Mike Litman
1,000 Venues. One Question.
All slides
A TALK BY MIKE LITMAN

1,000 Venues.
One Question.

What happens when an AI calls every cafe in London and asks: are you pram-friendly? Everything we built, broke, fixed, and found.

Buggy Smart 1,000+ venues called 30 London boroughs April 2026
The Origin

Standing outside a cafe.
Guessing.

Every parent with a pushchair knows the feeling. You approach a cafe. You can't see through the window. You don't know if the door is wide enough, if there's a step, if there's space, if they'll make you feel welcome or like a problem. So you guess. Sometimes you're wrong. Sometimes you fold the buggy in the rain.

I had a one-year-old and a buggy and no data. So I built the data.

The Gap

This information doesn't exist anywhere.

No Michelin star for pram-friendliness. No Google Maps layer. No TripAdvisor filter. Venues say they're "family-friendly" on their website. Parents find out the hard way. The data gap is complete and nobody had noticed because nobody had tried to fill it.

Not on Google Maps Not on TripAdvisor Not on OpenTable Nowhere
The Inspiration

Guinndex called 3,000 Irish pubs.

One question: what's the price of a pint of Guinness? A simple question, asked at scale, produced the most honest pub price data in Ireland. Nobody had done it before. Not because the idea was hard, but because making 3,000 phone calls was impossible. Until it wasn't.

Same logic. Different question. Different city. The technology made it possible. The opportunity was the same: a dataset that has never existed, collected by a machine, verified by voice.

The Script

"Hi, quick question — are you pram-friendly?"

That's it. One question. Under 20 seconds when it works. The answer — yes, no, difficult, or silence — goes on the map. No survey. No form. No self-reported data. An AI called them and they said what they said.

Yes = green pin Difficult = amber pin No = red pin
The Agent

Meet
Poppy.

ElevenLabs voice agent. Calls venues directly from a London number. Asks one question. Handles IVR menus with DTMF tones. Listens for vague answers and follows up — "so a pushchair can get through the door OK?" — before closing.

Sounded convincingly human in over 99.9% of calls. Only 8 out of 10,000+ conversations detected it was an AI.

Typical call
STAFF  "Hello, The Bach, how can I help?"
POPPY  "Hi, quick question — are you pram-friendly?"
STAFF  "Yeah of course, absolutely!"
POPPY  "Brilliant, thanks so much — I'll be over soon! Bye!"
Classified: yes Duration: 18s
The Milestone

1,000
venues on the map.

522
Green — confirmed
pram-friendly
526
Amber — limited space,
worth calling ahead
92
Red — not
pram-friendly
30 London boroughs ~10,500 venues in dataset calls London daily
Finding #1

London is more pram-friendly than it thinks it is.

Only 8% of venues gave an outright no. The other 92% are accessible in some form — confirmed yes, or accessible with some nuance. Most cafes want pram customers. The hostility isn't policy, it's architecture. Steps and narrow doorways, not attitude.

The amber category is where the honesty lives. "It depends when you come." "It's a bit tight but we try." That nuance is split almost 50/50 with green — and it didn't exist anywhere before Buggy Smart.

~46% confirmed pram-friendly ~46% limited access / nuanced ~8% not accessible

"We're a basement venue, so there's about fifteen steps down. Once you're in, it's all on the flat."

London restaurant — classified amber

This venue would have shown as "family-friendly" in any self-reported survey. The AI call got the actual answer. That's the data that doesn't exist elsewhere.

Finding #2

Venues had never been asked this question before.

The pause before the answer. The hesitation. The "ooh, good question." Venues were genuinely surprised to be asked. Some consulted a colleague. Some looked around the room. The question made them think about accessibility in a way they never had to articulate before.

That's not a quirk. That's the proof of concept. If venues had to think, then parents had to guess. The gap between those two states is the entire value proposition of Buggy Smart.

Finding #3
8

out of 10,000+ calls detected it was an AI.

Most just answered the question. A few chatted. One took a full reservation. The calls are indistinguishable from a curious parent calling ahead. That's not a trick — it's just what a simple, honest question sounds like.

Failing #1
86% of calls were being classified as "unclear."

The Claude Haiku classifier was too conservative. When a human answered with anything ambiguous — "I think so," "probably," "we try" — Haiku returned "unclear" instead of inferring the most likely answer. The result: thousands of real conversations buried in a fog of uncertainty, contributing nothing to the map.

The fix: Rewrote the extraction prompt with a strict rule — if a human answered, you must return yes / difficult / no. Unclear is only permitted when nobody answered. 1,378 misclassified entries queued for automatic reclassification. Unclear rate: 86% → near zero for human-answered calls.
Failing #2
Every pipeline was dying at exactly 60 minutes. Every day.

GitHub Actions has a default 60-minute timeout. All three pipeline workflows — morning, refresh, retry — were hitting it daily and getting cancelled mid-batch. The watchdog that should have alerted us was also failing silently, due to a YAML heredoc parsing bug that made it crash in 0 seconds on every push.

The fix: Raised all three workflow timeouts to 180 minutes. Fixed the watchdog YAML error by replacing the Python block with a single curl command. Watchdog is now live and will alert Slack if no pipeline fires that day.
Failing #3
Voicemail calls were burning 90 seconds each.

69% of calls go to voicemail or no answer. Without answering machine detection, the ElevenLabs agent connected to every voicemail and spoke into it for the full call duration. One endpoint had a 90-second timeLimit. Every voicemail cost 90 seconds of AI time.

The fix: Twilio async AMD now detects voicemail in ~5-7 seconds and hangs up immediately. timeLimit reduced to 30s across all endpoints. Farewell detection ends the call 1.5s after Poppy says goodbye. Estimated saving: 46 minutes of wasted AI time per 175-call batch.
April 2026

One day. 12 things fixed. The pipeline came out the other side genuinely humming.

+67
New venues on map
in a single day
+9
New London boroughs
added in one session
85%
Reduction in wasted
voicemail call time
April 2026

184 venues appeared on the map this morning.
No calls were made.

The evening pipeline re-evaluated 10,000+ past call transcripts overnight and corrected its own earlier decisions. Calls made months ago, re-scored while no one was watching. Most datasets are frozen the moment they're collected. This one improves retroactively.

9,824 transcripts re-evaluated Runs nightly at 9pm Zero new calls required
Finding #4

This isn't just parenting data. It's accessibility infrastructure.

A venue that can get a pushchair in can also get a wheelchair in. Or a walking frame. Or a delivery trolley. Pram-friendliness is a proxy for step-free access, door width, ground-floor service — data that benefits anyone with a mobility need, not just new parents.

No London borough holds this data. No accessibility database has it. The NHS doesn't have it. Health visitors recommend cafes for postnatal groups without knowing if they're physically accessible. Buggy Smart fills a civic gap as much as a parenting one.

The Audience

Parents.
Buyers.
Boroughs.

Parents (B2C)
3.57M children aged 0–4 in the UK. Every one of them has at least one parent with a pushchair looking for somewhere to go. The map is free. The data grows daily. The audience is enormous, emotionally motivated, and highly social.
Venues (B2B)
Already-verified green venues are the warmest leads imaginable. They told an AI they're pram-friendly. They're the first call list for paid accreditation.
Organisations (B2B)
Supermarket chains, London boroughs, property developers, accessibility organisations. Anyone who needs to know what London's access infrastructure actually looks like.
Revenue Stream 1
The London Buggy Access Index 2026
A report nobody else can publish.
Borough breakdowns. Chain rankings. Best and worst venues named. Supermarkets compared. The first independent, AI-verified pram-accessibility dataset in London — published as a PDF report and raw data export.
Target buyers: supermarket chains · London boroughs · property developers · NCT · Mumsnet · Which? · Bugaboo

The press hook writes itself: "AI makes 10,000 calls to rank London's venues on buggy access." The supermarket chain comparison is the hero data point.

Revenue Stream 2

The sticker in the window that nobody can fake.

Buggy Smart Verified — £99/yr
Window sticker (posted), digital badge, verified map listing, printable certificate. For independent cafes and restaurants.
Buggy Smart Featured — £179/yr
Everything above + featured borough placement + social shoutout + "best of borough" inclusion.
The Moat
Every accredited venue is independently verified by phone call. Not self-reported. Not a form they filled in. A call was made and a human said yes. No competitor can manufacture that credential without doing the same work.
500 venues = £62K/yr  ·  1,000 = £123K/yr
Revenue Stream 3

The dataset as a product.

Once the London dataset is complete, the underlying data — venue IDs, coordinates, access classifications, call transcripts, confidence scores — becomes a structured feed licensable via API.

Parenting apps
Hoop, Peanut, Mush — all list venues, none have accessibility data. Buggy Smart fills their gap.
Mapping + booking
Google Maps, OpenTable, Resy, AccessAble — accessibility data enhances every listing and fills a regulatory gap.
Brand Partnerships

Brands whose customers are pushing buggies.

Buggy brands
Bugaboo
Co-brand the report. "Bugaboo recommends these venues." Natural audience alignment, £5-10K sponsorship range.
Buggy brands
iCandy / UppaBaby
Same playbook. Premium parent audience. Report launch partners or accreditation co-brand.
Parenting media
Mumsnet / NCT
Editorial partners. May pay for data exclusivity or commission the full report for their audience.
Consumer media
Which?
"Which supermarket is most pram-friendly?" is a Which? cover story. Exclusive data deal or licensing.
Supermarkets
Waitrose / Pret
Will pay to see their ranking before it goes public. And to respond to a bad one. Chain pricing: £5-10K flat.
Supermarkets
Tesco / Sainsbury's
Same. When chain comparison data is complete, every chain has a commercial reason to engage.
Baby / toddler
Hipp / Ella's Kitchen
Parent audience at exactly the right life stage. Map sponsorship or branded borough guides.
Lifestyle
Yoyo / Maxi-Cosi
Travel system brands selling to the exact audience using the map. Seasonal campaign partners.
Institutional Partners

Organisations that need this data and don't have it.

Civic / Public sector
All 33 London boroughs — "Family Friendly Borough" is a real civic initiative. None hold this data.

NHS / Health visitors — recommend postnatal meet-up venues without knowing if they're accessible. Buggy Smart is the layer they're missing.

Transport for London — natural co-brand with First Out (tube step-free guide). Combined pram+transit layer.
Property + Development
Property developers — "buggy-friendly neighbourhood" is a selling point for new-build marketing in family areas.

AccessAble — wheelchair access database, complementary not competitive. Partnership or data-share to cover both mobility communities.

OpenTable / SevenRooms — accessibility data enhances every listing. Integration or white-label deal.
The Launch

Once the technology is named in a Guardian article, the category is owned.

The press launch target: Times, Guardian, Telegraph family desk, Which?, Mumsnet News. The hook is the supermarket chain comparison — every editor wants to know which supermarket is worst. The mechanism (AI calling 10,000 venues) is the story above the story. Set a launch date. The pipeline runs itself.

After all 33 boroughs covered After 50+ results per supermarket chain Target: summer 2026
What's Next

The pipeline
runs itself.

Now
1,140 venues on map. 30 boroughs covered. Pipeline calling London daily. Classification self-improving nightly.
Next
Complete all 33 boroughs. Finish 76-venue supermarket batch (Tesco, Sainsbury's, Waitrose, M&S, Aldi, Lidl). Each chain comparison is a press story in its own right.
Phase 2
Accreditation launch. First call list: the 484 green venues already on the map. They're the warmest leads imaginable — they already said yes.
Phase 3
The London report. Press embargo. Data drop. Chain comparison. Borough rankings. The story that makes Buggy Smart the definitive source.
Beyond
National. Google Places API for data collection beyond London. National chains. Councils. The model scales anywhere a parent pushes a buggy.
Buggy Smart

"We called London's cafes.
So you don't have to."

Built by a London dad who got tired of guessing. Started it for my 2-year-old. Turns out every buggy-wielding parent in London needed it too.

This data should have existed a long time ago. I made it for myself. Now it does.

Continue from slide ?