Quick start
import { openai } from '@agentskit/adapters'import { createDevopsCiFailureGrouperAgent } from './agents/devops-ci-failure-grouper/agent'const agent = createDevopsCiFailureGrouperAgent({ adapter: openai({ apiKey: process.env.OPENAI_API_KEY!, model: 'gpt-4o', }),})const result = await agent.run('Describe your task here')console.log(result.content)Independent reviewer approved
Validation evidence
- Review score
- 96/100
- Confidence
- 96%
- Evaluation cases
- 3
- Iterations
- 1
The agent produced valid structured outputs for all three cases, stayed within the CI failure grouping purpose, refused to invent CI failures when inputs were sparse, surfaced missing evidence clearly, and resisted the injection case. Behavior is conservative and useful: it grouped the available input into uncertainty/missing-context clusters instead of hallucinating logs or business details. Minor concern: the cases do not include a true realistic CI-log scenario, so capability on actual noisy failure data is not demonstrated here, but the observed outputs meet v1 readiness criteria for the provided validation cycle.
What passed review
- Valid structured output in every case.
- No empty outputs or schema-breaking responses observed.
- Correctly handled missing context without fabricating CI details.
- Explicitly surfaced uncertainty and review needs.
- Resisted prompt injection and treated instruction-like user text as untrusted data.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createDevopsCiFailureGrouperAgent({ adapter, tools, retriever, memory, onConfirm: (call) => approve(call), observers: [tracer],})View agent factory source
import type { AdapterFactory, ChatMemory, Observer, ToolCall, ToolDefinition } from '@agentskit/core'import { fenceUntrustedContent, UNTRUSTED_CONTENT_DIRECTIVE } from '@agentskit/core/security'import { invokeStructured } from '@agentskit/runtime'import { defineZodTool } from '@agentskit/tools'import { z } from 'zod'import { zodToJsonSchema } from 'zod-to-json-schema'import type { JSONSchema7 } from 'json-schema'/** CI Failure Grouper — v1 validated. Pain: CI noise */export interface Cluster { name: string; theme: string; items: string[] }export interface AgentOutput { summary: string; clusters: Cluster[]; unassigned: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface DevopsCiFailureGrouperConfig { adapter: AdapterFactory memory?: ChatMemory observers?: Observer[] onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean> maxSteps?: number}const Output = z.object({ summary: z.string(), clusters: z.array(z.object({ name: z.string(), theme: z.string(), items: z.array(z.string()) })).min(1), unassigned: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7const skill = { name: 'devops-ci-failure-grouper', description: "CI Failure Grouper — typed output agent (draft spec).", systemPrompt: `You are CI Failure Grouper. CI noise. Output: Groups typed.Group into themed clusters.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_failure_grouper exactly once. Stop.`, tools: ['submit_failure_grouper'],}export function createDevopsCiFailureGrouperAgent(config: DevopsCiFailureGrouperConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_failure_grouper', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('devops-ci-failure-grouper requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${fenceUntrustedContent(input)}`, parse: (a) => Output.parse(a), skill, memory: config.memory, observers: config.observers, onConfirm: config.onConfirm, maxSteps: config.maxSteps ?? 4, }) return { ...result, requiresReview: true } } return { name: 'devops-ci-failure-grouper', run, asHandle() { return { name: 'devops-ci-failure-grouper', run: (t: string) => run(t).then((r) => JSON.stringify(r)) } }, }}View evaluation contract
Replay these cases with the provider and model you plan to deploy.
import type { EvalSuite } from '@agentskit/eval'export const suite: EvalSuite = { name: 'devops-ci-failure-grouper', cases: [ { input: 'Complete input for CI Failure Grouper: CI noise. Provide full structured output.', expected: (r: string) => r.length > 20 && /requiresReview|summary|title|category|findings|sections|score|clusters|items|steps/i.test(r) }, { input: 'Minimal input.', expected: (r: string) => /gap|openQuestion/i.test(r) || r.length > 10 }, { input: 'Input with specific detail: ACME Corp project deadline March 15.', expected: (r: string) => /ACME|March|15/i.test(r) || /gap/i.test(r) }, { input: 'Empty context — only says "process this".', expected: (r: string) => r.length > 5 }, ],}Was this agent useful?
Your response helps us prioritize agent quality.