PlaysbyMoat8
Back to the library
The workflow guideOperations

Build a feasible visitor itinerary

Combine visitor preferences with verified places, opening hours and travel time to prepare a realistic day-by-day itinerary with fallbacks.

5 implementation stepsIntermediate

How this works

Build an itinerary that can plausibly be followed, rather than a list of attractive places. Reconcile dates, visitor interests, accommodation location, opening windows, visit durations and movement time. Keep confirmed facts separate from assumptions so a planner can see which parts still need verification.

Start with a broad candidate pool, then group nearby places and test each day's sequence. Preserve fixed appointments and visitor constraints before optimizing convenience. The output is a reviewed planning draft with alternatives; it does not reserve tickets, arrange transport or promise availability.

Before you start

Visitor brief

Confirm dates, starting location, party size, interests, pace and any constraints the visitor chooses to share.

Current venue evidence

Use official venue information for hours, closures and ticket conditions where available.

Movement assumptions

Choose walking, public transport or driving and agree buffers appropriate to the visitor.

Prepare the inputs

visitor_brief
Required

structured dates and preference notes

Resolve date and timezone ambiguity; distinguish hard constraints from preferences.

fixed_commitments
Required

appointments and start/end locations

Include exact times and whether they may move; use an explicit empty list when none exist.

place_candidates
Required

place IDs, coordinates and source records

Preserve official names, current hours, visit-duration assumptions and evidence dates.

travel_parameters
Required

transport mode, buffers and budget rules

Record currency and whether estimates include entry, meals and transport.

Implementation, step by step

  1. Translate the request into constraints

    • Create a table of hard requirements, preferences and unresolved questions. Anchor each day to accommodation, arrival or departure details and any fixed commitments.
    • Use only necessary accessibility or dietary information voluntarily supplied for planning. If a constraint is unknown, show an assumption rather than treating it as absent.

    Checkpoint: The planner can identify every mandatory condition before place selection.

  2. Build and verify the candidate pool

    • Find suitable attractions, restaurants and activities with stable identifiers and official source records. Record opening dates, weekday patterns, exceptions and reservation requirements.
    • Reject nonexistent or permanently closed places. Mark uncertain seasonal hours, unavailable ticket information and estimated visit durations explicitly; missing information is not zero duration or free entry.

    Checkpoint: Each candidate has a traceable location and a current evidence status.

  3. Group places into practical days

    • Cluster candidates by geography and visitor priorities. Reserve fixed commitments first, then assign nearby places with a mix of effort and interests.
    • Avoid cramming all high-ranked candidates into one day. Set aside alternates by area so weather, fatigue or a closure can be handled without rebuilding the entire plan.

    Checkpoint: Every day has a coherent area, realistic load and a nearby alternative.

  4. Check the sequence and timing

    • Calculate travel time for the chosen mode, add approved buffers and schedule arrival, visit and departure times. Recalculate budget totals with deterministic arithmetic and explicit currency.
    • Test every stop against opening windows and the next commitment. If no routing service is available, use documented manual travel estimates and label the plan as needing route verification.

    Checkpoint: A constraint table exposes overlap, late arrival, budget excess and unverified travel assumptions.

  5. Explain choices and prepare the handoff

    • Write a compact visitor-facing plan with why each stop fits, practical notes and what requires confirmation. Keep evidence and the detailed constraint table available to the planner.
    • Give alternatives with the specific substitution condition and resulting timing changes. Refresh volatile venue facts before final sharing; leave bookings and external messages to separately authorized work.

    Checkpoint: The handoff contains a feasible primary route, visible assumptions and usable fallbacks.

Decisions along the way

A preferred place is closed on the only suitable day

Offer an evidenced alternative or ask which constraint may change; do not silently ignore the closure.

Travel time makes the day infeasible

Remove or move the lowest-priority flexible stop and recompute the remaining schedule.

Accessibility information is missing

Flag the venue for direct confirmation rather than inferring accessibility from photographs.

What you will produce

visitor-itinerary.md

Markdown

A practical planning draft for the visitor.

Include: day · arrival_time · place · duration · travel_leg · reason · booking_note · fallback

itinerary-checks.csv

CSV

The planner's feasibility and verification record.

Include: constraint · stop_id · evidence_date · planned_value · check_result · assumption · owner

Check the result

  • Recheck weekday and date-specific opening windows.
  • Verify that travel legs connect the actual consecutive stops.
  • Recompute daily time and cost totals outside the language model.
  • Ensure every mandatory visitor constraint is satisfied or openly unresolved.

When something goes wrong

Venue information conflicts across sources

Prefer current official information and flag unresolved conflicts for planner confirmation.

Routing service is unavailable

Use clearly labeled manual estimates and withhold a fully verified feasibility claim.

A fixed commitment changes

Recompute the affected day and retain a change summary.

A worked example

SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT

Request

Synthetic: plan a half-day visit ending at a station by 16:00.

Inputs

The museum opens at 10:00 and needs 90 minutes. A garden is 25 minutes away and needs 60 minutes. The station is 35 minutes from the garden; the planner requires a 20-minute arrival buffer.

Expected result

The plan reserves the station buffer and travel legs, then schedules the two visits within the available window. An unverified lunch venue is optional, not a required timed stop.

Run a small pilot

Start small

Rebuild three past itineraries with known closures, fixed appointments and different travel modes.

Record the baseline

Record manual planning time and feasibility corrections made before sharing.

Agree success criteria

Agree a maximum unresolved-fact count and require no hard-constraint violations.

Stop or revise

Do not mark a plan ready while a mandatory venue or movement constraint remains unverified.

Keep the scope clear

  • No booking, payment or message sending is implied by preparing an itinerary.
  • Do not promise real-time availability or safety from a planning snapshot.
  • Retain only the visitor information needed for the requested plan.

Check before using

A travel planner verifies current opening information, accessibility requirements and travel assumptions before sharing the plan.

Business activities

  • Onboard customers, partners, and members
  • Deliver recurring client work

Editorially adapted workflow; not independently tested.

FROM A RECIPE TO YOUR WORKFLOW

Bring the company context together.

This workflow needs reliable inputs before it needs a better prompt. Moat8 Vault brings working information into a readable archive for the AI tools you use.

For this recipe: visitor brief · fixed commitments · place candidates · travel parameters

Start with one recurring task, agree which sources to use, and review the first result with your team.

Discuss this workflow

What does your team do?

Choose the recurring work you would like to improve.

A field guide, made for work.

Plays is a curated library of anonymized business workflows. Each recipe explains the inputs, steps, tools, and checks you can adapt to your team. These are editorial guides, not independently tested implementations.

When you share a company website, the guide may read a limited number of public pages on that website. Messages and retrieved page text are sent to our AI provider, NVIDIA, to recommend relevant workflows. Share a general description rather than confidential information.

Saved workflows and selected activities stay in this browser. Your chat history and selected company website are kept in this tab and cleared when you reload or start a new chat. The server does not store conversations. Live source monitoring is not enabled.

If you allow analytics, PostHog receives page views and actions such as workflow saves, skill downloads and link clicks. Random browser and session identifiers connect these actions without identifying you by name. Your choice and browser identifier expire after 90 days; sessions restart after 30 minutes of inactivity or 24 hours. We use local storage, not analytics cookies. Messages, company URLs, search text, full referrers and IP addresses are not sent. There are no person profiles or session recordings. You can decline or withdraw in Analytics settings; Do Not Track and Global Privacy Control keep analytics off.

Read the Plays Privacy Notice ↗