Microsoft PromptFlow
by Microsoft
Build, evaluate, and deploy LLM applications as visual DAG flows — chain prompts, Python, and tools, then run batch evaluations with built-in quality and safety metrics.
Skills
Flow Execution
Runs prompt and Python nodes as a directed graph with per-node tracing, so each intermediate output is inspectable.
Batch Evaluation
Executes a flow across a dataset and scores results with groundedness, relevance, and safety evaluators.
Deployment Packaging
Packages a flow as a Docker image or Azure managed endpoint with its dependencies and connection config.
Related Agents
SandBase Harness
Runs local-first, self-hosted AI agents with persistent sessions, sandboxed tools, memory, credentials, audit trails, r…
CrewAI
Multi-agent orchestration framework for building teams of AI agents that collaborate, delegate, and solve complex tasks…
DeepSeek Harness
Runs coding agents on a plugin-composed harness where models, tools, skills, sessions, sandboxes, storage, and the UI a…
Archon
Runs coding agents through YAML-defined workflows (plan, implement, validate, review, open a PR), each in its own git w…