Your agent said
it checked its work.
Did it?

Receipts runs AI reasoning through a deterministic interpreter. Every citation checked against source. Proof, not promises.

No AI grading AI. The interpreter does the math.

For teams using AI agents to make decisions, produce work, or cite sources — a verifiable audit trail of what was actually checked.

Get the skill
Q3 earnings review
23 May 2026
09:14:22
source-state
verified
claim-basis
verified
normative
2 required
inherited
1 statement
rationales
2 with because
01verified-against-10K-filing
02revenue-matches-SEC-source
cite "94.9 billion" from sec-filing
measure 94.9 from sec-filing within 0.5
research
cite "quarterly guidance raised" from sec-filing
substring not found in source "sec-filing"
1about "Q3 earnings review"
2remember a source called sec-filing with "Revenue was $94.9 billion..."
3starting "2025-07-01" require revenue-reported is above 0 because "SOX"requiredactive
SOX compliance
4inherited require data-source is equal to "10-K" from compliance-agentrequiredinherited
5cite "94.9 billion" from sec-filing
6measure 94.9 from sec-filing within 0.5
7cite "quarterly guidance raised" from sec-filing
Reading the receipt — verb key
citeDid the AI use words that actually appear in the source?
measureIs the number close enough, or did it drift?
requireEnforce a rule — halt if it's not met.
inheritedThis rule was carried forward from a prior session.
startingThis rule takes effect on a specific date.
becauseThe rationale — why this check exists.
aboutWhat this contract is about. Metadata, not executable.

The entire AI industry is trying to solve hallucinations with more AI.
We used a 58-word interpreter.

Receipts doesn't ask the agent if it was honest. It checks. The interpreter runs every citation against its declared source — substring match, deterministic, reproducible. An AI cannot fake a passing cite.

Receipts doesn't judge your work. It judges the AI's. Every failure in a receipt is the model's mistake, verified against the source you declared. The receipt protects the analyst, not the vendor.


Liminate
A prose-as-syntax language designed from the human end

Every language in history was designed by programmers. This one wasn't.

Liminate programs are English sentences. The language has a bounded vocabulary that stays small permanently — any addition must pass the word salad test: can a non-programmer read a sentence using this word and understand what it does?

58 reserved words · 21 verbs · 22 connectives · deterministic execution

Session contracts are the artifact.

At the end of a working session, the AI agent produces a .limn file — a structured record of what it verified versus what it inferred, what decisions were locked, what questions remain open. Both human-readable and machine-checkable.

remember a string called source-state with "verified"
remember a list called tracked-decisions with "none"
add "use-fastapi-not-flask" to tracked-decisions
cite "FastAPI provides automatic Swagger docs" from framework-comparison

when source-state is equal to "unscanned"
  show "HOLD: scan the repo before making claims"

Receipts is where you scan the result.

Submit the contract. The interpreter runs every line. Citations checked by substring match — not by another model, not by embeddings, not by vibes. Green check or red X. The proof travels with the claim.


Your agent writes the contract.
The interpreter checks it.
You read the receipt.

1

Install the skill

Drop the session contracts skill into your AI agent. Works with Claude, ChatGPT, Cursor, Codex — any agent that accepts a system prompt or SKILL.md file.

The skill teaches the agent to produce .limn contracts — structured records of what it verified, what it inferred, and what it decided. No code changes needed. One file.
2

Work normally

The agent produces a contract during your session. Every source it reads, every claim it makes, every decision it locks — tracked in the contract as executable prose.

The contract uses Liminate's 58-word vocabulary. cite checks text. measure checks numbers. require enforces rules. because attaches rationale. The agent writes it. You can read it.
3

Scan the receipt

Paste the contract or save it via API. The Liminate interpreter runs every line — deterministic, no model in the loop. Green check or red X.

The receipt shows reasoning state, tracked decisions, citation checks (pass/fail), warnings, session corrections, and the annotated source. Share it, attach it to a PR, send it to compliance.
The skill is free and open source

The interpreter checks, not the model.

The Liminate interpreter runs cite statements as substring_check operations against declared sources. No neural network in the verification loop. If the text isn't in the source, the line fails. The check is the same every time. Think of it as checking the work by hand. Long division, not autocomplete.

The proof travels with the claim.

Every receipt is a permalink — source, inspection results, and verification state in one URL. Share it with your team, attach it to a PR, send it to compliance. The receipt is the record.

You can't vibe-code your verification layer.

Your verification layer cannot depend on the same probabilistic system it is meant to inspect. The barrier to building software is approaching zero — but the thing that checks whether the AI told the truth requires a proprietary interpreter, a bounded vocabulary, and deterministic execution. That's not something you spin up in Cursor on a weekend.

500claims verified · 50S&P companies · 4industries · 33concept substitutions · 58stale truths · 3sign reversals

SEC EDGAR 10-K filings. Real data. Deterministic verification. → See the case study


AI Governance
Verify what agents actually checked before outputs are relied upon.
Legal & Compliance
Attach source-backed receipts to sensitive summaries, claims, and decisions.
Marketing & Brand
Validate AI-generated claims, research summaries, and messaging inputs.
Engineering & Product
Attach verification receipts to PRs, specs, and agent handoffs.

Two kinds of people ship AI work
without knowing if it's grounded.

Verified organizational memory

Your agents cite sources, lock decisions, and accumulate commitments across sessions. Receipts gives your team an inspectable chain — and catches when one agent contradicts another.

  • Cross-contract coherence checking
  • Commitment tracking · reversal detection
  • Constitutional pinning for baselines
  • Narratia depth narrative
  • Shared inspection history

Trust what you shipped

You built something with Cursor, Claude, or ChatGPT. The agent said it checked its work. Receipts shows you whether it actually did — every citation traced, every claim inspectable.

  • Paste and run — nothing to install
  • Free tier with real verification
  • On-device narrative at zero cost
  • $0.25/receipt — no subscription needed
  • Save, share, revisit

The free tier works. Unlimited paste-and-scan. 10 saved receipts. Real verification, not a demo.


Pay for outcomes, not access

A receipt is a verified outcome. The pricing reflects that.

FREE$0
Unlimited paste-and-scan · 10 saved receipts · on-device narrative
PER RECEIPT$0.25
Everything in Free + unlimited saved receipts · no subscription · pay only when you save
INDIVIDUAL$5/mo
Unlimited saved receipts · cloud coherence checking · export history · API keys
NARRATIA coming soon$12/mo
Everything in Individual + Claude-powered depth narrative · semantic coherence · re-verify
TEAMS coming soon$39/mo + $12/seat
Narratia included per seat + cross-contract comparison · constitutional pinning · commitment tracking

The person affected must remain the author of their understanding.

Fifty-eight words. One interpreter.
One receipt.