Tag

#aiagents

291 posts3 followers

Explore Hashnode

Alternatives

How to Secure AI Coding Agents: Sandboxing, Permissions, and Human Approval Gates

Prompt injection can't be fully fixed, so contain it: sandbox the agent, lock down what it can touch, and keep humans on the actions that can't be undone.

11 min readblog.zyvop.com

2

MEHO3d ago

What are the office hours of an AI agent?

Why an agent’s permissions should depend on the operation, not on who happens to be awake. A research note from the MEHO lab, with sources.

9 min readmeho-ai.hashnode.dev

2

Jon Dixon6d ago

APEX AI Agents: Convenience vs. Control

APEX AI Agents simplify development with familiar tools and built-in features. Explore the benefits, limitations, and when to look beyond APEX.

2 min readblog.cloudnueva.com

4

Amir PournasserianNov 5

Decision models against small LLMs: Jev, Kev, Laya and Mammoth-1 on 6,662 decisions

Four decision models and five small LLMs, tested on six public datasets with the harness and raw calls published. https://pournasserian.com/writing/decision-models-vs-small-llms-2026

1 min readpournasserian.hashnode.dev

1

KarmaBoxNov 3

Why your agent's rework rate is an architecture problem, not a model problem

Which model is best for agents? Wrong question. Two teams can run the same model with the same prompts and see rework rates three times apart.

10 min readkarmabox.hashnode.dev

techpotionsNov 2

8 AI Agent Builders and What Each Locks You Into

Every team evaluating an AI agent builder eventually hits the same wall: the first 100 runs feel free, the next 1,000 get expensive, and leaving becomes a project in itself.

12 min readtechpotions.hashnode.dev

techpotionsNov 2

RAG vs MCP: What Your Agent Actually Needs

RAG is a retrieval pattern over a copy you own; MCP is a protocol for asking the system that owns the data. Here’s where each one fails, how to combine them, and how to tell which one produced your agent’s confident wrong answer.

10 min readtechpotions.hashnode.dev

Neural CoreTechNov 1

AI Productivity Tools 2026: Embedded Assistants vs. Always-On Autonomous Agents

From embedded AI assistants to autonomous cloud-based agents: explore the latest tools, pricing models and security controls.

2 min readneuralcoretech.hashnode.dev

Jon DixonOct 29

You Don’t Need to Know Anything Anymore

Codex and OCI CLI built an MCP server for an Oracle APEX app. The experience showed why knowing what good looks like still matters.

2 min readblog.cloudnueva.com

5

techpotionsOct 29

Build Your Own AI Coding Benchmarks

Stop trusting public leaderboards built on generic repos. Build your own AI coding benchmarks tuned to your codebase: real tickets, precise scoring, and a refusal safety net. Run it cheap, run it often, and re-evaluate monthly.

8 min readtechpotions.hashnode.dev

Search Hashnode