AI matching platform
Work Transcendence
A knowledge graph of what a person knows, where every claim keeps the sentence that proves it, matched to real work requirement by requirement.
Visit the live productWhy a match should come with its evidence
Every hiring system produces a number, and almost none can explain it. A candidate is a 78 percent fit, nobody can say what the missing 22 percent is made of, and the number gets trusted or ignored depending on who happens to read it.
Work Transcendence keeps the evidence attached. A person talks to an agent about what they have done, or uploads a CV, and every skill, role, company and goal becomes part of a graph. Each item keeps the sentence it came from and the date it was said, so a claim is never separated from its source.
Matching then runs requirement by requirement. A percentage shows which claim met each requirement and which requirements nobody has met yet, so a candidate can see what to work on and a company can see exactly why someone ranks where they do.
The person stays in control of all of it. Quotes stay in the language they were said in, being visible in the pool is a choice, and everything can be exported or deleted at any time. A graph of what someone knows is theirs before it is anyone's product.
How it works
Tell it, or upload
Talk to the agent about what you have done, or upload a CV. It asks back where something is unclear instead of filling the gap with a guess.
It becomes a graph
Skills, roles, companies and goals, each tied to the sentence that proves it and the time it holds for. The interpretation can be rebuilt; the claims stay as they were said.
Get matched
A listing or a person is compared against the graph requirement by requirement, with the evidence for every match and every gap.
For companies
Describe a role in conversation, correct the extracted requirements, then see candidates ranked with the claims behind each percentage.
Built with
For your product
What this says about how we work
The hard part of an AI product is rarely the model. It is deciding what the system is allowed to claim and making every claim traceable to something real. That is the rule we hold our own website to, and it is the first conversation we have about any AI feature that puts a number in front of a customer.
Questions people ask
- What makes the percentage checkable?
- Each requirement shows the claim that met it, with the sentence and date it came from, and the requirements nobody has met are listed rather than hidden.
- Does it rewrite what people say?
- No. Claims stay as they were said. When the interpretation improves it is rebuilt from them, and the original sentences remain.
- Who owns the data?
- The person. Visibility in the pool is optional, and the account can be exported or deleted at any time. After deletion only anonymous statistics remain.
- What does it cost?
- It is free to start for people, with tokens to try the job hunt, and a company's first thirty days are free.
What we did on this one
- Backend development
- Frontend development
- Product design
More from Work Transcendence
- worktranscendence.comThe EU AI Act and hiringWhy recruitment AI is treated as high-risk from August 2026, and five questions to ask any vendor.Read it
- worktranscendence.comFour ways an AI screener misleads youAnd the one question that catches all of them, as a checklist you can use on any scoring tool.Read it
- worktranscendence.comHow a match is computed, and why we show the workingWhat happens between a listing's requirements and a person's claims, step by step.Read it
Your project
Build something like this
Get a preliminary budget, timeline and team shape for your product, or talk it through with the engineer who would deliver it.
Other projects
Monitoring SaaS
Server Inspector
Uptime, SSL, domain and API monitoring that tells you something broke before your customers do.
Email infrastructure
PigeonAtlas
Email sending for applications: an HTTP API and an SMTP endpoint, Resend-compatible, with your own DKIM key and newsletters that can never delay a password reset.
AI marketing workspace
Merlin Studio
An AI marketing workspace where strategy, brand knowledge and content live in one place, and a person approves the final version.
Keep going
Where to go next
- Read the case studiesChallenge, solution and measured outcome from delivered engagements.Continue
- Calculate project costA guided technical discovery that returns a budget range, timeline and team shape.Continue
- Book a strategy callForty-five minutes with the engineers who would actually build it.Continue
