Examples
DSPy
Baseline prompt vs DSPy-optimized prompt, scored side-by-side against the AgentsKit eval pipeline.
Side-by-side scoring of a baseline ReAct prompt vs a DSPy-optimized variant, run through the 8 bundled scorers (4 quality + 4 robustness).
pnpm --filter @agentskit/example-dspy startOutput: a markdown table comparing both prompts across every scorer.
#What it shows
- Baseline ReAct prompt at
prompts/baseline.txt— short, cheap, day-one prompt. - DSPy-optimized variant produced via
BootstrapFewShot. - AgentsKit eval pipeline scoring both with the same harness.
#Related
Explore nearby
- PeerExamples
Interactive demos. For copy-paste code, see Recipes.
- PeerBasic Chat
The simplest use case — streaming AI conversation with auto-scroll, stop button, and keyboard handling. All in 10 lines with AgentsKit.
- PeerTool Use
AI assistants that call functions — weather, search, DB queries. Tool calls render as expandable cards.