Skip to main content
← All Tags

AI Engineering

61 articles in this category (Page 1 of 3)

AI NewsSoftware ArchitectureAI Engineering

The Shift to Multi-Agent AI: Moving the Bottleneck from Implementation to Specification

CTO Anuar Ustayev reports a workflow shift to 80% planning and 20% debugging after adopting multi-agent AI orchestration.

Read more
AI NewsDevOpsAI Engineering

APEX: A Production-Grade Operating Model for Agentic Teams

APEX provides a three-phase operating cycle to close the gap between individual agent use and reliable team-wide production output.

Read more
AI NewsSecurityAI Engineering

Evidence-First AI Security: Building the EllipticZero Research Lab

Vladimir Stelmak introduces EllipticZero, a local-first workflow separating AI reasoning from technical evidence in smart-contract security reviews.

Read more
AI NewsAI EngineeringSoftware Development

Beyond the Tutorial: Building an AI Portfolio Based on Real Company Briefs

Move beyond RAG clones with 5 real-world company briefs designed to demonstrate engineering judgment and architectural decision-making.

Read more
AI NewsAI EngineeringSystems Architecture

Moving Beyond Prompt Engineering: AI Alignment as Systems Architecture

SAFi introduces a zero-trust runtime governance engine to enforce AI alignment via deterministic system constraints rather than probabilistic prompts.

Read more
AI NewsAI EngineeringSoftware Architecture

LangGraph Architecture: When to Use Graph-Based Orchestration for AI Agents

Evaluate whether LangGraph's state management and human-in-the-loop features are necessary for your AI workflow or if simpler Python logic suffices.

Read more
AI NewsAI EngineeringDeveloper Tools

Prism: Optimizing AI Editor Workflows via MCP Delegation

Prism reduces orchestrator input tokens by 94.1% by delegating context-heavy tasks to local Ollama specialists.

Read more
AI NewsAI EngineeringOpen Source

The Agent Economy: Scaling Autonomous AI Bounty Hunting on GitHub

An autonomous AI agent earned $500+ across 84 pull requests, revealing a power-law distribution in open source bounty acceptance.

Read more
AI NewsAI EngineeringSoftware Security

Securing Autonomous AI Agents: A Three-Tiered Defense Architecture for Untrusted Code

Learn how the Hermes Agent framework (v0.13) prevents catastrophic system failures like 'rm -rf /' using policy-based sandboxing and state-machine orchestration.

Read more
AI NewsAI EngineeringCybersecurity

Architecting Agentic Systems: Governance and Identity Challenges

Dataiku and 1Password experts discuss the necessity of orchestration frameworks and new identity standards for ephemeral agent swarms.

Read more
AI NewsAI EngineeringFintech

Architecting Explainable AI Agents for Financial Compliance Monitoring

Learn how to build a compliance AI architecture that replaces vague risk scores with auditor-ready reasoning to meet FINRA and FCA requirements.

Read more
AI NewsAI EngineeringSoftware Development

Implementing RAG: Solving LLM Hallucinations with Retrieval Augmented Generation

RAG eliminates LLM hallucinations by grounding generation in private knowledge bases using a chunk-embed-retrieve pipeline.

Read more
AI NewsAI EngineeringSoftware Development

Implementing State-Based AI Workflows with LangGraph Templates

Explore 5 reusable LangGraph agent templates for implementing state-based workflows, including RAG, multi-tool loops, and human-in-the-loop systems.

Read more
AI NewsAI EngineeringSoftware Architecture

The Six Levels of MCP Server Maturity: Moving Beyond API Wrapping

Most production MCP servers are stuck at Level 1 or 2, failing to provide the domain context necessary for effective agent reasoning.

Read more
AI NewsAI EngineeringCloud Infrastructure

Google Managed Agents API: Transitioning AI Agents to Serverless Compute

Google's Managed Agents API reduces agent infrastructure setup from three weeks of plumbing to eleven lines of code.

Read more
AI NewsSoftware ArchitectureAI Engineering

Solving AI Agent Ambiguity with Domain-Driven Design's Ubiquitous Language

AI coding agents amplify vocabulary ambiguity, leading to semantic mismatches that can result in critical production incidents.

Read more
AI NewsAI EngineeringLarge Language Models

DeepSeek-V3: Scaling 671B MoE Models with FP8 Precision and R1 Distillation

DeepSeek-V3 achieves GPT-4o level performance with a 671B parameter MoE architecture activating only 37B parameters per token.

Read more
AI NewsOpen SourceAI Engineering

Agentic OS: A 7-Layer Open-Source Architecture for Multi-Agent Coordination

Mihir N Modi releases Agentic OS, an MIT-licensed 7-layer framework that coordinates specialized AI agents with built-in memory and zero-cost tier support.

Read more
AI NewsCybersecurityAI Engineering

Securing AI Agents: Lessons from a 40-Minute AWS Credential Leak

An AI agent leaked hardcoded AWS keys to a public GitHub repository, resulting in a 40-minute exposure window before automated scanners detected the breach.

Read more
AI NewsAI EngineeringPrompt Engineering

Benchmarking XML Delimiters in LLM Prompts: When Structure Becomes Token Waste

Claude Sonnet 4.5 testing shows XML delimiters on 150-token prompts increase token overhead by 31% with no accuracy gain, suggesting flat prose for short tasks.

Read more
AI NewsAI EngineeringPlatform Engineering

Engineering Reliable AI Agents: Why Programmatic Tests Must Replace Prompt-Only Control Flow

Michael Tuszynski argues that reliable AI agents require programmatic tests over prompts to prevent failures like PocketOS's database loss.

Read more
AI NewsSecurityAI Engineering

Securing AI Agents with Ephemeral, Task-Scoped Credentials

AI agents live for 2 minutes but credentials last 60, a 30x mismatch. Task-scoped brokers close this attack surface by issuing short-lived, ephemeral identities.

Read more
AI NewsDevOpsAI Engineering

Preventing AI Agent Configuration Drift with Agent Contract Testing

Ramanpreet Singh released a Python-based CI tool to enforce YAML-defined access control lists and tool permissions for AI coding agents.

Read more
AI NewsAI EngineeringDevOps

Scaling 20 Autonomous AI Agents on a €4.57/Month Infrastructure

Developer Vilius successfully deployed 20 autonomous AI agents for just €4.57/month using a Hetzner CX23 VPS and a 10-pattern methodology for resilience and memory.

Read more