# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Retarget marketplace searchers who found nothing once supply arrives.
The #roadway-skill block on this page holds a SKILL.md for it, including the full prompt. Treat that file as a starting point. It will not just work if you paste it into ChatGPT or Claude.
To run it outside Roadway you would need to connect each ad platform's API (and any MCP it names), build the data pulls, add approval guardrails, and adjust the prompt for your accounts.
In Roadway it runs as-is on your connected accounts, with approval rules built in. Open it in a new chat at https://www.roadwayai.com/workflows/retarget-marketplace-searchers-who-found-nothing-once-supply-arrives
Page: https://www.roadwayai.com/workflows/retarget-marketplace-searchers-who-found-nothing-once-supply-arrives
Library index: https://www.roadwayai.com/automation-library
---
name: retarget-marketplace-searchers-who-found-nothing-once-supply-arrives
description: >-
When a city or category that used to return no results now has enough listings, brings back the people who searched there and left empty-handed, using the audience PostHog or Segment syncs, judged on marketplace revenue.
---
# Retarget marketplace searchers who found nothing once supply arrives
Source: https://www.roadwayai.com/workflows/retarget-marketplace-searchers-who-found-nothing-once-supply-arrives
From the Workflow Automation Library by Roadway.
## Before you use this outside Roadway
This SKILL.md is a starting point. It needs adjusting before it will work outside Roadway.
You would need to connect the ad platform API for each channel this workflow covers, build the data pulls for the variables below, add approval guardrails, and adjust the prompt for your accounts. If the prompt names an MCP tool, you also need that MCP connected.
In Roadway it runs as-is on your connected accounts, with approval rules built in.
## What it does
When a city or category that used to return no results now has enough listings, brings back the people who searched there and left empty-handed, using the audience PostHog or Segment syncs, judged on marketplace revenue.
Each run, it checks your supply data for cities or categories that now have enough listings. When one crosses your bar, it brings back the people who searched there and left with nothing, using the audience your PostHog or Segment setup syncs, and judges the campaign on marketplace revenue. It checks for its trigger on every scheduled run, so you can act on it then instead of waiting for your next review. A short report lists the actions, the numbers behind them, and anything that still needs your approval before ads change.
## Steps
1. Collect the inputs listed under Variables. In Roadway they come from your connected accounts. Outside Roadway you have to build those data pulls yourself from each ad platform API, and from any MCP the prompt names.
2. Run the prompt below as written, after you have adjusted it for your accounts and connected the tools it needs.
3. Review the result. Apply changes to a live ad account only after you approve them. Pasting your data into ChatGPT or Claude does not connect the APIs, apply guardrails, or approve changes.
## Variables
auto_approve, brand_kit, creative_library, customer_audiences, experiment_budget_pct, funnel_metrics, goal_metric, marketplace_liquidity, max_change_pct, monthly_budget_cap, task_history
## Prompt
Retarget marketplace searchers who found nothing once supply arrives
Check [set this to your own marketplace liquidity] for markets or categories that crossed the liquidity bar since the last run, and for each one with a synced audience of people who searched there and found nothing, decide:
1. Launch win-back campaign
2. Wait for more supply
3. Scale
4. Pause
Context and defaults (use these; don't ask):
- Supply and demand balance by market or category: [set this to your own marketplace liquidity]. If it isn't available, say so and stop.
- The liquidity bar: the supply level in [set this to your own marketplace liquidity] your team treats as healthy for a market. If none is set, say so and stop.
- The zero-results audience: people who searched a market and found nothing, synced to each platform by PostHog or Segment ([set this to your own customer audiences]). Reference it by name only; Roadway never builds or uploads user lists. If none is synced for a market, skip that market.
- Marketplace revenue: the revenue stage in [set this to your own funnel metrics] from completed transactions. If it isn't mapped, judge on [set this to your own goal metric] and say so.
- The brand kit: [set this to your own brand kit]. If not set, use the logo, colors and fonts visible on the coworker's landing pages and live ads, and mark anything beyond that Unverified.
- The creative library: [set this to your own creative library]. If not set, use the ad platform's asset performance and Task History.
- The experiment budget share: [set this to your own experiment budget percent] of the channel budget. If not set, 10%.
- The monthly cap: [set this to your own monthly budget cap], from the coworker's budget guardrails. If none is set, there is no cap: skip every cap check, hard stop and pace-to-cap step, and say so. Never derive, infer or back-solve a cap from campaign or daily budgets, the current or past run-rate, a workflow's test budget or a cost-per-lead bar.
- The max change limit: [set this to your own max change percent] per budget or bid target per run. If not set, 20%. It does not apply to experiment traffic splits.
- Auto-approve: [set this to your own auto approve]. If not set, it's off: list every change as a proposal for approval.
Rules:
- A market qualifies when it crossed the liquidity bar since the last run and its zero-results audience is large enough for the platform to deliver.
- Launch win-back campaign: a local retargeting campaign on that audience with "now available in [city or category]" creative, at [set this to your own experiment budget percent] of the channel budget, claiming only what the current listings support.
- Wait for more supply when the market only just crossed the bar and could fall back under it.
- Exclude people who already transacted in that market, using synced audiences.
- Judge on Roadway-attributed marketplace revenue per dollar, not clicks. Scale by up to [set this to your own max change percent] when it beats the account's other retargeting, and pause when it's clearly worse.
- Prospecting for new demand in a newly liquid market belongs to the city launch workflow. This one only brings back people who already searched.
- Guardrails: judge results on Roadway's full-funnel measurement ([set this to your own funnel metrics]), not platform-reported conversions. Check [set this to your own task history] so you don't repeat a change that already hurt performance. Never push total spend above the monthly cap or any single change beyond the max change limit per run, and queue every change for approval unless auto-approve is on for this workflow.
Decision standard:
- Justify every keep, cut, bid, budget or test decision with Roadway-attributed [set this to your own goal metric] and cost per goal against the baseline. Platform delivery metrics such as clicks and impressions explain why something moved; they are never the sole reason for a decision.
- Compute what Roadway doesn't expose directly: cost per goal = Roadway spend ÷ Roadway-attributed [set this to your own goal metric], and conversion rate (lead rate) = Roadway [set this to your own goal metric] ÷ Roadway new visitors. Don't substitute platform-reported conversions or conversion rates.
- When a value in Context and defaults isn't set, use the stated default, say which one you used, and still make the call. Don't stop to ask.
- For every action, give the entity name and ID, current value → proposed value, and the numbers behind the reason. Write "None" under any empty heading.
- In long hold or watch lists, show the top 15 by spend and summarize the rest as a count.
Give me a report of each with reasoning for each action. Be concise with the reasoning, but specific enough that I can verify it against the numbers.
Report structure:
Marketplace supply win-back report
Summary:
Markets that crossed the bar, campaigns launched or changed, and the marketplace revenue they brought back.
Launch win-back campaign:
- [market] - [reason]
Wait for more supply:
- [market] - [reason]
Scale:
- [market] - [reason]
Pause:
- [market] - [reason]
## Run it in Roadway
https://www.roadwayai.com/workflows/retarget-marketplace-searchers-who-found-nothing-once-supply-arrives
Retarget marketplace searchers who found nothing once supply arrives
Retarget marketplace searchers who found nothing once supply arrives
When a city or category that used to return no results now has enough listings, brings back the people who searched there and left empty-handed, using the audience PostHog or Segment syncs, judged on marketplace revenue.
Each run, it checks your supply data for cities or categories that now have enough listings. When one crosses your bar, it brings back the people who searched there and left with nothing, using the audience your PostHog or Segment setup syncs, and judges the campaign on marketplace revenue. It checks for its trigger on every scheduled run, so you can act on it then instead of waiting for your next review. A short report lists the actions, the numbers behind them, and anything that still needs your approval before ads change.