Vienna Calling

Slide 1Seven AI Patterns

• Zoom Meeting ID
• 503 616 9422

Vienna is calling. Answer the damn phone

Matt Navarre · navarre.ai · free classes every Thursday

Slide 2About Me

• Passionate trainer, Expert developer
• Founded 3 companies
• FBA Awards, conference sessions, meetups, YouTube vids
• ClarisTalk AI podcast with Cris Ippolite
• 20 years of FileMaker Podcasts

Slide 3My One Request

• Make A free appointment with me to talk about AI in your solutions
• www.navarre.ai

Matt Navarre · navarre.ai · free classes every Thursday

Slide 4Agenda

• Hello World – Invoice Summary
• AI Models – Which, when and Why?
• fmSearchResults AI
• Basic Semantic Search
• ‘Enriched’ Search
• Error Finder – on Load
• Reporting – Can AI do math?
• Image Description (and PDF and URL)
• Building & iterating WebViewer layouts

Slide 5‘Perform Semantic Find’

Perform Semantic Find + Insert Embedding ship out of the box.

Great at

Quietly bad at

• Paragraphs of prose
• Product descriptions, notes, resumes
• Support tickets, meeting transcripts
• “What does this mean?” lookups

• Names (“Bob Smith”)
• Company names and addresses
• SKUs, short codes, tight labels
• Dates, prices, numeric ranges

Most data in a FileMaker solution lives up here ^ ^

Vienna Calling :: Navarre Training :: Navarre AI

Slide 6Semantically clever. Numerically blind.

THE HONEST LIMIT

Meaning, similarity, paraphrase

“law office audit” matches “Financial Audit Preparation Law Office” because the WORDS mean similar things.

Dates, amounts, ranges, exact strings

“Projects in Q2” vs a due-date of 2026-05-14 – a vector will not know those are the same thing. Numbers are not meanings.

Right tool rule:

semantic search for meaning + a plain WHERE clause for dates and amounts.

Stop trying to make one tool do both. That's the #1 mistake I see with new FileMaker AI work.

Slide 7Default Config

QUERY

DATABASE HAS

“Robert Smyth”

Bob Smith

Slide 8Enrich & Embed the data

STORED DATA

GENAI

ENRICHED TEXT

EMBED → STORE

Bob Smith

Generate variants

• Bob Smith
• Robert Smith
• Smith, Robert
• Bobby / Rob
• Smyth / Smithe

[0.13, -0.44, 0.88 ...]

SYSTEM PROMPT · person

“Generate realistic name variants for use in a semantic search index. Always include: the original name, LastName-FirstName form, accent-free spelling, common nicknames or diminutives, transliteration variants if relevant. Return a plain text list – one variant per line.”

Everything goes into the embedding. The record side is now fat with signal.

Slide 9Enrich & Embed the Query :: Set to Set Search

ENRICHED RECORD

ENRICHED QUERY

• Bob Smith
• Robert Smith
• Smith, Robert
• Bobby / Rob / Robb
• Smyth / Smithe
• ABC Technology
• bob@abctech.com

• Robert Smyth
• Rob Smyth
• R. Smyth
• Smyth, Robert
• robertt@abc-tech.com
• 237 More Park Dr, CA
• Alphabet Tek?

MATCH

Orthogonal variants meet in the middle. Typos, nicknames and transliterations fall on the same point in vector space.

Slide 10Expand to companies, projects, products, etc.

ENTITY → COMPANIES

WHAT WE EMBED

REAL-WORLD MATCH

User types:

• Original org name
• Abbreviations & acronyms
• With / without suffix
• List of staff names
• Project description
• Invoice Description
• Product info

PA Family Law

Finds:

Pennsylvania Divorce Resources

ACME secondary office update project

A C M E Satellite Lighting & Ergonomics update

Slide 11Teach the index what “cheap” means

ENTITY → PRODUCTS

Users search “cheap red shoes.” The database stores $39.99 / crimson / Nike.

PRICE TIERS

COLOR FAMILIES

CATEGORY SYNONYMS

• Shoes:
• < $50 → cheap, budget
• $50–150 → mid-range
• > $200 → luxury, premium
• Cars:
• < $20k → basic, economy
• > $50k → luxury, flagship

• Red →
• crimson, cherry,
• cardinal, burgundy,
• wine, garnet, brick,
• tomato, rose, maroon
• Silver → platinum,
• ash, pewter, titanium

• Shoes →
• sneakers, trainers,
• kicks, running shoes
• SUV →
• crossover, 4x4,
• sport utility

“Cheap” is not a price. It's a category-relative judgment. Bake that in at write-time.

Slide 12Re-enrich and re-embed

• Scheduled or
• triggered script

• Re-embed &
• store

Re-enrich

Nightly / weekly

Fresh variants

Insert Embedding

Slide 13Gen + Embed cost: basically free

~100

small

tokens in

tokens out

Dumb embed is fine

the search string + a compact system prompt

• gpt-4-mini, haiku, local models.
• No frontier needed.

5–10 name or query variants