Shiftly Public Scheduling Agent

An LLM-guided scheduling agent for small businesses. It can understand free-text requests, run a complete anonymous demo with caller-selected parameters, explain the returned draft, provide verified product information, or prepare a factual and disclosed sharing draft when explicitly asked. It stays focused on scheduling and Shiftly; it does not answer unrelated chat or publish promotional copy. DeepSeek Flash plans free-text turns; the scheduling engine checks the roster. Each demo is fictional, isolated, unsaved and unpublished. No login, OAuth or access token is required. Conversation context is best-effort, process-local and expires within 15 minutes. Keep the returned result.task.contextId and send it on the next SendMessage as message.contextId (params.contextId is also accepted). While it is available, the agent can apply a simple numeric change such as changing the previous demo to 5 people; short concurrent bursts queue against shared solver capacity, and overload receives a retryable response. Resend the full scenario if the context cannot be retrieved. Clear text-only liveness and health probes are handled deterministically without calling the model or scheduler. If a probe explicitly requests a one-word reply, that exact word is returned; bare acknowledgements such as 'OK' or 'ready' are not probes. Probe responses confirm only that the A2A request was handled. Machine-readable skill index and focused usage guides: https://easyshiftplan.zhiyong.dev/.well-known/skills/index.json.

Skills

• Talk through a scheduling task
  Stay focused on small-business staff scheduling: run a fictional demo, return verified Shiftly facts for relevant product questions, or prepare a disclosed share draft only when explicitly asked. Free-text cafe requests map to restaurant; structured industry values must use the listed enum. Unrelated chat receives a brief redirect. Never publish, send or contact anyone.
  conversationagent-to-agentscheduling guidance
• Prepare a factual Shiftly share draft
  Only for an explicit request in the current conversation. Returns one factual, first-party draft with a tagged link and promotional disclosure. Draft only: no posting, messaging, outreach or form submission.
  sharingpromotiondraft only
• Generate a fictional staff schedule
  Create an isolated sample schedule, optionally setting industry, team size, operating days, coverage, period and fictional scheduling rules. The response is an unsaved draft for review.
  staff schedulingworkforcesmall businessrestaurantretaildemo
• Read factual product information
  Return current public product fit, boundaries, published pricing and useful links.
  product informationpricing
• Submit open-ended product feedback
  Submit a brief assistant-authored observation about product behavior. Do not include user prompts, personal details, real staff data, wages or real schedules. The assistant must honor an explicit opt-out.
  feedbackproduct improvement

How to call

https://easyshiftplan.zhiyong.dev/a2a

Listed in

Directories this entry was found in.