{"audit":{"version":"1.3","generated_at":"2026-07-26T03:04:24.819847+00:00","generated_by":"Agenstry","report_url":"https://agenstry.com/agents/cerebras-inference.main-kill-isr.mintlify.me","methodology_url":"https://agenstry.com/methodology","verifier_jwks_url":"https://agenstry.com/.well-known/jwks.json","subject":{"domain":"cerebras-inference.main-kill-isr.mintlify.me","name":"Cerebras Inference","url":"https://cerebras-inference.main-kill-isr.mintlify.me/.well-known/agent-card.json"}},"identity":{"provider":{"organization":"Cerebras Inference","url":"https://inference-docs.cerebras.ai/"},"registry_verification":null,"signature":{"signed":false,"signature_valid":null}},"protocol":{"version":"0.3","supports_streaming":false,"supports_push_notifications":false},"operational":{"live_state":"unreachable","live_responds":null,"last_status_code":200,"last_elapsed_ms":525,"last_error":null},"track_record":{"first_seen":"2026-07-20T18:48:33.928427+00:00","last_checked":"2026-07-24T17:20:10.546506+00:00","last_seen_ok":"2026-07-24T17:20:10.546506+00:00","checks_total":5,"checks_ok":5,"uptime_pct":100.0,"archived":false,"archived_reason":null},"conformance":{"score":49,"grade":"D","summary":"D-grade: significant issues, auth-gated, partially broken, or stale.","criteria":[{"key":"valid_card","label":"Valid AgentCard","points":10,"max_points":10,"status":"pass","detail":"Schema-validated A2A AgentCard returned by the well-known endpoint."},{"key":"live_responds","label":"Live JSON-RPC","points":0,"max_points":25,"status":"fail","detail":"DNS dead or connection refused."},{"key":"protocol_version","label":"Protocol version","points":5,"max_points":10,"status":"partial","detail":"Declares pre-1.0 A2A 0.3 (Google preview). Upgrade to v1.x for full points."},{"key":"signature","label":"JWS signature","points":0,"max_points":10,"status":"info","detail":"Card is unsigned (most published agents are)."},{"key":"uptime","label":"Uptime track record","points":15,"max_points":15,"status":"pass","detail":"5/5 probes succeeded (100% uptime)."},{"key":"skills","label":"Skill declaration","points":10,"max_points":10,"status":"pass","detail":"Declares 10 skills with structured metadata."},{"key":"verified_identity","label":"Verified Identity","points":5,"max_points":10,"status":"partial","detail":"Provider declared: Cerebras Inference (https://inference-docs.cerebras.ai/). Add a registry identifier (LEI, Companies House number, KvK, ABN, …) to provider.legalEntity for full verified-business credit."},{"key":"freshness","label":"Freshness + modern flags","points":4,"max_points":5,"status":"pass","detail":"seen in upstream source within 1d"},{"key":"security","label":"Security declaration","points":0,"max_points":5,"status":"info","detail":"No securitySchemes declared (common for open agents, not penalised)."}]},"skills":[{"id":"metrics","name":"cerebras-metrics","description":"Set up Prometheus scraping and Grafana dashboards for Cerebras dedicated inference endpoints. Use when configuring observability for dedicated endpoints, building monitoring dashboards, or integrating with Prometheus/Grafana Cloud/Datadog.","tags":[],"examples":[],"inputModes":[],"outputModes":[],"url":"https://inference-docs.cerebras.ai/.well-known/agent-skills/metrics/skill.md"},{"id":"models","name":"cerebras-models","description":"Discover models available on Cerebras Inference and migrate workloads between them. Use when listing available models, checking rate limits per tier, or converting an existing workload to a different model.","tags":[],"examples":[],"inputModes":[],"outputModes":[],"url":"https://inference-docs.cerebras.ai/.well-known/agent-skills/models/skill.md"},{"id":"openai-compatibility","name":"cerebras-openai-compatibility","description":"Use the OpenAI SDK or OpenAI-compatible clients with Cerebras by swapping the base URL. Use when migrating from OpenAI, or using Cerebras with OpenAI-compatible tooling.","tags":[],"examples":[],"inputModes":[],"outputModes":[],"url":"https://inference-docs.cerebras.ai/.well-known/agent-skills/openai-compatibility/skill.md"},{"id":"output-control","name":"cerebras-output-control","description":"Control Cerebras Chat Completions output using stop sequences, frequency/presence penalties, temperature, and sampling parameters. Use when filtering phrases, tuning determinism, or adjusting response creativity.","tags":[],"examples":[],"inputModes":[],"outputModes":[],"url":"https://inference-docs.cerebras.ai/.well-known/agent-skills/output-control/skill.md"},{"id":"payload-optimization","name":"cerebras-payload-optimization","description":"Reduce TTFT on the Cerebras API by compressing request payloads with gzip or msgpack. Use when benchmarking compression strategies, measuring prompt size in tokens, or optimizing large chat payloads.","tags":[],"examples":[],"inputModes":[],"outputModes":[],"url":"https://inference-docs.cerebras.ai/.well-known/agent-skills/payload-optimization/skill.md"},{"id":"prompt-caching","name":"cerebras-prompt-caching","description":"Measure and optimize Cerebras automatic prompt caching. Use when benchmarking cache hit rate, understanding prompt_cache_key scoping, or analyzing TTFT reduction from warm caches.","tags":[],"examples":[],"inputModes":[],"outputModes":[],"url":"https://inference-docs.cerebras.ai/.well-known/agent-skills/prompt-caching/skill.md"},{"id":"rate-limits","name":"cerebras-rate-limits","description":"Use Cerebras rate limit response headers to maximize throughput and avoid 429 errors. Use when building clients that resume as soon as limits reset, or debugging unexpected rate limiting behavior.","tags":[],"examples":[],"inputModes":[],"outputModes":[],"url":"https://inference-docs.cerebras.ai/.well-known/agent-skills/rate-limits/skill.md"},{"id":"reasoning","name":"cerebras-reasoning","description":"Configure and benchmark reasoning on Cerebras models (gpt-oss-120b, zai-glm-4.7). Use when testing reasoning formats, measuring performance across effort levels, or debugging multi-turn reasoning retention.","tags":[],"examples":[],"inputModes":[],"outputModes":[],"url":"https://inference-docs.cerebras.ai/.well-known/agent-skills/reasoning/skill.md"},{"id":"structured-outputs","name":"cerebras-structured-outputs","description":"Enforce JSON schema compliance on Cerebras model responses using strict mode. Use when debugging schema validation errors, checking strict=true compatibility, or migrating from JSON mode to structured outputs.","tags":[],"examples":[],"inputModes":[],"outputModes":[],"url":"https://inference-docs.cerebras.ai/.well-known/agent-skills/structured-outputs/skill.md"},{"id":"tool-use","name":"cerebras-tool-use","description":"Implement tool calling with Cerebras models, including parallel tool calls and end-to-end latency measurement. Use when building agentic workflows, benchmarking parallel vs. sequential tool calls, or debugging tool call schemas.","tags":[],"examples":[],"inputModes":[],"outputModes":[],"url":"https://inference-docs.cerebras.ai/.well-known/agent-skills/tool-use/skill.md"}],"provenance":[{"source":"manifests","first_seen":"2026-07-20T18:48:33.928427+00:00"},{"source":"recrawl_hot","first_seen":"2026-07-22T15:37:44.364429+00:00"}],"recent_probes":[{"fetched_at":"2026-07-24T17:20:10.546506+00:00","ok":true,"status_code":200,"error":null,"elapsed_ms":525,"live_responds":null},{"fetched_at":"2026-07-22T22:59:29.130825+00:00","ok":true,"status_code":200,"error":null,"elapsed_ms":566,"live_responds":null},{"fetched_at":"2026-07-22T15:37:44.364429+00:00","ok":true,"status_code":200,"error":null,"elapsed_ms":585,"live_responds":null},{"fetched_at":"2026-07-21T17:31:10.444838+00:00","ok":true,"status_code":200,"error":null,"elapsed_ms":541,"live_responds":null},{"fetched_at":"2026-07-20T18:48:33.928427+00:00","ok":true,"status_code":200,"error":null,"elapsed_ms":559,"live_responds":null}],"catalog_attestation":null,"verification_history":[]}