Koog 1.0 idioms, gotchas, and scaffolding skills for Kotlin agents on the JVM
88
88%
Does it follow best practices?
Impact
88%
1.95xAverage score across 43 eval scenarios
Passed
No known issues
{
"context": "Tests whether the agent reaches for the FunctionalAIAgent factory (right shape for a one-shot text transformation with no topology) rather than the default GraphAIAgent or a custom strategy<...>, which would be over-engineering for the developer's explicitly minimal need.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Uses the functional-agent factory",
"description": "Constructs via AIAgent.functional(...) (or equivalent functional factory) with an AIAgentFunctionalStrategy. Does NOT use the default AIAgent(...) graph factory and does NOT author a strategy<String, String>(\"...\") block — both would be over-engineering for the developer's stated minimal need",
"max_score": 35
},
{
"name": "Strategy block is a single suspending block",
"description": "The functional strategy body is a single suspending lambda that calls the LLM and returns the result. Does not contain a sub-graph, does not split work across multiple nodes (there are no nodes in a functional agent)",
"max_score": 25
},
{
"name": "Trims the LLM response inside the block",
"description": "The strategy body calls .trim() (or equivalent whitespace-trimming) on the LLM response before returning. The developer asked for this explicitly",
"max_score": 15
},
{
"name": "Includes the system prompt for formal-English rewriting",
"description": "Passes a systemPrompt to the factory that instructs the LLM to rewrite into formal English. Does not leave systemPrompt blank or unrelated to the task",
"max_score": 10
},
{
"name": "Reads OPENAI_API_KEY from environment",
"description": "Reads the OpenAI key via System.getenv. Does not embed the key literal",
"max_score": 10
},
{
"name": "No tools registered",
"description": "Does not pass a toolRegistry to the factory — the developer said no tools. The functional shape has no use for tools when the strategy is one-shot text-in-text-out",
"max_score": 5
}
]
}evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
scenario-31
scenario-32
scenario-33
scenario-34
scenario-35
scenario-36
scenario-37
scenario-38
scenario-39
scenario-40
scenario-41
scenario-42
scenario-43
skills
add-observability
add-persistence
add-rag
add-structured-output
add-token-budgeting
add-tool
cache-llm-calls
define-prompt
domain-model-subtask-pipeline
references
enable-prompt-caching
handle-agent-events
manage-state
migrate-from-0-x
model-planner-subtasks
persist-chat-history
query-sql-from-agent
scaffold-agent
snapshot-and-restore
test-koog-agents
trace-agent-internals
use-attachments
use-functional-agent
use-llm-node-variants
use-planner
wire-a2a
wire-acp-server
wire-ktor-server
wire-mcp-server
wire-spring-boot