# Using Workflows and Tools > Trigger a specific tool or workflow from a local agent, the workflow page, the dashboard, the mobile app, or the API. Content type: documentation Source URL: https://www.agentpmt.com/docs/getting-started/using-workflows-and-tools Markdown URL: https://www.agentpmt.com/docs/getting-started/using-workflows-and-tools?format=agent-md Category: Getting Started --- # Using Workflows and Tools Tools and workflows on AgentPMT are callable from several surfaces. Pick the one that fits how you are working. Workflows also support schedules, and every schedule chooses who performs the due run. --- ## Tell a local agent exactly what to use Local agents (Claude Code, Cursor, Codex, Zed, anything connected over MCP) decide which tool to call based on what you say. Most of the time you can be loose: *"summarize this article."* When you want predictability, name the workflow or tool. ### By workflow name > Use the **Daily Market Digest** workflow with topic `AI infrastructure`. The agent looks for a workflow named "Daily Market Digest" in its MCP tool list and runs it. ### By tool name > Use the **Web Search** tool to find "MCP specification". Force a specific tool when the agent keeps picking the wrong one. ### By tool family > Use a market data tool to get the AAPL price. Useful when several tools could handle the same job and you want the agent to stay within a specific tool family. If the agent says it cannot find the workflow or tool, the most common cause is that it is not attached to your Agent Group. Add it in **Control Center → Agent Groups**, then ask again — no reconnect required. --- ## Copy the prompt from the workflow page Every published workflow has a marketplace page with a one-click prompt copy. Use this when the agent is not reliably picking the workflow on its own, or when you want to paste into a chatbot that is not connected to AgentPMT. 1. **Open the workflow's marketplace page** From the marketplace, click any workflow. Its detail page opens. 2. **Click Use skill, then Copy prompt for LLM** The **Use skill** dropdown opens. Select **Copy prompt for LLM** ("Paste into your AI assistant"). The prompt copies to your clipboard with the workflow name, required inputs, and invocation instructions. 3. **Paste into your chatbot** Drop it into Claude, ChatGPT, Cursor, anywhere. Fill in the input fields the prompt asks for. Send. [Note title="Works even without an MCP connection"] The copied prompt is self-contained instructions for the chatbot. You do not need an MCP server up to use it — the prompt itself describes what to do. --- ## From the dashboard or the mobile app Hosted agents run tools and workflows on your behalf. To trigger a specific one: **Dashboard** — Open the agent in the Agent Builder, click **Open Chat** in the **Scoped chat preview** section, and type the workflow or tool name plainly: *"Run the Daily Market Digest workflow."* The agent calls it directly. **Mobile app** — Open the agent on your phone and type the same request. Activity logs the same way as on the dashboard; pending payment confirmations route to the device. The agent only runs tools and workflows that are attached to it (or to its Agent Group). If a request does not match anything attached, the agent says so rather than guessing. --- ## Schedule a workflow Use **Control Center -> Workflows -> Schedules** when a workflow should run on a calendar or interval. Schedules are attached to an Agent Group and can only target workflows that the group is allowed to access: workflows added explicitly, public published workflows covered by **Allow all workflows**, and private workflows covered by the group's private-workflow access settings. **BYO agent scheduler** — AgentPMT tracks due times and exposes them to external agents. OpenClaw, Hermes, Claude, or your own runtime can list due items, execute independently, and advance the schedule after handling the occurrence. Use this when your own agent runtime owns credentials, environment, approvals, or orchestration. **AgentPMT managed run** — AgentPMT's cron runner executes due workflow items through the gateway using the model assigned to the workflow. Use this when you want AgentPMT to perform the scheduled run for you. The owner must have at least 100 credits available or the occurrence is skipped and a low-credit notice is sent. Manual **Test Run** from the dashboard checks the stored schedule prompt without advancing the due time. It is separate from both scheduled execution paths. For the BYO path, use the external schedule due/advance API-key + budget-key endpoints from the API reference. Those endpoints coordinate timing only; they do not execute workflows inside AgentPMT. --- ## Via the API Programmatic invocation uses your Agent Group's **Bearer Token** in the standard `Authorization: Bearer ` header. Immediate workflow invocation and BYO schedule polling use different API auth surfaces; the full request shapes, streaming, polling long-running workflow executions, error codes, and response schemas live in the dedicated [API tutorial](/docs/api-reference/programmatic-access). Endpoints are not duplicated here so they cannot drift. --- ## When something does not run | Symptom | Most likely cause | |---|---| | Agent says the workflow does not exist | Workflow is not allowed on the Agent Group or agent. Add it under **Control Center -> Agent Groups** or use the group's allow-all workflow settings where appropriate. | | 401 from the API | Bearer Token is missing, expired, or copied with whitespace. Re-copy from **Show Bearer Token**. | | 402 from the API | Out of credits, or agent group spending cap reached. Top up or raise the cap. | | BYO scheduled item is due but no run appears | BYO schedules only list due work. Your external agent must poll, execute, then advance the schedule. | | Managed scheduled item is skipped | The workflow owner has fewer than 100 credits, the workflow is no longer in the Agent Group, or required credentials/setup are missing. | | Tool runs but errors out | Required credential not bound. Open the tool inside your Agent Group and connect the credential. | --- ## Where to next - [Using Agents](/docs/getting-started/using-agents) - Run agents on every surface AgentPMT exposes. - [API Reference](/docs/api-reference/programmatic-access) - Full programmatic invocation reference.