{"license":"CC BY 4.0","attribution":"AI Dispatch — https://aidispatch.news","methodology":"https://aidispatch.news/methodology","generated_at":"2026-10-06T15:51:26.019Z","entity":{"name":"HarnessRouter","slug":"harnessrouter","type":"agent","subtype":"ai agents platform","developer":null,"homepage_url":"https://harnessrouter.ai","summary":"HarnessRouter sells embedded infrastructure for running third-party agent harnesses - Codex, Claude Code, Hermes and others - in isolated per-task sandboxes behind a single API, so a customer product can send a task and get back finished work such as videos, games, codebases or documents. The harness and model are named in config and swappable with a one-line change, and requests go to whichever model provider and credentials the customer configures. It is offered both as a managed Cloud service and as a self-hosted Apache 2.0 Community Edition in which runtime and application state stay in the customer environment. Agent work is metered from $0.014 per active work minute with waiting for model responses unbilled, and plans start at $20 per month applied as usage. The company publishes Y Combinator backing and names Stanford Medicine as a launch partner. On the assurance questions this index scores, the published record is thin. Every session runs in its own isolated sandbox, which bounds blast radius, but no scope, spend or authority limit on the agent itself is published. The only record of agent activity is an execution trace streamed to the calling application, with no stated retention period and no tamper-evidence. No certification, carrier, cover limit or customer indemnity is named anywhere in the capture. Currency note - this page was substantially rewritten between the 2026-09-04 and 2026-09-11 captures, which added the Apache 2.0 Community Edition and dropped the per-minute rate. Eight fields, the two pricing fields among them, still cite the earlier capture and are marked as dated where the newer capture no longer carries the wording. Re-extraction against the newest capture is pending with the Researcher.","description":"HarnessRouter sells embedded infrastructure for running third-party agent harnesses - Codex, Claude Code, Hermes and others - in isolated per-task sandboxes behind a single API, so a customer product can send a task and get back finished work such as videos, games, codebases or documents. The harness and model are named in config and swappable with a one-line change, and requests go to whichever model provider and credentials the customer configures. It is offered both as a managed Cloud service and as a self-hosted Apache 2.0 Community Edition in which runtime and application state stay in the customer environment. Agent work is metered from $0.014 per active work minute with waiting for model responses unbilled, and plans start at $20 per month applied as usage. The company publishes Y Combinator backing and names Stanford Medicine as a launch partner. On the assurance questions this index scores, the published record is thin. Every session runs in its own isolated sandbox, which bounds blast radius, but no scope, spend or authority limit on the agent itself is published. The only record of agent activity is an execution trace streamed to the calling application, with no stated retention period and no tamper-evidence. No certification, carrier, cover limit or customer indemnity is named anywhere in the capture. Currency note - this page was substantially rewritten between the 2026-09-04 and 2026-09-11 captures, which added the Apache 2.0 Community Edition and dropped the per-minute rate. Eight fields, the two pricing fields among them, still cite the earlier capture and are marked as dated where the newer capture no longer carries the wording. Re-extraction against the newest capture is pending with the Researcher.","description_source":"summary","url":"https://aidispatch.news/agents/harnessrouter/","published_at":"2026-10-06T08:41:12.311162+00:00","updated_at":"2026-10-06T11:32:09.963023+00:00"},"fields":[{"key":"environment","label":"Operating environment","category":"agency","status":"present","value":"Runs third-party coding/agent harnesses in isolated sandboxes as embedded backend infrastructure inside a customer product","not_yet_interpreted":false,"quote":"Run Codex, Claude Code, Hermes, and more in isolated sandboxes as your product backend.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-04T12:06:16.822572+00:00","review":null,"superseded_quote":{"state":"not_in_latest_capture","confidence":"high","latest_capture_at":"2026-10-06T12:09:17.546888+00:00","detected_at":"2026-10-06T14:05:00.022606+00:00"}},{"key":"runtime_governance","label":"Runtime governance","category":"assurance","status":"present","value":"Enforces a separate isolated sandbox per agent session/run","not_yet_interpreted":false,"quote":"Every session runs in its own isolated sandbox.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-04T12:06:16.822572+00:00","review":null,"superseded_quote":{"state":"not_in_latest_capture","confidence":"high","latest_capture_at":"2026-10-06T12:09:17.546888+00:00","detected_at":"2026-10-06T14:05:00.022606+00:00"}},{"key":"model_swappable","label":"Model swappable","category":"models","status":"present","value":"Harness/model is configurable and swappable via a one-line config change without altering integration code","not_yet_interpreted":false,"quote":"Your config names the harness: claude-code today, codex tomorrow, or back again, swapped anytime with one line.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-04T12:06:16.822572+00:00","review":null,"superseded_quote":{"state":"not_in_latest_capture","confidence":"high","latest_capture_at":"2026-10-06T12:09:17.546888+00:00","detected_at":"2026-10-06T14:05:00.022606+00:00"}},{"key":"integrations","label":"Integrations","category":"practicality","status":"present","value":"Harnesses can take real tool actions against GitHub, Slack, Notion, and internal APIs","not_yet_interpreted":false,"quote":"confirmations of real tool actions like GitHub, Slack, Notion, or internal APIs.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-04T12:06:16.822572+00:00","review":null,"superseded_quote":{"state":"not_in_latest_capture","confidence":"high","latest_capture_at":"2026-10-06T12:09:17.546888+00:00","detected_at":"2026-10-06T14:05:00.022606+00:00"}},{"key":"user_base","label":"User base","category":"impact","status":"present","value":"Named launch partner: Stanford Medicine","not_yet_interpreted":false,"quote":"Launch Partner: Used by Stanford Medicine","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-04T12:06:16.822572+00:00","review":null,"superseded_quote":{"state":"not_in_latest_capture","confidence":"high","latest_capture_at":"2026-10-06T12:09:17.546888+00:00","detected_at":"2026-10-06T14:05:00.022606+00:00"}},{"key":"action_space","label":"Action space","category":"agency","status":"present","value":"A single API call returns completed artifacts: videos, games, codebases and docs","not_yet_interpreted":false,"quote":"Your app sends a task through one API and gets back finished work: videos, games, codebases, docs, and more.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-04T12:06:16.822572+00:00","review":null,"superseded_quote":{"state":"not_in_latest_capture","confidence":"high","latest_capture_at":"2026-10-06T12:09:17.546888+00:00","detected_at":"2026-10-06T14:05:00.022606+00:00"}},{"key":"price_point","label":"Price point","category":"practicality","status":"present","value":"Plans start from $20 per month applied as usage credit, as worded in the 2026-09-04 capture. The 2026-09-11 capture still carries a $20 figure but not this sentence, so the wording is dated.","not_yet_interpreted":false,"quote":"Plans from $20/month include their full price as usage.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-04T12:06:16.822572+00:00","review":null,"superseded_quote":{"state":"not_in_latest_capture","confidence":"high","latest_capture_at":"2026-10-06T12:09:17.546888+00:00","detected_at":"2026-10-06T14:05:00.022606+00:00"}},{"key":"pricing_model","label":"Pricing model","category":"practicality","status":"present","value":"Metered by active agent work minute from $0.014, with idle wait for model responses unbilled, as stated in the 2026-09-04 capture. The newest capture of this page, 2026-09-11, no longer contains the figure 0.014, so treat the rate as dated rather than current.","not_yet_interpreted":false,"quote":"Agent work from $0.014 per active work minute, and agent memory. Waiting for model responses is free.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-04T12:06:16.822572+00:00","review":null,"superseded_quote":{"state":"not_in_latest_capture","confidence":"high","latest_capture_at":"2026-10-06T12:09:17.546888+00:00","detected_at":"2026-10-06T14:05:00.022606+00:00"}},{"key":"autonomy_level","label":"Autonomy level","category":"agency","status":"present","value":"Platform autonomously provisions and manages a sandboxed execution environment for each task without manual infrastructure operation.","not_yet_interpreted":false,"quote":"HarnessRouter provisions and operates one isolated sandbox for every task, so workloads scale without infrastructure work.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"human_oversight","label":"Human oversight","category":"agency","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"goal_complexity","label":"Goal complexity","category":"agency","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"initiative","label":"Initiative","category":"agency","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":{"state":"flagged","confidence":"medium","reviewed_at":null,"detected_at":"2026-09-14T08:05:00.028778+00:00"},"superseded_quote":null},{"key":"deployment_scale","label":"Deployment scale","category":"impact","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"high_risk_domains","label":"High-risk domains","category":"impact","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"documented_incidents","label":"Documented incidents","category":"impact","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"market_recognition","label":"Market recognition","category":"impact","status":"present","value":"Company publicly discloses Y Combinator backing as a signal of investor validation.","not_yet_interpreted":false,"quote":"Backed by Y Combinator","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"deployment_options","label":"Deployment options","category":"practicality","status":"present","value":"Offered both as a managed hosted Cloud service and as a self-hosted open-source Community Edition.","not_yet_interpreted":false,"quote":"Use the managed Cloud or run it yourself.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"supported_regions","label":"Supported regions","category":"practicality","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"support_model","label":"Support model","category":"practicality","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"model_provider","label":"Model provider","category":"models","status":"present","value":"Model provider is chosen by the customer; requests are routed directly to whichever provider and credentials they configure.","not_yet_interpreted":false,"quote":"Requests to the model provider still follow the provider and credentials you choose.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"open_weights","label":"Open weights","category":"models","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"fine_tuning","label":"Fine-tuning","category":"models","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"context_window","label":"Context window","category":"models","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"protocols_supported","label":"Protocols supported","category":"ecosystem","status":"present","value":"The company's Unified Harness Protocol standard explicitly covers configuring MCP servers as part of a harness, indicating Model Context Protocol support.","not_yet_interpreted":false,"quote":"It defines how a harness is discovered, selected, and configured, including its model, skills, tools, and MCP servers, and how tasks, sessions, streaming events, files, artifacts, cancellation, errors, and results flow between the two.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"target_sectors","label":"Target sectors","category":"impact","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"base_models","label":"Base models","category":"models","status":"present","value":"The router lists multiple harness-and-model combinations, including gpt-5.4 and gpt-5.4-mini variants and claude-opus-4.7.","not_yet_interpreted":false,"quote":"Codex gpt-5.4-mini Claude Code claude-opus-4.7 Hermes gpt-5.4-mini Pi gpt-5.4-mini Oh My Pi gpt-5.4-mini DeepSeek Harness gpt-5.4-mini Qwen Code gpt-5.4","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"availability","label":"Availability","category":"practicality","status":"present","value":"Self-serve signup starts at $0 and requires no payment card. The capture names no release stage, so no general-availability claim is made.","not_yet_interpreted":false,"quote":"Start at $0, no card needed.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"tool_use","label":"Tool use","category":"ecosystem","status":"present","value":"A harness (the router's core abstraction) equips the underlying model with sandboxed tools and an execution loop so it produces finished work, not just text.","not_yet_interpreted":false,"quote":"A harness gives it a sandbox, tools, and a loop, so it returns actual work.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"multi_agent","label":"Multi-agent","category":"ecosystem","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":{"state":"flagged","confidence":"high","reviewed_at":null,"detected_at":"2026-09-14T08:05:00.028778+00:00"},"superseded_quote":null},{"key":"api_access","label":"API access","category":"ecosystem","status":"present","value":"The product is integrated and controlled through a single unified API.","not_yet_interpreted":false,"quote":"One API. One console. Every agent harness.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"open_source","label":"Open source","category":"ecosystem","status":"present","value":"The self-hosted Community Edition is released under the Apache 2.0 open-source license.","not_yet_interpreted":false,"quote":"Community Edition is Apache 2.0 and runs on infrastructure you control with your own keys, state, and files.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"marketplace_presence","label":"Marketplace presence","category":"ecosystem","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"safety_evaluations","label":"Safety evaluations","category":"safety","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"red_teaming","label":"Red teaming","category":"safety","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"safety_policy","label":"Safety policy","category":"safety","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"usage_restrictions","label":"Usage restrictions","category":"safety","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"model_card","label":"Model or system card","category":"safety","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"incident_reporting","label":"Incident reporting","category":"safety","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"third_party_evals","label":"Third-party evaluations","category":"safety","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"data_handling","label":"Data handling","category":"safety","status":"present","value":"In the self-hosted Community Edition, all runtime and application state remains within the customer's own environment rather than the vendor's.","not_yet_interpreted":false,"quote":"With Community Edition, the runtime and application state stay in your environment.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"insurance_available","label":"Insurance available","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"own_liability_cover","label":"Own liability cover","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"insurance_carriers","label":"Insurance carriers","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"coverage_limits","label":"Coverage limits","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"indemnification","label":"Indemnification","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"liability_cap","label":"Liability cap","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"audit_trail","label":"Audit trail","category":"assurance","status":"present","value":"Each task execution produces a trace with progress, status, artifacts and errors that the integrating application can retrieve.","not_yet_interpreted":false,"quote":"Your application can receive streamed progress and events, task status, generated files and artifacts, the final result, errors, and execution trace.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"audit_trail_immutable","label":"Tamper-evident log","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"explainability","label":"Explainability","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"permission_scopes","label":"Permission scopes","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"compliance_certs","label":"Compliance certifications","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"regulatory_alignment","label":"Regulatory alignment","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"outcome_based_pricing","label":"Outcome-based pricing","category":"assurance","status":"present","value":"Pricing is metered by active agent work time rather than tied to task outcomes or success; idle/waiting time is not billed.","not_yet_interpreted":false,"quote":"You pay for Agent work only; waiting is free.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"settlement_mechanism","label":"Settlement mechanism","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"asset_custody","label":"Asset custody","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"dispute_process","label":"Dispute process","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"sla_terms","label":"SLA terms","category":"assurance","status":"no_public_information","value":null,"not_yet_interpreted":false,"quote":null,"source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"eval_coverage","label":"Evaluation coverage","category":"assurance","status":"present","value":"Platform includes a built-in benchmarking/arena tool that lets customers compare harness-and-model configurations on their own tasks before choosing one for production.","not_yet_interpreted":false,"quote":"Benchmark harness × model combinations on your task, then choose the configuration you route to, all through one integration.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null},{"key":"self_reported_performance","label":"Self-reported performance","category":"assurance","status":"present","value":"Vendor claims its harness/model routing approach can reduce enterprise agent usage costs by 90% or more versus a less optimized configuration.","not_yet_interpreted":false,"quote":"Cut enterprise agent usage costs by 90% or more.","source_url":"https://harnessrouter.ai","retrieved_at":"2026-09-11T13:05:41.923254+00:00","review":null,"superseded_quote":null}],"trust_gap_scores":[{"dimension":"runtime_governance","score":1,"rationale":"The vendor states every session runs in its own isolated sandbox. That is run-time execution isolation, which bounds blast radius, but no scope, spend or authority limit on the agent itself is published.","rubric_version":"v1","scored_by":"fact-checker","judged":true,"scored_at":"2026-09-07T08:30:42.406313+00:00","superseded_scores":[{"score":1,"rationale":"Scored from 1 evidenced field(s): runtime_governance. Automated score; capped at 2 pending review.","rubric_version":"v1-auto","scored_by":"spark-verifier","judged":false,"scored_at":"2026-09-07T08:00:00.157055+00:00"}],"rests_on_flagged_absence":null,"evidence_newer_than_judgement":{"fields":["Permission scopes"],"newest_capture_at":"2026-09-11T13:05:41.923254+00:00"}},{"dimension":"audit_trail","score":1,"rationale":"The vendor states the integrating application can receive task status, generated artifacts, errors and an execution trace for each task, which is a retrievable record of agent activity. The judged score of 0 recorded on 2026-09-07 read no record at all, which was correct for the 2026-09-04 capture it cited but went stale when the 2026-09-11 capture added this text. It scores 1 rather than higher because the trace is delivered to the caller as a product feature with no stated retention period, no tamper-evidence and no hash-chaining, and the word audit does not appear anywhere in the capture.","rubric_version":"v1","scored_by":"fact-checker","judged":true,"scored_at":"2026-10-06T08:38:14.2621+00:00","superseded_scores":[{"score":1,"rationale":"Scored from 1 evidenced field(s): audit_trail. Automated score; capped at 2 pending review.","rubric_version":"v1-auto","scored_by":"spark-verifier","judged":false,"scored_at":"2026-09-14T08:00:00.123456+00:00"}],"rests_on_flagged_absence":null,"evidence_newer_than_judgement":null},{"dimension":"compliance","score":0,"rationale":"No public evidence found: no certification or regulatory framework is named, a notable absence for infrastructure named as used by Stanford Medicine.","rubric_version":"v1","scored_by":"fact-checker","judged":true,"scored_at":"2026-09-07T08:30:42.406313+00:00","superseded_scores":null,"rests_on_flagged_absence":null,"evidence_newer_than_judgement":{"fields":["Compliance certifications","Regulatory alignment"],"newest_capture_at":"2026-09-11T13:05:41.923254+00:00"}},{"dimension":"outcome_settlement","score":1,"rationale":"The vendor bills agent work per active work minute and states waiting for model responses is free. Billing is metered to work actually performed rather than wall-clock or seats, but payment is not conditioned on a verified outcome.","rubric_version":"v1","scored_by":"fact-checker","judged":true,"scored_at":"2026-09-07T08:30:42.406313+00:00","superseded_scores":[{"score":1,"rationale":"Scored from 1 evidenced field(s): outcome_based_pricing. Automated score; capped at 2 pending review.","rubric_version":"v1-auto","scored_by":"spark-verifier","judged":false,"scored_at":"2026-09-14T08:00:00.123456+00:00"}],"rests_on_flagged_absence":null,"evidence_newer_than_judgement":{"fields":["Outcome-based pricing","Settlement mechanism"],"newest_capture_at":"2026-09-11T13:05:41.923254+00:00"}},{"dimension":"insurance_indemnity","score":0,"rationale":"No public evidence found: no carrier, cover, limit or customer indemnity is published.","rubric_version":"v1","scored_by":"fact-checker","judged":true,"scored_at":"2026-09-07T08:30:42.406313+00:00","superseded_scores":null,"rests_on_flagged_absence":null,"evidence_newer_than_judgement":{"fields":["Insurance available","Insurance carriers","Coverage limits","Indemnification"],"newest_capture_at":"2026-09-11T13:05:41.923254+00:00"}}]}