What does AI
say about you?
In 10 seconds, see the verbatim answer an AI agent returns when a recruiter asks about you. Then see what changes when it has your Open-Shadow profile as context.
New York, NY · English · French
Jordan T. Smith
Full-Stack Engineer & OSS Contributor
Currently at
Stripe
Senior Software Engineer · 2022–Now
Open to opportunities
Remote · EU/US · Full-time
About
Building developer tools and distributed systems at scale. 8+ years shipping product across fintech and climate-tech. Passionate about open protocols and machine-readable data.
Skills
2022 – Present
Senior Software Engineer
Stripe
New York, NY
Led the redesign of the payment intent reconciliation pipeline, reducing P99 latency by 62%. Authored the internal TypeScript SDK used by 40+ teams. Mentored 4 junior engineers through structured bi-weekly 1:1s.
2020 – 2022
Software Engineer
Watershed
San Francisco, CA
Built the emissions data ingestion layer from scratch, processing 500M+ rows/year across 30 supply-chain data sources. Designed the schema that became the foundation of the public API.
2018 – 2020
Frontend Engineer
Alan
Paris, FR
Shipped the claims management dashboard used daily by 200+ ops agents. Reduced form-submission errors by 38% through inline validation redesign.
Education
M.Sc.
Computer Science
École Polytechnique
2018
Project · 2024
Rust · Postgres · WALpg-stream
Zero-copy logical replication consumer for Postgres. Streams WAL events as structured JSON with sub-millisecond lag. 1.4k GitHub stars.
Project · 2023
TypeScript · JSON Schema · Zodllms-schema
Open spec + validator for the llms.txt talent profile format. Powers structured extraction for 3 commercial AI sourcing tools.
Contact
inlinkedin.com/in/jordan-t-smith
@••••@•••.com
ghgithub.com/jordan-t-smith
Native indexing supported by
Built on the llms.txt spec.
How it works
From PDF to protocol in under a minute.
Drop your LinkedIn export. We hash it, structure it, publish it. One URL, three endpoints — one for humans, two for agents.
Upload & anchor
Drop your LinkedIn PDF. We hash it on upload — the cryptographic fingerprint anchors your profile to a real document at a real moment. Edit later as you wish; the original source stays verifiable.
linkedin_export_2026.pdf
sha256:eb3cc1a7…d93e8c
Extract & structure
Our LLM reads the PDF and emits your structured llms.txt layer and Bento grid simultaneously — no free-form rewrites.
name:Jordan T. Smith
headline:Full-Stack Engineer
skills:TypeScript,React,Rust
role:Sr. Engineer@Stripe|2022–Now
llms-full:/jordan-t-smith/llms-full.txt
Publish
Ship one URL. Three endpoints: a Bento for humans, a public llms.txt, and a gated llms-full.txt for verified recruiters.
/Bento · humans/llms.txtpublic/llms-full.txtgated · TollBitOne file in. One URL out. Read by every human and every agent.
Agents are already sourcing. Without you.
AI recruitment tools have quietly replaced human sourcers for first-pass screening. Your LinkedIn PDF isn't in any of their databases — and you don't know it.
AI agents are the new gatekeepers — and you don't exist to them.
Sourcing agents don't scroll LinkedIn. They query structured endpoints. No llms.txt, no match — you're skipped before a human ever sees your name.
senior rust engineer · Paris · openGET /in/jordan-t-smith
→ 403 · auth required
fallback: pdf parse
→ partial · 3 fields missing
GET /jordan-t-smith/paris/llms.txt
→ 200 · 142 tokens
score: 89/100 · match
contact verified ✓
senior rust engineer · paris2 results · grounded in machine-readable profiles
Jordan T. Smith
Sr. Engineer @ Stripe · Rust · Postgres
89
/100
Clément Roux
Staff @ Doctolib · Rust · distributed
84
/100
Verified talent, ranked. No more ghost profiles.
Shadow-Badge anchors every profile to a real source PDF via cryptographic hash. Extraction is faithful — no LLM rewrites — and any candidate edits are clearly authored by them, never silently inserted by AI.
Shadow-Badge
Faithful extraction + cryptographic provenance
answer difference
The same model returns a cold, pattern-matched blur without your profile — and a precise, grounded, current brief with it. Two answers to the same question, side by side.
Before & after
Same model. Same question. Two different answers.
Here's what Gemini says about a typical engineer — first cold, then when it has their Open-Shadow profile attached as context. An illustrative example; run a real one on yourself above.
Same model, no context. Whatever Gemini can stitch together from training data.
Jordan T. Smith
Jordan T. Smith appears to be a seasoned technology professional, likely with a background in full-stack development. Based on common name patterns, he may have experience across the US tech ecosystem, possibly including startups and established firms.
His toolkit probably covers the mainstream stack — JavaScript, Python, cloud platforms, maybe some modern frameworks. He likely has over a decade of experience and may have moved into senior IC or leadership roles.
Without more specific information, I can't confirm his current employer, recent projects, or specific achievements. There are likely several professionals with this name — further disambiguation would help.
Pattern-matched guesses. A plausible-sounding blur. Exactly what recruiters get today.
Same model, same question — now with Jordan's machine-readable profile attached.
Jordan T. Smith
Jordan T. Smith is a Senior Engineer at Stripe (since 2022) based in New York, specializing in Rust and distributed systems. Over 11 years in the industry, he's moved from mobile (iOS at Square) to infrastructure at scale.
| Area | Specifics |
|---|---|
| Current role | Sr. Engineer @ Stripe · NYC · since 2022 |
| Core stack | Rust, Postgres, Kafka, TypeScript |
| Notable impact | Led Payments Core Rust migration — p99 latency −40% |
Beyond the core platform work, he maintains two open-source Rust crates (tokio-timeout, query-span) and has spoken at RustConf 2024 on latency budgeting. Distinctive profile: infra depth combined with a systems-design clarity rare at his level.
Every claim grounded in Jordan's Open-Shadow llms.txt. No invention, no pattern-matching.
Now see what it says about you.
Same setup. Your name, your context, verbatim AI response.
Before you claim your slug.
The real questions — on data, privacy, legal, and price.
What is llms.txt?+
A plain-text file that describes you in a format AI agents can read instantly — no PDF parsing, no HTML scraping. It looks like this:
name:Jordan T. Smith
headline:Sr. Engineer
skills:TypeScript,React,Rust
Think of it as your robots.txt, but for your career.
Is it free?+
Yes. Upload your PDF, get your profile, share your link — all free. Recruiters pay micro-fees via TollBit when their agents access the premium llms-full.txt layer. Candidates never pay.
Where is my data stored? Can I delete it?+
All profiles live in an EU-region Supabase instance (Frankfurt). Your data is yours — export or delete any time from your dashboard. Deletion is full: profile row, source PDF, and hash chain removed. GDPR-compliant by design, not retrofit.
Is my contact info public?+
You control every field individually. Each contact field can be set to one of three modes:
Phone, email, and custom links each have their own toggle. Nothing is exposed unless you opt in.
Can I stay anonymous?+
Yes. Shadow Mode hides your name, photo, and contact info on the public Bento page. Your llms.txt is served as name:anonymous. Only verified recruiter agents with a TollBit token can access your routing data in the gated layer.
What if my name is common? Can someone else take my slug?+
Slugs are city-scoped: /jordan-t-smith/new-york and /jordan-t-smith/paris coexist. Within a single city, first-claim wins, but collisions are resolved by matching the source PDF hash and LinkedIn URL. Claim early if you're worried.
How do AI agents actually find profiles?+
Every profile publishes a llms.txt at a predictable URL. Agents discover profiles two ways:
- Direct crawl — the agent fetches /name/city/llms.txt
- Semantic search — the API matches a query against pgvector embeddings and returns ranked profiles
Both return pure structured data — zero HTML to parse.
Will ChatGPT or Gemini suddenly know about me after I upload?+
Not exactly — and understanding why is the whole point. Here's what actually happens:
- Direct fetch — When a recruiter's agent fetches your URL directly, it gets your verified profile instantly. That's the surface you control.
- Cold query — When a recruiter asks ChatGPT cold ("who is Marie Dupont?"), the model answers from training data — which won't include you for months, even years. That's the gap your side-by-side proves.
- Live retrieval — Increasingly, recruiter tools chain LLM + live web fetch — they query the model and fetch your llms.txt at the same time, then merge. As more agents adopt llms.txt, more answers get grounded in your data.
The goal isn't that AI suddenly knows you. The goal is that when an agent does look you up, your truth wins — not the model's hallucination.
What does this cost my team?+
The public llms.txt layer is free — any agent can read it. The gated llms-full.txt is metered via TollBit at roughly $0.002 per crawl, with volume discounts above 100k reads/month. No seat licenses, no minimums. Pay only when your agents read.
What does the Shadow-Badge guarantee?+
It means the profile has cryptographic provenance — anchored to a real PDF the candidate uploaded. Specifically:
- ✓ Profile anchored to a real source PDF via cryptographic hash
- ✓ Source hash is stored — proof the document was real at a real moment
- ✓ Faithful extraction at parse time — no LLM rewrites; later edits are explicitly authored by the candidate
Agents see the full provenance trail — and the candidate's edits are clearly theirs, never AI hallucination.
Won't LinkedIn block or sue you for this?+
No. Open-Shadow never scrapes LinkedIn. You initiate the export from LinkedIn yourself and upload the PDF — under hiQ Labs v. LinkedIn (9th Cir. 2022) that's your data to share. We don't query LinkedIn APIs, reverse-engineer, or proxy. The wedge is that you own the document.
Still missing something? email us.
Take control
of what AI says about you.
Upload your PDF, publish your llms.txt — and decide what gets said when an agent looks you up.