📰 Dev.to · João André Gomes Marques
Articles from Dev.to · João André Gomes Marques · 47 articles · Updated every 3 hours · View all reads
All
⚡ AI Lessons (12148)
ArXiv cs.AIDev.to · FORUM WEBDev.to AIForbes InnovationOpenAI NewsHugging Face Blog
Dev.to · João André Gomes Marques
1w ago
NexusQuant benchmarks: every number, honestly
When you build a KV cache compression system and plan to publish a paper, you face a choice: present...
Dev.to · João André Gomes Marques
1w ago
Longer contexts are easier to compress (not harder)
The common assumption: longer sequences are harder to compress because there's more information to...
Dev.to · João André Gomes Marques
1w ago
Why E8 lattice quantization beats scalar quantization for KV caches
Most KV cache quantization methods treat each number independently: round each float to the nearest...
Dev.to · João André Gomes Marques
1w ago
Compress your LLM's KV cache 33x with zero training
Running out of GPU memory at long context lengths? The KV cache grows linearly with sequence length —...
Dev.to · João André Gomes Marques
1w ago
5 open source tools for AI agent governance in 2026
AI agents are moving into production faster than governance tooling can keep up. Here are the 5 open...
Dev.to · João André Gomes Marques
1w ago
5 things your AI agent should never leak (and how to detect them)
AI agents handle sensitive data all the time. Most have zero controls on what gets passed to external...
Dev.to · João André Gomes Marques
1w ago
Add governance to Claude Desktop with an MCP server
If you use Claude Desktop with MCP tools, every tool call is unaudited. There is no record of what...
Dev.to · João André Gomes Marques
1w ago
Add governance to OpenAI Agents SDK in 3 lines
OpenAI Agents SDK has guardrails for input/output validation but no audit trail. Here is how to add...
Dev.to · João André Gomes Marques
1w ago
How to add tamper-evident audit trails to CrewAI agents
CrewAI is great for multi-agent workflows but has no built-in audit trail. If you need to prove what...
Dev.to · João André Gomes Marques
1w ago
We just launched asqav on Hacker News - quantum-safe audit trails for AI agents
Just submitted asqav to Hacker News: https://news.ycombinator.com/item?id=47665415 asqav is an...
Dev.to · João André Gomes Marques
1w ago
EU AI Act compliance checklist for AI engineering teams
The EU AI Act deadline for high-risk AI systems is August 2, 2026. If you are building AI agents,...
Dev.to · João André Gomes Marques
1w ago
AI agent governance tools compared - 2026 landscape
I've been working in the AI agent governance space for a while and noticed there's no good comparison...
Dev.to · João André Gomes Marques
1w ago
How to make your AI agent accountable in 60 seconds
You built an AI agent. It calls APIs, reads databases, sends emails. But can you prove what it did...
Dev.to · João André Gomes Marques
1w ago
AI agent compliance scanner for your CI/CD pipeline
We lint code. We run tests. We scan for vulnerabilities. But most teams shipping AI agents don't...
Dev.to · João André Gomes Marques
1w ago
One decorator to make any Python function auditable
I've been building AI agents for a while, and the one thing that always bugged me was this: how do...
Dev.to · João André Gomes Marques
1w ago
Your MCP servers are unsigned. Here is why that matters.
MCP is everywhere right now. Every AI tool is adding MCP support. Claude Desktop, Cursor, Windsurf,...
Dev.to · João André Gomes Marques
1w ago
Your AI agents need audit trails before August 2026. Here is how I added them in 5 lines of Python.
Your AI agents need audit trails before August 2026. Here is how I added them in 5 lines of...
Dev.to · João André Gomes Marques
2w ago
One Decorator to Audit Every AI Agent Call
Your AI agent makes hundreds of API calls a day. Can you prove what it did last Tuesday at...
Dev.to · João André Gomes Marques
2w ago
Stop AI Agents from Leaking PII
Your AI agent passes a context dict to every LLM call. That dict might contain credit card numbers,...
Dev.to · João André Gomes Marques
2w ago
Your AI Agents Are Running Unsupervised
Your AI Agents Are Running Unsupervised The EU AI Act is enforceable. SOC 2 auditors are...
Dev.to · João André Gomes Marques
3w ago
Building a Governance MCP Server for AI Agents
MCP (Model Context Protocol) lets AI assistants use external tools. But when those tools make real...
Dev.to · João André Gomes Marques
3w ago
Adding Audit Trails to LangChain Agents with Asqav
LangChain agents make decisions autonomously. They call tools, query APIs, and process data. But once...
Dev.to · João André Gomes Marques
3w ago
EU AI Act Compliance for AI Agents: What Developers Need to Know
The EU AI Act is now active. If you build or deploy AI agents in the EU, you need to comply. Here is...
DeepCamp AI