Guides, answers & tools

AI Agents

Agentic AI — frameworks, automation and running agents yourself

Freshly updated

Making Money With AI Agents in 2026: The Honest Version →Updated Oct 26, 2026
n8n AI Agents (2026): The No-Code Way to Automate With AI →Updated Sep 27, 2026

Flat vector illustration of a person pulling one coral folder out of a single open drawer in a huge black filing cabinet, on a saturated indigo-violet background

Claude Skills explained: SKILL.md, and how a skill differs from CLAUDE.md, hooks and MCP

A skill is a folder with one SKILL.md file that Claude opens only when your request matches. Here is what goes in it, how it loads, and when to reach for a skill instead of CLAUDE.md, a slash command, a hook or an MCP server.

Aliteq Team · Oct 16 · 10 min

Hand-drawn editorial illustration of a small robot reading a long paper letter, while a tiny coral hand reaches out of the page to steer the robot's hand, on a near-black background

Agents

Your AI agent just read a web page. Who is it obeying now? Prompt injection, explained

Prompt injection is how text your AI reads turns into orders it follows. What direct and indirect injection are, why tools raise the stakes, Simon Willison's lethal trifecta, the defenses OWASP, Anthropic and OpenAI recommend, and their own admission that none of it is a full fix.

Aliteq Team · Oct 16 · 11 min

Hand-drawn editorial illustration of one large coral plug whose cable forks in two: one branch runs to a wall panel of many differently shaped sockets, the other to an empty terminal window with a single cursor block, on a near-black background

Agents

Is MCP dead? What the Model Context Protocol is in 2026, and when a CLI beats it

MCP has a new spec revision, a Linux Foundation home and a loud group of critics. Here is where each stands, read from the spec, Anthropic, Cloudflare, Claude Code's docs and the critic's own post, plus five rules for choosing an MCP server or a CLI.

Aliteq Team · Oct 16 · 12 min

Flat vector illustration of a developer at a laptop beside a tall stack of conversation pages squeezed by a giant clamp into one thin coral summary card next to a blank page, on a saturated indigo-violet background

Agents

Claude Code is forgetting things: /compact, /clear or a new session?

/compact squeezes your chat into a summary and keeps going. /clear wipes it and starts clean, for free. Here is what each one keeps, what auto-compact does on its own, and why your CLAUDE.md is the only rule book that survives both, from Anthropic's own docs.

Aliteq Team · Oct 16 · 10 min

Overhead photo of a desk at night with a row of blank white cards above four small trays, one tray holding green sticky notes and another coral ones, while a hand with a pen sorts cards, lit in warm and violet light

Agents

You changed the prompt. Is it actually better? LLM evals, explained

An eval is a test for an AI feature: a fixed set of tasks, a way to grade each answer, and a score you can compare before and after a change. Here is how golden sets, graders, LLM judges and regression gates work, read from Anthropic's and OpenAI's own guidance.

Aliteq Team · Oct 16 · 12 min

Hand-drawn editorial illustration of a tangle of loose violet scribbled lines entering a rigid off-white metal plate with eight square slots, and leaving the other side as eight perfectly straight coral lines, on a near-black background

Agents

My LLM returns broken JSON: JSON mode vs structured outputs vs tool calling

Valid JSON, the right shape and a correct value are three different promises. Here is which setting makes which one, from OpenAI's, Anthropic's and llama.cpp's own docs, plus the local equivalents.

Aliteq Team · Oct 16 · 9 min

Flat vector illustration of a person turning a large six-position mode dial on a control panel, with a striped barrier gate beside it, on a saturated indigo-violet background

Agents

Claude Code keeps asking permission? The six modes, and which one to pick

Manual, accept edits, plan, auto, don't ask, bypass: each one changes what Claude can do before it checks with you. Here is what Anthropic's docs say each does, how Shift+Tab moves between them, and where the safety lines sit.

Aliteq Team · Oct 12 · 9 min

Flat vector illustration of a developer holding a toolbox beside an oversized graphics card that opens like a toolbox, with a coral wrench lifting out toward a blank terminal window, on a saturated indigo-violet background

Agents

Best local coding model for OpenCode (2026): which ones call tools, and what fits your GPU

OpenCode only works when the model can call tools and holds 64K of context. Seven local models pass the first test. Here is what each one needs in VRAM, worked out from their configs.

Aliteq Team · Oct 9 · 11 min

Flat vector illustration of a developer with a laptop leaning against a giant hourglass whose sand has run out, beside a row of seven calendar squares with one marked in coral, on a saturated indigo-violet background

Agents

Claude Code says you hit your weekly limit? When it resets, what counts, what to do

The weekly cap is a different clock from the 5-hour one, and switching models won't fix it. Here is what Anthropic's own pages say about both limits on Pro, Max and Team, how to see where you stand, and what each way of keeping going costs.

Aliteq Team · Oct 7 · 10 min

Hand-drawn editorial illustration of a magnifying glass over a scatter of lavender dots with one coral dot connected by a line to a stack of paper files, on a near-black background

Agents

Claude Code Doesn't Need a Vector Database. Does Your AI App? Agentic Search vs RAG

Your coding agent finds code by grepping and reading files, not by embeddings. Anthropic says that works. Cursor says semantic search added accuracy. Here is how to decide which your own app needs.

Aliteq Team · Oct 5 · 7 min

Hand-drawn editorial illustration of a small coral robot walking along a path inside an off-white strap harness held by human hands, on a deep near-black background with indigo-violet shapes

Agents

AI agent keeps making the same mistake? Harness engineering, explained

The model is only one part of an agent. The loop, the tools, the permissions and the memory around it are the harness, and in 2026 OpenAI, Anthropic and Mitchell Hashimoto all described fixing agents there instead of in the prompt. Here is what that means and where the name came from.

Aliteq Team · Oct 3 · 11 min

Flat vector illustration of a person hauling on a giant fishing hook that lifts a coral gear above a conveyor belt, on a saturated indigo-violet background

Agents

Claude Code hooks, explained: block rm, auto-format, get pinged when it stops

A hook is a small script Claude Code runs for you at fixed moments, such as before a tool call or when Claude finishes. Here is every piece in Anthropic's docs that matters: events, matchers, exit codes, JSON, where the file lives, and the security warning.

Aliteq Team · Oct 3 · 11 min

Flat illustration of a person choosing between small, medium and large boxes to fit into a slot on a graphics card, a small robot helper watching

Agents

Run OpenClaw or Hermes on a local model: which fits your GPU

Ollama's default gemma4 is the small E4B and qwen3.5 is the 9B, not what most people assume. What each tag really downloads, what the bigger models need at the 64K context agents use, and what to pick for 12, 16 and 24GB cards.

Aliteq Team · Sep 25 · 7 min

Flat illustration of a person on a chair with a phone showing chat bubbles, two simple robot helper figures standing by a small home server

Agents

OpenClaw vs Hermes Agent: which to run on a local model

The two biggest open-source personal agents, compared on what their docs actually say: licence, chat apps, skills, safety defaults, and the one-command Ollama setup for each.

Aliteq Team · Sep 25 · 7 min

Flat illustration of a person placing a small robot helper inside a locked glass box while chat bubbles pass through a gate

Agents

OpenClaw security: the real risks and how to sandbox it

An agent that reads your messages and runs your tools can be talked into things. That's the core risk, and it's what OpenClaw's own advisories show. The plain-English version, and the safe setup step by step.

Aliteq Team · Sep 25 · 8 min

Illustration of a person with a coffee while a robot handles a repetitive task

Agents

Making Money With AI Agents in 2026: The Honest Version

Not the 'AI employees that print cash' fantasy — the real one: an agent that automates a workflow you already do saves real time, and time is leverage. How to actually use agents to save (and make) money, honestly.

Aliteq Team · Sep 22 · 8 min

Illustration of connecting many app tiles into a central robot node on a no-code canvas

Agents

n8n AI Agents (2026): The No-Code Way to Automate With AI

n8n is the no-code answer for building AI agents — a visual canvas, 500+ integrations, and a proper AI Agent node with guardrails. Where it beats a code framework, where it doesn't, and the hybrid pros use.

Aliteq Team · Sep 22 · 7 min

Illustration of a main robot handing tasks off to sub-robots

Agents

The OpenAI Agents SDK, Explained (2026): What It Is & When to Use It

OpenAI's own lightweight agent framework — agents, handoffs, guardrails, tracing — is the least-friction way to build GPT-centric agents. What it gives you, and the one caveat (it's OpenAI-model-optimised) that decides if it's right.

Aliteq Team · Sep 22 · 6 min