All
Articles 189,225Blog Posts 171,155Tech Tutorials 50,720Research Papers 36,770News 23,155
⚡ AI Lessons
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
3mo ago
Multi-agent runs need a handoff receipt, not just a shared trace
When a single agent does something dangerous, the audit problem is small. You have one run, one set...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
3mo ago
Agent runs need their own session identity, not the human's
One of the quiet assumptions that breaks first when agents move from demos to production is that the...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
3mo ago
AI agents need tiered approval escalation, not one big confirm button
Every agent product eventually has the same conversation: who is allowed to click "yes"? The...
Dev.to · Armorer Labs
📰 AI News & Updates
3mo ago
Agent traces are not enough. Agent runs need operating records.
Most production-agent discussions eventually land on observability. That is good. Traces...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
3mo ago
Why block counts are not enough for agent safety
A block count is not an audit record. If an agent guard says it blocked 200 actions, I still need to...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
3mo ago
The boring checklist before running a new local agent
Before I run a new local agent, I want a boring checklist. Not hype. Not a demo video. Just...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
3mo ago
Coding agents need branch policy at runtime
Telling a coding agent "do not push to main" is useful. It is not enough. Branch policy has to be a...
Dev.to · Armorer Labs
📰 AI News & Updates
3mo ago
Agent evals should explain why they passed
A passing agent eval is not always reassuring. Sometimes it means the agent behaved...
Dev.to · Armorer Labs
📰 AI News & Updates
3mo ago
Five receipts every AI agent run should leave behind
When an AI agent finishes a task, I do not only want a final answer. I want an operating...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
3mo ago
Agent guards need receipts, not just block counts
A lot of AI-agent safety tooling is framed around blocking bad actions. Blocking matters, but it is...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
3mo ago
Agent demos are easy. Agent operations need receipts.
I keep seeing the same pattern with AI agents: the demo works, the first workflow is exciting, and...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
3mo ago
Agent browser runs need receipts, not just screenshots
Agentic browser work is getting good enough that teams are starting to trust it for real workflows:...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
3mo ago
Agent frameworks create workflows. Production needs run receipts.
Everyone is comparing agent frameworks: LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, Claude Code,...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
3mo ago
Local Agents Need a Control Plane
AI agents are quickly moving from impressive demos to actual work. They read docs. They summarize...
Dev.to · Armorer Labs
☁️ DevOps & Cloud
⚡ AI Lesson
4mo ago
Armorer Guard: runtime control should start at the tool call
# Armorer Guard: runtime control should start at the tool call The more I work on local agent...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
4mo ago
I built a local Rust MCP security proxy for AI agents
Armorer Guard scans prompt injection, credential leaks, exfiltration, and dangerous MCP tool calls locally before agent tools execute.
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
4mo ago
Where to plug security hooks into AI agents: tool calls, MCP results, logs, and sends
Most AI-agent security advice collapses into one sentence: "add guardrails." That is too vague to...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
4mo ago
Install Armorer Guard from Cargo: local Rust scanning for AI-agent tool calls
Armorer Guard is now published on crates.io, so Rust-first teams can install the local scanner...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
4mo ago
Armorer Guard Learning Loop: live local feedback for AI-agent security, without model drift
A Rust-native local learning overlay for AI-agent prompt injection and tool-call risk scanning, with reviewed retraining instead of silent drift.
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
4mo ago
Armorer Guard: a 0.0247 ms local Rust scanner for AI-agent prompt injection
Most AI-agent security failures do not start as cinematic jailbreaks. They start at ordinary runtime...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
4mo ago
The hard part of AI agents is not building one. It is operating five.
Most AI agent demos optimize for the first successful run. Production teams care about the tenth...
Dev.to · Armorer Labs
🤖 AI Agents & Automation
⚡ AI Lesson
4mo ago
Armorer Guard: fast local scanning before AI-agent tool calls
Prompt injection gets more dangerous when an agent can act. The risky moment is often not the first...
DeepCamp AI