TL;DR
Win & Scale or Foreplay: the short answer
Win & Scale is Meta ads for AI agents, from $49/mo per ad account. Foreplay is ad inspiration and creative analytics, from $59/mo.
Foreplay is ad inspiration and creative analytics for paid social: a swipe file, an ad search engine, competitor tracking, Lens analytics on your own ads, AI briefs, and an MCP server and API.
Win & Scale is Meta ads for AI agents: your own agent reads every creative, briefs the next test and builds the launch paused. Spend starts only when you say go.
Pick Foreplay to research ads across networks and brief a creative team. Pick Win & Scale when your agent runs your Meta ads and you approve what spends.
How does Win & Scale compare to Foreplay?
Foreplay is built to find and organize ads. Win & Scale is built for an AI agent to read, test and launch your own.
| Capability | FForeplay | Win & Scale |
|---|---|---|
| The product | ||
| What it is | Ad inspiration and creative analytics: Swipe File, Discovery, Spyder, Lens and Briefs | Meta ads for AI agents, with a web app beside your agent |
| Where you work | Foreplay's web app, Chrome extension and mobile app. MCP and API are listed on Workflow and Agency | Your own AI agent: Claude Code, ChatGPT, Cursor or Codex, plus the web app |
| Ad networks | Meta, TikTok, LinkedIn. Lens connects Meta and TikTok ad accounts | Meta only: Facebook and Instagram |
| MCP access | Yes Yes, to research and your data. It searches ads and reads your boards and Lens data. Its help page describes nothing that changes an account | Yes Yes. Every action in the app is an MCP tool |
| Research and inspiration | ||
| Searching ads | Yes Discovery: AI search across Facebook, Instagram, TikTok and LinkedIn ads, filtered by niche and format | Yes Meta Ad Library search. meta_search_ad_library finds ads on demand |
| Tracking competitors | Yes Spyder: tracks a brand's Meta ads around the clock and keeps them | No Search, not tracking. Save what you find to a swipe file |
| Swipe file | Yes Boards and Swipe File, with transcription and sharing | Yes Swipe file. meta_save_swipe keeps an ad your agent can brief from |
| Reading your own ads | ||
| What a creative is | AI metadata and custom tags in Lens, plus manual ratings | Values you curate: angle, persona, offer, hook, format. The ad name is only a hint |
| Video | Yes Transcribed, with hooks pulled out | Yes Transcribed and read in full, not judged from one still |
| Reports | Yes Shareable reports, white-label and password-protected | Not public Not a reporting tool. Your agent answers in chat; the web app shows the account |
| Briefs, testing and launching | ||
| Briefs | Yes AI scripts and storyboards, in 150+ languages, exported to PDF or Sheets | Yes Briefs your agent saves. meta_save_brief keeps the angle, hook and evidence behind a test |
| Creative testing | Yes Creative test analysis in Lens, and competitor tests in Spyder | Yes A test loop. The question is frozen when you commit; outcomes are appended |
| Launching ads | Not public Not public. Its pages describe no way to launch ads | Yes Always paused. meta_launch_ads builds the campaign, ad set and ads |
| Turning spend on | Not public Not public | Yes Only on your go-ahead. meta_activate is a separate call |
| Price | ||
| Starting price | $59/mo on Basic for 1 user, without Lens. Workflow, with Lens and MCP, is $175/mo | $49/mo per ad account, up to $10k monthly spend |
| What the price counts | Users and Lens brands. $20 per extra user, $50 per extra Lens brand | Per ad account, by monthly spend. Every feature on every tier |
| API and AI usage | Yes 10,000 API credits a month. One ad is one credit; 100,000 more cost $99/mo | Yes 0 AI credits per agent call. Runs on your own Claude or ChatGPT plan |
| Free trial | Yes 7 days, with a credit card | Yes 7 days, every feature. No free plan |
Yes No Not publicForeplay facts from foreplay.co (pricing, mcp, api, discovery, spyder-ad-spy, lens-creative-analytics, briefs) and help.foreplay.co (MCP, API credits) · Checked 2026-10-28. “Not public” means we couldn't find it there. Spot something out of date? Tell us.
Why use Win & Scale instead of Foreplay?
Teams add it when the work moves from collecting ads to running them.
A brief for Saltmilk, a fictional skincare brand, with a swipe attached as its reference: a Daybloom selfie ad, Active since Oct 3. The concept reads, A Sunday skin reset, shot as a selfie at the bathroom sink. A Make one like this chip starts the brief, written with meta_save_brief. The swipe is reference only and cannot be launched. A saved ad becomes your next brief
Your agent searches the Meta Ad Library, saves what's worth copying and drafts a brief for the next test. Foreplay briefs are scripts and storyboards for a creative team.
A creative read by the agent: a Vessa Row fitting-room selfie, a fictional fashion brand, captioned Okay this blazer is the one. Its Values are the angle Staple blazer, the persona Office-to-evening dresser, the format UGC selfie and the hook Fitting room selfie caption. Its ad name, v3_final_FINAL, is only a hint. Your agent reads the ad, not its name
Angle, persona, offer and hook are stored as Values on every creative, read by a classifier and curated by you. Ads with messy names, or none, get read too, so your history counts from the first day.
A test record for Vessa Row, a fictional brand, with its two creatives. The question, Does a fitting-room selfie beat a studio shot for the capsule wardrobe shopper? was frozen on 14 October. Day 3 was low delivery, inconclusive and not a loss. Day 10 appended an observation. Concluding the test leaves the question unchanged. Every test keeps the question it asked
When you commit to a next test, its question and the evidence behind it are frozen. Results are appended, never rewritten, so the answer can't drift to fit what happened.
A launch built with meta_launch_ads for Vessa Row, a fictional fashion brand. The campaign, the cold-persona ad set and the three ads are all Paused. meta_activate is a separate call, waiting for you. Every launch lands paused
Your agent builds the campaign, ad set and ads, all created paused. Turning a launch on is a separate call that waits for your approval. Foreplay's pages describe no launch step.
When is Foreplay the better choice?
Foreplay does things Win & Scale doesn't. If the left column is your team, start with Foreplay.
Research
Pick Foreplay if you…Want a large ad search engine across Facebook, Instagram, TikTok and LinkedIn
Pick Win & Scale if you…Already work in Claude Code, ChatGPT, Cursor or another AI agent
Competitors
Pick Foreplay if you…Want competitor brands tracked and saved automatically, with Slack or email updates
Pick Win & Scale if you…Want your agent to read your own ads and name what's worth repeating
Team
Pick Foreplay if you…Have creators and clients who work from boards, brief pages and white-label reports
Pick Win & Scale if you…Want every launch created paused, and spend that starts only on your go-ahead
Networks
Pick Foreplay if you…Report on TikTok ad accounts as well as Meta
Pick Win & Scale if you…Want angle, persona, offer and hook stored on each creative, not parsed from names
Briefs
Pick Foreplay if you…Want AI scripts and storyboards in 150+ languages, exported to PDF
Pick Win & Scale if you…Want tests that keep the question they were launched to answer
How do I start if I use Foreplay?
Three steps, about an afternoon. Keep Foreplay for research if you like; Win & Scale reads your Meta account directly.
An agent session: one claude mcp add command registers the Win & Scale MCP server, and three of its tools show as connected. Connect your agent
Add the MCP server to Claude Code, Cursor or Codex, or add it as a connector in ChatGPT or Claude. Sign in once in the browser.
Settings, Meta connection: an ad account id and a masked System User token, checked against Meta before they are saved. The token is encrypted and revocable in Meta. Connect your ad account
A workspace admin pastes a System User token and the ad account id. It's checked against Meta before it's saved, and you can revoke it in Meta any time.
An agent reads the account's history: the prompt “Read our history and tell me what worked”, the call meta_pull_account_history, and three Vessa Row creatives, fictional, each marked Winner, In line or Unproven. Your agent reads the history
It pulls every ad's lifetime totals, reads the Values on each creative, and names the traits that bought more than their share of spend.
Is Win & Scale cheaper than Foreplay?
For one Meta ad account up to $25k a month in spend, yes. Foreplay prices by users and brands, so it costs less above that.
Win & Scale
- Ad spend up to $10k a month$49/mo
- Ad spend up to $25k a month$99/mo
- Ad spend up to $50k a month$199/mo
- Ad spend up to $100k a month$299/mo
- Ad spend up to $250k a month$399/mo
- Ad spend over $250k a monthCustom
7-day free trial with every feature. No free plan. 0 AI credits per agent call.
Foreplay
Plans by users and brands, billed monthly. Lens and MCP start on Workflow.
- Basic · 1 userSwipe File, Discovery, Briefs. No Lens$59/mo
- Workflow · 5 usersAdds Spyder, Lens for 1 brand, MCP and API$175/mo
- Agency · 10 usersLens for 10 brands, more Spyder brands$459/mo
- EnterpriseUnlimited users and usageCustom
Annual billing: Basic $49, Workflow $149, Agency $389 a month. 7-day free trial, card required. Source: foreplay.co/pricing, 2026-10-28.
Worked examples
Monthly list prices against Foreplay Workflow, one Lens brand per ad account
1 account at $8k spend
$49 vs $175 on Workflow
1 account at $40k spend
$199 vs $175 on Workflow
3 accounts at $8k each
$147 vs $275 on Workflow
Ad research, no ad account
Foreplay Basic, $59/mo
Questions, answered
Everything else is in the docs.
- Is Win & Scale cheaper than Foreplay?
- Win & Scale is cheaper for one Meta ad account up to $25k a month in spend. It costs $49 or $99 against $175 for Foreplay's Workflow plan, which adds Lens and MCP. Above that, Foreplay is cheaper, because it prices by users and Lens brands, not spend.
- Does Foreplay have an MCP server?
- Yes, Foreplay has an MCP server for Claude, ChatGPT and other MCP clients. It searches ads and reads your boards and Lens data; its help page describes nothing that changes an account. Win & Scale's tools also brief, test and launch, with every launch built paused.
- Does Foreplay have an API?
- Yes, Foreplay has an API with Spyder, Discovery and Swipe File endpoints. One ad costs one credit, plans include 10,000 credits a month, and 100,000 more cost $99 a month.
- Can Foreplay launch ads?
- Foreplay's own pages describe no way to launch ads. It covers research, analytics and briefs. In Win & Scale every launch is created paused, and spend waits for your go-ahead.
- Can I use Win & Scale with Foreplay?
- Yes, Win & Scale can run beside Foreplay. Keep Foreplay for finding ads, and let your agent read your account here; nothing Win & Scale builds spends until you turn it on.
- Does Win & Scale work with TikTok or LinkedIn ads?
- No, Win & Scale covers Meta only: Facebook and Instagram. Foreplay searches Facebook, Instagram, TikTok and LinkedIn ads, and its Lens connects Meta and TikTok ad accounts.
- Does Win & Scale charge for AI usage?
- No, Win & Scale charges 0 AI credits per agent call. Your agent runs on your own Claude, ChatGPT or other plan, and you pay one monthly price per ad account.