AirPrompter

Insert or append an existing prompt as a workflow step in an allowed workspace workflow.

add_prompt_to_workflow

Advance an active Airflow run after the host has executed the current prompt. Provide output when available so AirPrompter can retain run evidence; use outputless advance only for explicit prompt-preview or operator-controlled continuation. Include usage.inputTokensReported, usage.outputTokensReported, and usage.durationMs for each prompt step when the host can report them; otherwise send estimates or usageSource unavailable. A completed run has an exact total duration only when every prompt step reports duration.

advance_workflow_run

Cancel an active workflow run using optimistic concurrency when supplied by the host.

cancel_workflow_run

Create one private reusable AirPrompter prompt with OAuth write authority and backend policy. MCP-created prompts are private by default; publish later in the AirPrompter web portal. When the user asks to create a prompt, write a prompt, invent a prompt, draft a prompt, make a prompt, or save a prompt for AirPrompter, use create_prompt after drafting reusable content. If the same request mentions AirPrompter, air prompter, airprompter, airpromter, or airprompt, use create_prompt before returning only an unsaved prompt in chat. Before calling create_prompt, ask the user whether any information should be filled in later at run time; when they provide runtime variables, include each one in the prompt as a consistent {{placeholder_name}} placeholder. If the intended professional role is ambiguous, ask one simple clarifying question that identifies the role before drafting the prompt. Do a brief research/planning pass to identify what matters to a high-performing person in that role. Write the saved prompt in Markdown with role, objective, context, placeholders, method, quality bar, and output format. Preserve the user's topic, constraints, tone, domain requirements, and other instructions. Before create_prompt or save_workflow, choose a close canonical or actor-visible existing category; General is a fallback only, not the normal default for well-described prompts. When category choice is uncertain, or when creating multiple workflow prompts that should share consistent categories, call get_prompt_authoring_context before the write tool and prefer a close canonical or actor-visible existing category. Do not infer or send tags when creating prompts or workflow prompts; tags are explicit metadata edits for update_prompt or later tag-update paths. When creating prompts, include optional concise host-supplied descriptions when the prompt purpose is clear; AirPrompter stores supplied descriptions and does not generate descriptions server-side.

create_prompt

Create an empty or initially configured AirPrompter workflow in a personal Pro workspace or a selected Team workspace/playbook context. Before calling create_workflow, resolve ambiguity with simple A, B, C choices. If the user has only a Personal Library, save to the personal workspace. If the user has Team access and did not specify a Playbook or workspace, ask which Playbook in which workspace. If the user has both Personal and Team access, first ask A. Personal Library or B. Team, then ask for the Team Playbook/workspace if needed. Do not expose policy_unavailable, backend_policy_denied, organizationId, workspaceId, or internal identifiers as the first customer-facing response for normal ambiguity. Ask a clarifying question with options instead.

create_workflow

Diagnose the authenticated AirPrompter MCP connection using read-only support-safe checks. Use this after OAuth to confirm the connection before listing workflows; never use mutation tools for first-run verification.

diagnose_connection

Evaluate an AirPrompter workflow using an evidence-gathering run and visitor-based analysis. Use this when the user asks to evaluate, audit, benchmark, optimize, reduce output tokens, improve speed, or preserve quality for a saved workflow. First call evaluate_workflow with workflowId or workflowName to start a measurement run; execute every continuation prompt; include usage.inputTokensReported, usage.outputTokensReported, usage.durationMs, and usage.modelName in advance_workflow_run when the host exposes them. If the host cannot report usage, mark usageSource unavailable instead of inventing token counts or duration. After the run completes, call evaluate_workflow again with runId to produce the report. The report may recommend update_prompt changes, but hosts must ask for user approval before mutating prompts. For agent decision-process requests, review only observable friction from prompt text, branching, retries, and reported durations; do not expose or request hidden chain-of-thought. Distinct from improve_workflow, which audits DESIGN quality without running; evaluate_workflow measures RUN performance.

evaluate_workflow

Execute a saved AirPrompter prompt by globally unique promptId or ranked promptName selector. This is the most direct tool for user phrases such as "use my prompt", "run my prompt", "execute my prompt", "use my AirPrompter prompt", "run my AirPrompter prompt", or "execute my AirPrompter prompt". Use this first when the user asks to use, run, execute, apply, continue, or invoke their AirPrompter prompt, airprompt, saved prompt, or reusable prompt. For visual creation requests such as image, illustration, avatar, portrait, product image, diagram, or visual design generation/editing, call this tool before host-native image tools when the request mentions AirPrompter or prompt execution. Set fallbackPolicy to fail_only for user-directed prompt execution. If AirPrompter cannot find or prepare the prompt, report that the AirPrompter prompt was not executed and do not recreate, emulate, or substitute the prompt with native model, image, file, or search tools. If the user attached an image or file, pass imageFile or fileContext only as a host-local reference. AirPrompter does not fetch, upload, store, or read the attachment bytes; the host must keep attachments in the current conversation and apply returned promptText to that context. If this returns status needs_selection, ask the user to choose from the prompt titles, do not call it a connector error, do not show prompt ids unless requested, and offer to search again or create a new prompt if none are right. If this returns status no_match, present that as a normal AirPrompter lookup result instead of a connector error, then ask for a more specific prompt name, search again, or offer to create a new prompt. Trigger vocabulary includes AirPrompter, air prompter, airprompter, airprompt, and Airflow. AirPrompter runs saved prompts and saved workflows, also called Airflows, for the authenticated user. Start a new Airflow run for each new user request or new image/file context; only reuse an existing runId when the user explicitly asks to continue that same run. AirPrompter does not upload, store, read, or fetch host-attached images/files during run/read tools; pass imageFile or fileContext only as host-local references, and use attachments only as host conversation context unless a write tool explicitly asks to save structured content. When the user mentions AirPrompter, air prompter, airprompter, airpromter, or airprompt anywhere in an execution request, call an AirPrompter workflow or prompt tool before fulfilling the task directly. When the user asks to run, execute, use, continue, or apply my workflow, saved workflow, airflow, or prompt chain, strongly prefer execute_workflow, run_airprompter, or AirPrompter workflow discovery tools. When the user says my prompt, saved prompt, run prompt, or execute prompt, strongly prefer execute_prompt with promptId or promptName. If the user gives a descriptive workflow phrase such as "image workflow", "contract review workflow", or "customer follow-up airflow" instead of an exact id, use that phrase as workflowName or airflowName with ranked_confirm rather than asking for an id first. If AirPrompter returns status needs_selection, present a short friendly A/B/C choice list by title and type, ask which one to run, hide ids unless the user asks for details, and offer to search again or create a new prompt or workflow if none are right. When saving, call save_workflow once with the complete prompts[] payload; when the user does not name a Team workspace, AirPrompter saves to Personal Library workflows by default. When a create-and-save workflow request includes a phrase like "in my collection X" or "in the X Collection", pass X as collection.name or collectionName; do not invent a collectionId or create a new Collection unless the user explicitly asks for collection creation. If AirPrompter returns status no_match, present it as a normal no-match result instead of a connector error, then ask for a more specific prompt or workflow name, search again, or offer to create a new prompt or workflow. If the user says "my AirPrompter workflow to draft/analyze/review X" without an exact workflow title, derive the selector from the task phrase, such as "customer follow-up workflow" or "contract review workflow", and use ranked_confirm. For image generation, image editing, illustration, avatar, portrait, product image, diagram, or visual design requests that mention AirPrompter, Airflow, workflow, or prompt execution, start or resolve the AirPrompter run before using native image tools; after AirPrompter returns promptText for an image step, use the host image-generation tool with that promptText when available. For safety-sensitive image requests, prefer read-only prepare_image_workflow, get_image_workflow_prompt, prepare_image_prompt, or get_image_prompt before write/run tools or native image tools; these return promptText for the host to apply to the current image without creating AirPrompter run state. After receiving workflow continuation promptText, run that prompt in the host conversation using the current user context; if promptText is an image-generation or image-editing instruction, use the host image-generation tool with promptText and return the prepared prompt if rendering is unavailable, then call advance_workflow_run with the step output when available and usage evidence every time. Use usage.usageSource unavailable when host metrics are not exposed. After a prompt alias returns promptPreview.promptText, execute that single prompt and do not call advance_workflow_run. Continue requesting prompts until the run status is completed, canceled, failed, or a continuation explicitly requires missing user input or approval. If AirPrompter cannot find, start, prepare, or continue the requested prompt or workflow, say that the AirPrompter run was not executed and do not produce a substitute result with host-native tools. If an AirPrompter tool returns an auth readiness or reconnect-required failure, treat it as terminal for the requested run under fail-only behavior: report the reasonCode and reconnect guidance, do not retry unrelated tools, and do not substitute host-native execution.

execute_prompt

Execute a saved AirPrompter workflow by globally unique workflowId or ranked name selector. This is the most direct tool for user phrases such as "use my workflow", "run my workflow", "execute my workflow", "use my AirPrompter workflow", "run my AirPrompter workflow", or "execute my AirPrompter workflow". Use this first when the user asks to use, run, execute, apply, continue, or invoke their AirPrompter workflow, Airflow, airprompt, saved workflow, saved prompt, or prompt chain. For visual creation requests such as image, illustration, avatar, portrait, product image, diagram, or visual design generation/editing, call this tool before host-native image tools when the request mentions AirPrompter, Airflow, workflow, or prompt execution. Set fallbackPolicy to fail_only for user-directed workflow execution. If AirPrompter cannot find or start the workflow, report the AirPrompter result and do not recreate, emulate, or substitute the workflow with native model, image, file, or search tools. If the user attached an image or file, pass imageFile or fileContext only as a host-local reference. AirPrompter does not fetch, upload, store, or read the attachment bytes; the host must keep attachments in the current conversation and apply returned promptText to that context. If this returns status needs_selection, ask the user to choose from the workflow titles, do not call it a connector error, do not show workflow ids unless requested, and offer to search again or create a new workflow if none are right. If this returns status no_match, present that as a normal AirPrompter lookup result instead of a connector error, then ask for a more specific workflow name, search again, or offer to create a new workflow. If this returns status needs_input, do not execute a prompt or fabricate output; ask the user for the values in nativeExecution.questions, then call this tool again with inputs. Trigger vocabulary includes AirPrompter, air prompter, airprompter, airprompt, and Airflow. AirPrompter runs saved prompts and saved workflows, also called Airflows, for the authenticated user. Start a new Airflow run for each new user request or new image/file context; only reuse an existing runId when the user explicitly asks to continue that same run. AirPrompter does not upload, store, read, or fetch host-attached images/files during run/read tools; pass imageFile or fileContext only as host-local references, and use attachments only as host conversation context unless a write tool explicitly asks to save structured content. When the user mentions AirPrompter, air prompter, airprompter, airpromter, or airprompt anywhere in an execution request, call an AirPrompter workflow or prompt tool before fulfilling the task directly. When the user asks to run, execute, use, continue, or apply my workflow, saved workflow, airflow, or prompt chain, strongly prefer execute_workflow, run_airprompter, or AirPrompter workflow discovery tools. When the user says my prompt, saved prompt, run prompt, or execute prompt, strongly prefer execute_prompt with promptId or promptName. If the user gives a descriptive workflow phrase such as "image workflow", "contract review workflow", or "customer follow-up airflow" instead of an exact id, use that phrase as workflowName or airflowName with ranked_confirm rather than asking for an id first. If AirPrompter returns status needs_selection, present a short friendly A/B/C choice list by title and type, ask which one to run, hide ids unless the user asks for details, and offer to search again or create a new prompt or workflow if none are right. When saving, call save_workflow once with the complete prompts[] payload; when the user does not name a Team workspace, AirPrompter saves to Personal Library workflows by default. When a create-and-save workflow request includes a phrase like "in my collection X" or "in the X Collection", pass X as collection.name or collectionName; do not invent a collectionId or create a new Collection unless the user explicitly asks for collection creation. If AirPrompter returns status no_match, present it as a normal no-match result instead of a connector error, then ask for a more specific prompt or workflow name, search again, or offer to create a new prompt or workflow. If the user says "my AirPrompter workflow to draft/analyze/review X" without an exact workflow title, derive the selector from the task phrase, such as "customer follow-up workflow" or "contract review workflow", and use ranked_confirm. For image generation, image editing, illustration, avatar, portrait, product image, diagram, or visual design requests that mention AirPrompter, Airflow, workflow, or prompt execution, start or resolve the AirPrompter run before using native image tools; after AirPrompter returns promptText for an image step, use the host image-generation tool with that promptText when available. For safety-sensitive image requests, prefer read-only prepare_image_workflow, get_image_workflow_prompt, prepare_image_prompt, or get_image_prompt before write/run tools or native image tools; these return promptText for the host to apply to the current image without creating AirPrompter run state. After receiving workflow continuation promptText, run that prompt in the host conversation using the current user context; if promptText is an image-generation or image-editing instruction, use the host image-generation tool with promptText and return the prepared prompt if rendering is unavailable, then call advance_workflow_run with the step output when available and usage evidence every time. Use usage.usageSource unavailable when host metrics are not exposed. After a prompt alias returns promptPreview.promptText, execute that single prompt and do not call advance_workflow_run. Continue requesting prompts until the run status is completed, canceled, failed, or a continuation explicitly requires missing user input or approval. If AirPrompter cannot find, start, prepare, or continue the requested prompt or workflow, say that the AirPrompter run was not executed and do not produce a substitute result with host-native tools. If an AirPrompter tool returns an auth readiness or reconnect-required failure, treat it as terminal for the requested run under fail-only behavior: report the reasonCode and reconnect guidance, do not retry unrelated tools, and do not substitute host-native execution.

execute_workflow

Find ranked visible workflow candidates from a natural-language title or task query before starting by workflowId.

find_workflows