DEV Community

João André Gomes Marques profile picture

João André Gomes Marques

Founder of Asqav. Building cryptographic governance for AI agents through signed, tamper-evident receipts for actions, policy decisions, result digests, and independent timestamps.

Joined Joined on  Personal website https://asqav.com

Education

Master in Cybersecurity

Work

Founder at Asqav

Self-attested vs independently verifiable receipts

Self-attested vs independently verifiable receipts

Comments
2 min read
The OWASP AI Exchange cites the Asqav compliance-receipts profile

The OWASP AI Exchange cites the Asqav compliance-receipts profile

Comments
2 min read
Out-of-process signing for high-assurance agent audit trails

Out-of-process signing for high-assurance agent audit trails

Comments
4 min read
Signed receipts for AI coding agents

Signed receipts for AI coding agents

Comments
4 min read
How Signed Agent Receipts Map to NIST, OWASP, and NSA Frameworks

How Signed Agent Receipts Map to NIST, OWASP, and NSA Frameworks

Comments
6 min read
Tamper-Evident Logs for AI Agents

Tamper-Evident Logs for AI Agents

Comments
6 min read
SDK 0.6.0: offline and air-gapped verification

SDK 0.6.0: offline and air-gapped verification

Comments
2 min read
One Receipt, Nine Regulators

One Receipt, Nine Regulators

Comments
3 min read
An IETF profile for AI agent compliance receipts

An IETF profile for AI agent compliance receipts

Comments
3 min read
Verify is not just true or false, granular outcomes on /verify

Verify is not just true or false, granular outcomes on /verify

Comments
2 min read
Every rejection leaves a trail, persistent log of rejected attempts

Every rejection leaves a trail, persistent log of rejected attempts

Comments
2 min read
Per-agent hash chain, with a verifier that re-derives

Per-agent hash chain, with a verifier that re-derives

Comments
2 min read
Govern AI agents from your CLI

Govern AI agents from your CLI

Comments
2 min read
ML-DSA receipts in COSE for SCITT transparency services

ML-DSA receipts in COSE for SCITT transparency services

Comments
3 min read
Audit-trail receipts you can verify offline

Audit-trail receipts you can verify offline

Comments
3 min read
Asqav TypeScript SDK is live

Asqav TypeScript SDK is live

1
Comments 1
3 min read
Portable Evidence Artifacts for AI Validation

Portable Evidence Artifacts for AI Validation

Comments
4 min read
Try asqav in 30 seconds

Try asqav in 30 seconds

Comments
2 min read
Governance metadata in A2A Agent Cards, shipping the superset

Governance metadata in A2A Agent Cards, shipping the superset

Comments
2 min read
Portable Trust for AI Agents

Portable Trust for AI Agents

Comments
3 min read
Trace Agent Actions Across Workflows and Kill Everything in One Call

Trace Agent Actions Across Workflows and Kill Everything in One Call

Comments
2 min read
Sign the intent, the decision, and the execution

Sign the intent, the decision, and the execution

Comments
3 min read
Trace agent actions across workflows and kill everything in one call

Trace agent actions across workflows and kill everything in one call

Comments
2 min read
Stop Replay Attacks on AI Agent Tokens

Stop Replay Attacks on AI Agent Tokens

Comments
2 min read
Stop replay attacks on AI agent tokens

Stop replay attacks on AI agent tokens

Comments
3 min read
Portable Scope Tokens: Verify Agent Permissions Offline

Portable Scope Tokens: Verify Agent Permissions Offline

Comments
3 min read
Replay What Your AI Agent Did, Step by Step

Replay What Your AI Agent Did, Step by Step

Comments
2 min read
Replay what your AI agent did, step by step

Replay what your AI agent did, step by step

Comments
3 min read
One-click compliance bundles for AI agent audits

One-click compliance bundles for AI agent audits

Comments
2 min read
Test AI agent governance without touching production

Test AI agent governance without touching production

Comments
2 min read
Test AI Agent Governance Without Touching Production

Test AI Agent Governance Without Touching Production

Comments
2 min read
One-Click Compliance Bundles for AI Agent Audits

One-Click Compliance Bundles for AI Agent Audits

Comments
3 min read
Sign the Intent, the Decision, and the Execution

Sign the Intent, the Decision, and the Execution

Comments
3 min read
Layer 1 is identity, Layer 2 is attestation

Layer 1 is identity, Layer 2 is attestation

Comments
3 min read
Add governance to DSPy pipelines

Add governance to DSPy pipelines

Comments
2 min read
Why your AI agent needs a .well-known discovery endpoint

Why your AI agent needs a .well-known discovery endpoint

Comments
2 min read
Add governance to Hugging Face smolagents in 4 lines

Add governance to Hugging Face smolagents in 4 lines

Comments
2 min read
SDK v0.2.9: Output Verification, Attestations, Preflight and Budgets

SDK v0.2.9: Output Verification, Attestations, Preflight and Budgets

Comments
3 min read
Scan MCP tool definitions for prompt injection before your agent calls them

Scan MCP tool definitions for prompt injection before your agent calls them

Comments 1
2 min read
Three tiers of enforcement for AI agents - strong, bounded, detectable

Three tiers of enforcement for AI agents - strong, bounded, detectable

Comments
2 min read
asqav-mcp is now on Docker Hub

asqav-mcp is now on Docker Hub

Comments
2 min read
Asqav vs Microsoft Agent Governance Toolkit - what is the difference

Asqav vs Microsoft Agent Governance Toolkit - what is the difference

Comments
2 min read
Why the E8 lattice is the perfect quantizer for KV caches

Why the E8 lattice is the perfect quantizer for KV caches

1
Comments
2 min read
Running 1M-token context on a single GPU (the math)

Running 1M-token context on a single GPU (the math)

Comments
2 min read
NexusQuant is now on PyPI, HuggingFace, and 9 awesome lists

NexusQuant is now on PyPI, HuggingFace, and 9 awesome lists

Comments
2 min read
Why attention-aware eviction beats random eviction (with data)

Why attention-aware eviction beats random eviction (with data)

Comments
2 min read
One line of Python to extend your LLM's context window 10x

One line of Python to extend your LLM's context window 10x

Comments
1 min read
The 12 approaches I tested before finding one that works

The 12 approaches I tested before finding one that works

Comments
5 min read
NexusQuant: compressão de memória para LLMs — guia prático

NexusQuant: compressão de memória para LLMs — guia prático

Comments
3 min read
Como comprimir o KV cache do seu LLM em 33x sem treino

Como comprimir o KV cache do seu LLM em 33x sem treino

Comments
3 min read
KV cache memory calculator: how much does your LLM actually use?

KV cache memory calculator: how much does your LLM actually use?

Comments
3 min read
How to benchmark NexusQuant on your own model

How to benchmark NexusQuant on your own model

Comments
3 min read
What I Learned Testing 12 Compression Approaches That Failed

What I Learned Testing 12 Compression Approaches That Failed

Comments
6 min read
The Math Behind E8 Lattice Quantization (with Code)

The Math Behind E8 Lattice Quantization (with Code)

Comments
6 min read
How Much GPU Memory Does NexusQuant Actually Save?

How Much GPU Memory Does NexusQuant Actually Save?

Comments
4 min read
How to deploy NexusQuant in production (and what's missing)

How to deploy NexusQuant in production (and what's missing)

Comments
4 min read
NexusQuant vs KVTC vs TurboQuant vs CommVQ — honest comparison

NexusQuant vs KVTC vs TurboQuant vs CommVQ — honest comparison

Comments
4 min read
NexusQuant benchmarks: every number, honestly

NexusQuant benchmarks: every number, honestly

Comments
5 min read
Longer contexts are easier to compress (not harder)

Longer contexts are easier to compress (not harder)

Comments
2 min read
Why E8 lattice quantization beats scalar quantization for KV caches

Why E8 lattice quantization beats scalar quantization for KV caches

Comments
2 min read
loading...