Why this site, and not the obvious alternatives
We’re not a law firm and we’re not a chatbot. Here is what we are and why that matters for offer-letter review.
Why a lawyer is not always the right call first
Why an employment lawyer is the wrong tool here
An employment lawyer is the right call when you want to negotiate a counter-offer or you’ve already been wronged. Asking one to read your offer letter is $400 to $700 an hour, takes a week, and produces a verbal “looks fine” that you can’t bring to HR. Offer-letter review is a checklist job: scope of role, base + variable + equity mechanics, vesting schedule and cliff, IP and inventions assignment, non-compete enforceability in your state, arbitration carve-outs, post-termination obligations. We’ve signed offer letters. We’ve negotiated them. We tell you, in writing, what’s standard, what’s aggressive, and what’s worth pushing back on. Use the lawyer once you know what to ask for.
Why ChatGPT is not a substitute
Why ChatGPT is the wrong tool here
Offer-letter language is built to look generous and is not. The IP assignment on page 2 may sweep in side projects you started before you joined; the non-compete on page 4 may be unenforceable in California, partly enforceable in New York, and fully enforceable in Texas. A chatbot doesn’t track FTC’s 2024 non-compete rule, the state-by-state variations after the rule was struck down, or which of your inventions actually fall under prior-art carve-outs. We’ve signed offer letters with all these clauses. The chatbot has read about them.
How we build quality in
A quality system, not a prompt
Borrowed from manufacturing: a serious quality program is not “we tried hard.” It is layered checks, a measured defect rate, and a patch loop that improves with every report.
Document parse and anchor map
Every line indexed before any analysis runs
Issue detection, layered
Pattern checks for IP assignment scope, non-compete enforceability, equity vesting cliffs, arbitration carve-outs, at-will carve-outs
Citation verification
Every claim tied back to a line in your file
Plain-English translation
Bound to the source, no rewording drift
Report assembly and final check
No claim ships unless every prior stage passed
Document parse and anchor map
Every line indexed before any analysis runs
Issue detection, layered
Pattern checks for IP assignment scope, non-compete enforceability, equity vesting cliffs, arbitration carve-outs, at-will carve-outs
Citation verification
Every claim tied back to a line in your file
Plain-English translation
Bound to the source, no rewording drift
Report assembly and final check
No claim ships unless every prior stage passed
Reader flags something? We patch the stage, not the report. Every reader after benefits.
Our patch loop
Every flagged issue runs the same five steps. The loop is what raises the floor — not heroics on any single report.
- 01
Flag
A reader reports an issue. Anything: a missed clause, an unclear translation, a number that does not match the source.
- 02
Diagnose
We trace it back to the part of the system that produced it — the prompt, the schema, the merge logic, the rendering layer.
- 03
Patch
We change the system, not just the one report. A new guardrail, a sharper question, a stricter check.
- 04
Verify
We re-run the patched system against the original input and against a regression set, so the fix does not break anything else.
- 05
Ship
The patch goes live for every future reader. The bar moves up once and stays up.
OUR COMMITMENT
If you find a defect, we fix the system. Then we tell you what we changed.
Every flagged issue feeds the patch loop. Every patch raises the floor for the next reader. That is the only quality program worth running.