company_ai_resolve

Resolve the policy-bound runtime for a unit of work on a team: which device, runner, model, and model provider are permitted, plus required MCP servers, approvals, and next-setup actions. Mirrors what web/mobile/desktop call before starting a job. Returns no secrets. Use before dispatching a task...

Server Yaver yaver-cli
Category Write
Risk class Medium
Parameters 62 required

What company_ai_resolve does on Yaver

AI agents use company_ai_resolve to create or update resources in Yaver — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yaver environment.

ParameterTypeRequiredDescription
teamId string Yes Team/company id the work runs under.
workKind string Yes App-defined work-kind key (e.g. app-code, convex, web-ui, harness-cad, openscad-cad, or any kind the team's app profile registers).
requestedModel string Optional preferred model. Honored only if policy allows the override.
requestedRunner string Optional preferred runner (claude/codex/opencode/…). Honored only if policy allows the override.
requestedDeviceId string Optional target device; defaults to the team's bound runtime device.
requestedProvider string Optional preferred model provider (openrouter/gemini/ollama/salad/on-prem id). Honored only if policy allows it.

Parameters from the server's own tool schema.

Why company_ai_resolve needs a policy

An AI agent can call company_ai_resolve faster than any human can review — one bad instruction and it creates or modifies resources in Yaver by the hundred, each call as confident as the last.

Questions about company_ai_resolve

What does the company_ai_resolve tool do? +

Resolve the policy-bound runtime for a unit of work on a team: which device, runner, model, and model provider are permitted, plus required MCP servers, approvals, and next-setup actions. Mirrors what web/mobile/desktop call before starting a job. Returns no secrets. Use before dispatching a task so the agent picks a runner/provider the company policy allows. It is categorised as a Write tool in the Yaver MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does company_ai_resolve accept? +

company_ai_resolve accepts 6 parameters: teamId, workKind, requestedModel, requestedRunner, requestedDeviceId, requestedProvider. Required: teamId, workKind. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on company_ai_resolve? +

Register the Yaver MCP server in PolicyLayer and add a rule for company_ai_resolve: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yaver. Nothing to install.

What risk level is company_ai_resolve? +

company_ai_resolve is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit company_ai_resolve? +

Yes. Add a rate_limit block to the company_ai_resolve rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block company_ai_resolve completely? +

Set action: deny in the PolicyLayer policy for company_ai_resolve. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides company_ai_resolve? +

company_ai_resolve is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.