DEV Community

#agents

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
building-ai-agents-right-way

building-ai-agents-right-way

Comments
4 min read
agents-concepts-principles-patterns

agents-concepts-principles-patterns

Comments
5 min read
Prompt Engineering, Context Engineering, Loop Engineering: What Actually Changed

Prompt Engineering, Context Engineering, Loop Engineering: What Actually Changed

10
Comments 1
8 min read
Put a hard stop in front of your CrewAI crew's tool calls

Put a hard stop in front of your CrewAI crew's tool calls

3
Comments 6
5 min read
CrewAI vs Traditional Automation: When Do AI Agents Actually Make Sense?

CrewAI vs Traditional Automation: When Do AI Agents Actually Make Sense?

Comments
2 min read
【Deep Dive】Frontier Code: The Benchmark That Asks "Would a Maintainer Merge This?"

【Deep Dive】Frontier Code: The Benchmark That Asks "Would a Maintainer Merge This?"

Comments
8 min read
The AI Bill Grows in the Agent Loop

Retries and loops as primary cost drivers

The AI Bill Grows in the Agent Loop

16
Comments 11
16 min read
AIClaw v1.10.5: Configurable Web Search for Tool-Using Agents

AIClaw v1.10.5: Configurable Web Search for Tool-Using Agents

Comments
3 min read
Arquitetura Hexagonal e IA: Integrando Flexibilidade e Manutenibilidade

Arquitetura Hexagonal e IA: Integrando Flexibilidade e Manutenibilidade

Comments
4 min read
Alberta Ran 50 AI Agents in Parallel. Everyone Shared the Same Number.

Quiet failures in agent handoffs

Alberta Ran 50 AI Agents in Parallel. Everyone Shared the Same Number.

21
Comments 7
4 min read
Lead Quorum: a multi-agent lead qualifier that refuses to guess (ADK + A2A)

Education Track: Build Multi-Agent Systems with ADK

Lead Quorum: a multi-agent lead qualifier that refuses to guess (ADK + A2A)

6
Comments 26
4 min read
Penpot for Developers: The Open-Source Design Tool That Speaks Your Language

Penpot for Developers: The Open-Source Design Tool That Speaks Your Language

6
Comments 1
3 min read
One Triage Pass, Every Trace Format: Stop Letting Fragmentation Shrink Your Eval Coverage

One Triage Pass, Every Trace Format: Stop Letting Fragmentation Shrink Your Eval Coverage

3
Comments 1
5 min read
Building an Enterprise RAG & Knowledge Graph Engine with Governed AI Workflows

Building an Enterprise RAG & Knowledge Graph Engine with Governed AI Workflows

1
Comments
3 min read
AutoLab Benchmarks Frontier Agents on Long-Horizon R&D Tasks: Iterative Experiment-Loop Evaluation

AutoLab Benchmarks Frontier Agents on Long-Horizon R&D Tasks: Iterative Experiment-Loop Evaluation

Comments
6 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.