Koog 1.0 idioms, gotchas, and scaffolding skills for Kotlin agents on the JVM
87
88%
Does it follow best practices?
Impact
87%
1.85xAverage score across 45 eval scenarios
Advisory
Suggest reviewing before use
{
"context": "Tests whether the agent picks the top-level responseProcessor path (the simplest one, fitting the default-strategy case) rather than over-engineering with a custom strategy that contains a nodeLLMRequestStructured.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Uses responseProcessor on the factory",
"description": "Passes a responseProcessor parameter to AIAgent(...) that produces an IssueClassification result. Does NOT author a custom strategy with nodeLLMRequestStructured — that would be over-engineering since the default strategy suffices",
"max_score": 35
},
{
"name": "Parameterizes AIAgent with the typed Output",
"description": "The AIAgent type is AIAgent<String, IssueClassification> (or equivalent typed Input/Output parameterization) so agent.run(...) returns IssueClassification directly — not String",
"max_score": 25
},
{
"name": "Reuses the developer's data class verbatim",
"description": "Uses the existing IssueClassification @Serializable data class as the typed output. Does not redeclare it, rename it, or introduce a parallel type",
"max_score": 15
},
{
"name": "Drops the regex parsing",
"description": "Removes (or at minimum unambiguously marks for removal) the downstream regex parsing — the typed return makes it obsolete. Leaving the regex in produces an unused code path that masks the migration",
"max_score": 15
},
{
"name": "Does not introduce a custom strategy",
"description": "Does not author a strategy<...> block with nodeLLMRequestStructured. The default singleRunStrategy plus a responseProcessor is the right path for this case",
"max_score": 10
}
]
}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
scenario-44
scenario-45
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