DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
My Actor ranked #1 in an agent's search. No one else's agent could see it at all.

My Actor ranked #1 in an agent's search. No one else's agent could see it at all.

4
Comments 1
10 min read
Three layers of automated fact-checking for an LLM newsroom (and the bugs that forced each one)

Three layers of automated fact-checking for an LLM newsroom (and the bugs that forced each one)

Comments 1
3 min read
Gibson ADK's Zero Trust Runtime: How Bug Bounty Automation Agents Enforce Security Boundaries at the Tool Layer

Gibson ADK's Zero Trust Runtime: How Bug Bounty Automation Agents Enforce Security Boundaries at the Tool Layer

Comments
6 min read
AgentCore Evaluations: How AWS Built a Framework-Agnostic Eval Layer Using OpenTelemetry as the Contract

AgentCore Evaluations: How AWS Built a Framework-Agnostic Eval Layer Using OpenTelemetry as the Contract

1
Comments
6 min read
Your Documents, Chunked and Searchable: The Knowledge Base in ByteChef

Your Documents, Chunked and Searchable: The Knowledge Base in ByteChef

Comments
7 min read
Needle 2: the 14 MB agentic model, tested properly

Needle 2: the 14 MB agentic model, tested properly

1
Comments
1 min read
Why Your AI Agent Doesn't Have a Reasoning Problem—It Has a Memory Problem: A Practical Guide to Production-Grade Agent State

Why Your AI Agent Doesn't Have a Reasoning Problem—It Has a Memory Problem: A Practical Guide to Production-Grade Agent State

1
Comments
12 min read
What it takes to get an x402 seller counted by the Coinbase Bazaar (and a 0.25 USDC thank-you for your first receipt)

What it takes to get an x402 seller counted by the Coinbase Bazaar (and a 0.25 USDC thank-you for your first receipt)

Comments 1
2 min read
How I built a kernel-enforced sandbox for LLM agent tool calls

How I built a kernel-enforced sandbox for LLM agent tool calls

Comments
3 min read
Runtime over Prompt: Why the System Prompt Is Not a Security Boundary

Runtime over Prompt: Why the System Prompt Is Not a Security Boundary

Comments 4
6 min read
Giving AI Agents a Deterministic Clock (Zero LLM in the Loop)

Giving AI Agents a Deterministic Clock (Zero LLM in the Loop)

Comments
3 min read
Passing Once Isn't Reliable — This Week's Agent Engineering Puts the Harness Before the Model

Passing Once Isn't Reliable — This Week's Agent Engineering Puts the Harness Before the Model

Comments
6 min read
A counter in process memory is not a guard: 131 restarts proved it

A counter in process memory is not a guard: 131 restarts proved it

4
Comments 6
6 min read
The Flaky Test That Only Failed After the Model Swap: A Debugging Retrospective

The Flaky Test That Only Failed After the Model Swap: A Debugging Retrospective

Comments
4 min read
Stop Blaming the Model When Your Agent Repeats the Same Mistake

Stop Blaming the Model When Your Agent Repeats the Same Mistake

Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.