wehub-resource-sync
db620d33df
3.4 KiB
Harness Agent Samples
Samples demonstrating the Harness AIContextProviders — reusable providers that add planning, task management, and mode tracking to any ChatClientAgent.
Samples
| Sample | Description |
|---|---|
| Harness_Step01_Research | Using a ChatClientAgent with TodoProvider and AgentModeProvider for research, showcasing planning mode and todo management |
| Harness_Step02_Research_WithBackgroundAgents | Using BackgroundAgentsProvider to delegate stock price lookups to a web-search background agent concurrently |
| Harness_Step03_DataProcessing | Using FileAccessProvider to give an agent access to CSV data files for reading, analysis, and output generation |
| Harness_Step05_Loop | Wrapping a HarnessAgent with the LoopAgent decorator to re-invoke it until a configured LoopEvaluator (completion marker, predicate, AI judge, or approval-aware loop) decides to stop |
Build your own claw blog series
Samples accompanying the Build your own agent harness or claw with Microsoft Agent Framework blog series, which builds a personal finance assistant step by step.
| Sample | Description |
|---|---|
| Claw_Step01_MeetYourClaw | Post 1 — a minimal HarnessAgent with a custom get_stock_price tool, web search, and planning |
| Claw_Step02_WorkingWithData | Post 2 — file access, approvals, and durable memory (file memory plus optional Foundry memory) |
| Claw_Step03_ScalingCapabilities | Post 3 — scaling the claw with skills (plus optional Foundry skills), a confined shell, CodeAct, and background agents |
Security Considerations
Several harness providers extend the agent's trust boundary to external systems the developer configures — see the security notes in the individual sample READMEs (and the XML docs on the corresponding types) before enabling them in production:
BackgroundAgentsProvider— delegates work to developer-supplied agents (see Harness_Step02_Research_WithBackgroundAgents).AIJudgeLoopEvaluator(used byLoopAgent) — sends conversation content to a second, external judge chat client (see Harness_Step05_Loop).AgentSkillsProviderwith external skill sources (e.g.UseMcpSkills) — loads skill content, and potentially scripts, from a remote source (see AgentSkills samples).SummarizationCompactionStrategy— used for in-loop context compaction viaHarnessAgentOptions.CompactionStrategy, calls out to an LLM whose output becomes permanent chat history (see Agent_Step18_CompactionPipeline).
In every case, the capability is opt-in and requires explicit configuration by the developer, who is responsible for vetting the external service, agent, skill source, or provider before enabling it.