Multi-agent AI pipeline · Claude + Gemini

Land interviews
on autopilot.

A multi-agent resume pipeline that extracts JD keywords, rewrites your resume, and scores its keyword coverage — targeting 95%+ on Greenhouse and 98%+ on Workday.

Example:
Claude Sonnet 4.6Gemini 3.5 FlashATS Scoring LoopPDF + DOCX ExportWorkday-Strict
Why Relay

Built for scale and precision.

Five AI agents and an export step, tuned for Greenhouse and Workday, with standard formatting for everything else.

5
AI agents
Claude + Gemini
98%
Workday keyword target
Relay's own scoring
1–3m
Typical runtime
End-to-end
3×
Scoring attempts
Best version kept

Tuned For Greenhouse And Workday

Greenhouse≥ 95%

Exact token match

Workday≥ 98%

Ultra-strict parsing

LeverStandard

Generic formatting

iCIMSStandard

Generic formatting

Claude
Gemini
Next.js
Supabase
Tailwind CSS
FastAPI
Python
WebSockets
Claude
Gemini
Next.js
Supabase
Tailwind CSS
FastAPI
Python
WebSockets
The Pipeline

Five AI agents. A few minutes.

Watch the relay. Each agent hands off to the next.

JD Overview
Company · role · seniority
Gemini
Token Extract
Keywords & skills
Claude
Resume Writer
Per-job rewrite
Claude
ATS Validator
Score & retry
Claude
Resume Review
Second opinion
Gemini
DOCX / PDF Export
Supabase storage
Export
Claude Sonnet 4.6
Gemini 3.5 Flash
Typical runtime: 1–3 minutes
The Product

A dashboard built for throughput.

Submit jobs, watch the live pipeline, grab your resume. Everything in one place.

9:41
📶🔋
R
Relay
Dash
Recent Jobs
Backend Engineer
99%
Northwind Labs
Frontend Engineer
99%
Cedar Commerce
ML Engineer
99%
Helix Research
Features

Every stage has one job.

Five AI agents and an export step in a coordinated pipeline.
JD Parsing, Token Extraction, Writing, Validation, Review, Export.

Intelligent JD Parsing

Gemini extracts company, role, seniority, and a structured overview from the job description text you paste.

Exact Token Extraction

Claude mines must-have keywords, skills, and phrases from the JD — preserving exact plural/tense to beat strict ATS parsers.

Per-Job Resume Writing

Claude rewrites your resume for the target role. Forbidden verbs are blocked. Bullet realism rules enforced.

ATS Validation Loop

Claude scores the generated resume against the JD keywords and sends feedback to the writer — up to 3 attempts, keeping the best-scoring version.

Reviewer

Second-opinion pass from Gemini catches tone issues, redundancy, and weak phrasings after the main write.

Clean PDF and DOCX Export

PDF on every plan, DOCX on Standard and Pro, with plain formatting that applicant tracking systems read cleanly.

Why It Works

Precision engineering, not prompt hacks.

Every design decision is deliberate. No magic. Just careful orchestration of the best models for each job.

Multi-model

Right model for every phase.

Claude Sonnet 4.6 handles writing, token extraction, and validation — where rule-adherence matters most. Gemini 3.5 Flash handles JD parsing and post-write review — where breadth of understanding wins.

Claude Sonnet 4.6
3 stages
Gemini 3.5 Flash
2 stages
Pipeline timeline
JD Parser
Token Extract
Resume Writer
ATS Validator
Resume Review
Export
JD Parser + Token Extract run in parallel — Phase 0
Speed
Typically 1–3 minutes.
< 3m
Target
Workday keyword target.
98%
Security
Hardened against injection.
4-Layer
Export
Plain, ATS-friendly files.
PDFDOCXPlain
ATS Targets

Tuned to each platform's strictness.

Relay scores keyword coverage itself and holds each platform to its own target. These are Relay's scores, not numbers Greenhouse or Workday display.

Greenhouse

greenhouse.io

≥ 95%

Target

Standard exact token matching

  • Exact keyword match on JD tokens
  • Standard section headers enforced
  • Bullet realism & verb seniority
  • Up to 3 scoring attempts

Workday

myworkdayjobs.com

≥ 98%

Target

Strict matching mode

  • Exact plural/singular matching
  • Strict verb tense enforcement
  • Canonical date formatting
  • Standard section headers only
Illustrative Example

Generic LLM Draft vs. Relay Tailored Output

Relay score: target met98% Match
  • ✓100% exact token match with exact plural & tense preservation
  • ✓Canonical Workday headers & standardized date formatting
  • ✓Enforced action verbs ("Architected", "Deployed", "Optimized")
Security First

Built to resist
prompt injection.

Your profile and job description pass through four layers of defense on their way into the resume writer, so no single check is the only line of protection.

01
Pydantic Input Validation
Length caps, structural checks, and suspicious-keyword warnings at the API boundary.
02
XML Entity Escaping
Profile and job-description text is escaped before it is placed into the resume writer's prompt.
03
USER_DATA Boundaries
Tagged markers tell Claude to treat the block as data, not instructions.
04
Constrained Output Format
System prompt enforces strict output tags, limiting injection blast radius.
Validation
Escape
Boundaries
Output
4
Defense layers
JWT
Every account route
RLS
Row-level isolation
How It Works

From job description to tailored resume in minutes.

01

Paste the JD

Paste the job description text and pick Greenhouse or Workday. Jobs you save from Job Monitor arrive with the posting and platform already filled in.

02

Agents go to work

JD overview → token extraction → resume writing → ATS validation → Gemini review. All in parallel where possible.

03

Download your resume

PDF on every plan, DOCX on Standard and Pro, saved to your dashboard with the ATS report.

Pricing

Power your job search.

Every plan runs the same pipeline. Paid plans add throughput, DOCX export and control over the prompts.

Free
$0forever

Prove the value before committing.

  • 10 resumes / month
  • 1 parallel run at a time
  • Claude Sonnet 4.6 + Gemini 3.5 Flash
  • PDF export
  • Full ATS scoring loop
  • 25 spaces to organize jobs
  • Email support
Get Started Free
Most Popular
Standard
$15/ month

The full product. For active job seekers.

  • 200 resumes / month
  • 4 parallel runs
  • Claude Sonnet 4.6 + Gemini 3.5 Flash
  • Batch 20 jobs at once
  • 500 spaces
  • 15 GB storage
  • PDF + DOCX export
  • Advanced ATS reruns
  • Prompt view & guided chat
  • Version compare
  • 2 resume profiles
Launching soon
Pro
$39/ month

Maximum throughput and control.

  • 300 resumes / month
  • 10 parallel runs
  • Claude Sonnet 4.6 + Gemini 3.5 Flash
  • Claude Opus in prompt chat
  • Batch 50 jobs at once
  • Unlimited spaces
  • Unlimited storage
  • PDF + DOCX export
  • Advanced ATS reruns
  • Prompt editing & versioning
  • Prompt view & guided chat
  • Version compare
  • 5 resume profiles
Launching soon

No credit card required for Free. Standard and Pro open for purchase soon.

FAQ

Questions, answered.

How is this different from ChatGPT rewriting my resume?
ChatGPT gives you one shot with no validation. Relay runs a dedicated ATS validator after every write and sends its feedback back to the writer — up to 3 attempts, keeping the best-scoring version. It also enforces rules like forbidden verbs, canonical date formats, and exact plural/tense matching — things a general chatbot won't track. And since one run takes 1–3 minutes, Relay's parallel execution means you can queue up multiple applications while the first one finishes.
Which LLMs does it use?
Claude Sonnet 4.6 handles token extraction, resume writing, and ATS validation. Gemini 3.5 Flash handles JD parsing and post-write review. Each model is used where it performs best — Claude for rule-strict writing, Gemini for broad understanding.
What's the difference between Greenhouse and Workday modes?
Greenhouse mode targets ≥95% with standard exact-token matching. Workday mode targets ≥98% and is stricter about exact plural/singular forms and verb tense, and uses only standard section headers. Both targets are Relay's own keyword-coverage scores, not numbers Greenhouse or Workday display.
Is my data safe?
Every account API route requires a signed-in session; only health checks, the contact form and the payment webhook are public. Your profile and job description go through four layers of defense on the way into the resume writer: Pydantic validation, XML escaping, USER_DATA boundary markers, and a constrained output format. Row-Level Security keeps your data separate from other users'.
Do you store my resume?
Your profile and generated files are stored in Supabase, and only your signed-in account can reach them. You can delete individual jobs and their files yourself. To delete your whole account, email support@relayresume.com and we'll remove it and its stored documents.
Can I customize the prompts?
Standard users can view prompt templates and use guided prompt chat. Pro users can fully edit every prompt template, access the full prompt history, and version-restore previous prompts.
Why pay for Relay when I can use ChatGPT?
ChatGPT is a text tool. Relay is a workflow system. Relay handles ATS scoring, retry loops, multi-step pipelines, company/role organization, parallel execution, and persistent output storage. You spend less time prompting and waiting — Relay runs in the background while you keep applying.

Ready to stop
writing resumes?

Let five AI agents do the heavy lifting. You focus on the interview.