then carefully refined by our team of discerning human reviewers.*
81<!-- markdownlint-enable MD036 -->
82