Koog 1.0 idioms, gotchas, and scaffolding skills for Kotlin agents on the JVM
86
88%
Does it follow best practices?
Impact
86%
1.86xAverage score across 45 eval scenarios
Advisory
Suggest reviewing before use
{
"context": "Tests whether the agent uses the koog-ktor plugin (the supported integration path) inside the developer's existing Application.module(), rather than hand-rolling a parallel Ktor server or constructing the agent inside the route handler on every request.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Installs the Koog Ktor plugin",
"description": "Calls install(Koog) { ... } inside Application.module(). Does NOT construct the AIAgent inside the route handler (which would rebuild it on every request) and does NOT start a separate Ktor server instance",
"max_score": 30
},
{
"name": "Adds the koog-ktor dependency",
"description": "Adds ai.koog:koog-ktor at 1.0.0 or later to build.gradle.kts. The umbrella does not include the Ktor integration",
"max_score": 20
},
{
"name": "Configures the prompt executor inside the install block",
"description": "Wires simpleOpenAIExecutor (reading the API key from env) inside the install(Koog) configuration block. Does not construct executors inside the route handler",
"max_score": 15
},
{
"name": "Reads the OpenAI API key from the environment",
"description": "Reads the API key via System.getenv(\"OPENAI_API_KEY\"). Does not embed the key literal in source",
"max_score": 10
},
{
"name": "Adds a POST /agent route",
"description": "Inside routing { ... }, declares a post(\"/agent\") { ... } handler that reads the request body and writes the agent result back. Receives input as call.receiveText() (or equivalent) and responds with call.respondText (or equivalent)",
"max_score": 15
},
{
"name": "Resolves the agent from the plugin attribute",
"description": "Reads the configured agent inside the route handler via the plugin attribute key (call.attributes[Koog.key] or equivalent supported accessor) rather than referencing a top-level lateinit or rebuilding the agent inline",
"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