Home · Platform · How it works
Platform · How it works

One AI call becomes one verifiable receipt.

A thin library sits between your app and the AI vendor. It captures each call, signs it with established cryptography in under a millisecond of CPU, and emits a receipt to your own store off the request path, so the AI response is never blocked and your application code is unchanged.

Architecture at a glance

It sits between your app and the AI, and changes nothing else.

Wrap the client once; every call is captured, signed, and written where you choose. The signing key never leaves your HSM, and no data is routed to a third party.

Your applicationcode unchanged
AskLedger SDKcapture · sign · chain
AI vendorOpenAI, Anthropic, …
The sequence, end to end

Signed once. Verifiable by anyone, any time after.

The value is in the two moments coming apart. The receipt is created the instant the AI decides. It is checked later, by someone who was not there and does not trust you, using nothing but a public key and the math.

1 · When the AI decides
Your applicationmakes an AI call, code unchanged
AskLedger SDKcanonicalize, hash, sign (Ed25519), chain
Signed receipt, into your ledgertamper-evident, never leaves your environment
🧾
the same receipt, months or years later
2 · Later, when someone asks
An auditor, regulator, or courtwho was not there, and does not trust you
Takes the receipt and your public keyno account, no call back to AskLedger
Verified ✓signature, chain, and timestamp all check out
The complete picture

From one AI call to evidence anyone can check.

The receipt is the foundation. One layer sits before it, stopping an irreversible action until an independent reviewer clears it, and two sit on top: bundling a whole workflow into one verifiable artifact, and checking the decision against the rules it was meant to follow. These are the same four layers described in the architecture section below, with the same numbering.

Layer 1

Pre-execution guardian

prevent
Proposed actionthe irreversible step
Independent verdictsigned under the reviewer's own key
Bound to the actionapprove A, run B is refused
Cleared or blockedbefore anything happens
Layer 2

Cryptographic integrity

prove
Capturethe AI call
CanonicalizeRFC 8785
Hash & signSHA-256 · Ed25519
Chainper-tenant
Receipttamper-evident
Layer 3

Execution history

trace
Many receiptsa workflow or agent run
Merkle root+ inclusion proofs
Evidence bundleone verifiable artifact
Layer 4

Rule-based assurance

assure
Rules in forcepinned by hash at decision time
Checkeda bounded rule check, not a proof
Gradedthe L0 to L3 assurance ladder
Travels with the receiptanswer and its evidence, together
Verify

Anyone can check it, independently

Signature
Chain link
Bundle inclusion
Timestamp
Free, no account, works even without us

Where each layer actually stands: all four ship in the open SDK today and are exported from its public API, and one runnable example walks a single action through every one of them. Layer 2 is the most hardened and the most used, and it is what the public verifier checks. Layers 1, 3 and 4 are newer and are being exercised with early users, so treat them as production-ready code with less mileage than Layer 2, not as roadmap. Two honest limits: AskLedger records and carries correctness evidence, it does not itself perform formal verification, and Layer 4's rule check is a bounded comparison of recorded values against recorded rules, which is not a mathematical proof and is labelled as a rule check in the receipt.

How it works

Three primitives. Cryptographic guarantees.

An independent verifier ships in every SDK. No new cryptography: every guarantee rests on published, reviewed RFCs. What those guarantees cover is integrity and authorship since signing, not whether the decision itself was right.

01

Canonical hashing

RFC 8785 gives every receipt one deterministic byte representation. The SHA-256 of those bytes is the receipt_hash. Every SDK produces the same canonical bytes and the same SHA-256 for the same input, which is exactly what our shared cross-language conformance vectors cover. Signed-receipt vectors are not frozen yet, so cross-language signature checking is not something we claim as proven.

02

Per-tenant hash chain

Each receipt's previous_receipt_hash binds it to the one before. Alter any historical receipt and every later verification fails. Truncating the chain is a different attack: detecting it requires publishing periodic Merkle roots somewhere outside the environment that issues the receipts. The Merkle primitives and RFC 3161 timestamping ship today; the connector to an external transparency log does not, so until you publish roots externally the chain is tamper-evident against a third party but not against whoever holds the signing key.

03

HSM-backed signatures

Ed25519 over the canonical bytes, with the private key held in AWS KMS, Azure Key Vault, GCP KMS, or a PKCS#11 HSM so signing happens without the key being exported. Check Ed25519 availability for your provider, region and tier before you design around it, since support varies. Optional RFC 3161 timestamps anchor each signature to absolute time, which is what lets a signature survive a later key compromise.

The architecture

Five layers: prevent, prove, then govern.

Four technical layers are the proof engine. They prevent the wrong action and prove what happened, how, and why, every one cryptographically verifiable and each optional. A fifth layer is the program built around that engine. It turns the proof into governance, compliance, and business impact you can put in front of a board, with one rule that keeps it honest: every number is proven against signed evidence, never just claimed.

1

Pre-execution guardian

Prevents the wrong action. Before an irreversible step, an independent reviewer signs a verdict bound to that exact action. Approving one thing and running another is rejected, high-risk actions can require several reviewers, and the verdict itself is recorded.

2

Cryptographic evidence

Proves what happened. A signed, tamper-evident receipt for every AI action, linked into a per-tenant hash chain. Verify a single receipt, or an entire ledger, with a public key alone.

3

Execution traceability

Proves how the process ran. Multi-step agent runs leave a linked graph of receipts that can be deterministically reconstructed and verified end to end, so a dropped or reordered step is caught.

4

Rule-based assurance

Proves why the decision was sound. The governing policy is recorded and checked against the decision, and every receipt carries an assurance level from Declared to Anchored, so a verifier knows exactly how strong the evidence is.

Layer 5 wraps all four
Layer 5The program around the engine

Responsible AI enablement and compliance by design

Helps you adopt, govern and scale it, and measure business value against signed evidence. The four technical layers make every action verifiable. Layer 5 turns that into an operating model: an institutional governance framework, pre-built rule packs mapped to the frameworks your regulators enforce, guided enablement, and business impact measured against a signed baseline. Said precisely, because this is where vendors usually overreach: signing a baseline and a later measurement makes those numbers tamper-evident and attributable, so nobody can quietly revise them after the fact. It does not make them true. Whether a saving was caused by the change is a judgement about your business, and we do not claim the cryptography settles it. Layer 5 is delivered as a service engagement, not a library call.

Governance frameworkPolicies, processes and best practices that embed accountability, with a named owner for every AI system in production.
Pre-built compliance rule packsReady-to-use templates for RBI, the EU AI Act, ISO 42001 and more, that run as Layer 4 assurance checks and are recorded on the receipt.
Rapid onboarding and enablementQuick-start packages, training and guided implementation to go from pilot to production in 90 to 120 days.
Business impact, measured not assertedCost and usage measured against a signed baseline, so the figures are tamper-evident and attributable. Tamper-evident is not the same as true, and causation stays a business judgement.
Ongoing supportOptional managed services for monitoring, updates and continuous compliance.
The difference

A log is a claim. A receipt is evidence.

A fair comparison, because an unfair one is easy to take apart. Well-run vendor logging is better than this table used to give it credit for: on WORM storage with object lock it is not editable, and retention is a policy setting on both sides. The real difference is narrower than "mutable versus immutable", and it still matters.

 
Vendor logs & dashboards
AskLedger receipts
Tamper-evidence
Depends on how the store is configured
A property of the record itself
Who can verify it
Whoever the platform grants access
Anyone, with a public key
Detecting a single edit
Needs trust in the store's controls
Verification fails on the changed record
Works across AI vendors
Siloed per platform
Vendor-neutral, one format
Detecting deletion or truncation
Needs trust in the store's controls
Chain gaps show, and external anchoring is required to catch wholesale rewriting

Where the honest limit sits: receipts live in your store, so you can delete them too. A hash chain makes a missing link visible, but an issuer who re-signs an entire chain can only be caught if Merkle roots were published somewhere that issuer does not control. That connector is not built yet, so we do not claim the property it would give us. See what a receipt does not prove.

See it in your language.

Wrap your AI client and ship a receipt in one import: TypeScript, Python, Go, Rust, or Java.