Agents & Automation tag

48 Articles

Agents & Automation ×

One vendor's documentation describes its own interface like this: **"a green status means the session started and exited without an infrastructure error. It does not mean the task succeeded."** That one sentence sums up the entire problem with background agents. And according to one measurement, **more than a third** of failures are exactly this: the agent **does not know when to stop**.

Advanced Business owner How-To Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

Browser and Computer-Use Agents: Real Uses

In April 2024 the best model solved **12.24%** of computer-use tasks; a human solved **72.36%**. In August 2026 the best number is **85.96%**. So the capability is there — the question is the cost. And it does not grow linearly, it grows **with the square of the step count**: 6.7 times more steps means a **34 times bigger bill**. The biggest turnaround, though, is somewhere else entirely: the agent that **writes code instead of clicking** is cheaper and more accurate at the same time.

Intermediate Business owner Tool review Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

Agent Memory: What to Store and What to Forget

Memory is the weakest agent capability there is. On the best independent measurement, **the average of 109 models fails to reach 30% on any memory strategy** — the very same models score 86–91% on simple tool calls. That measurement also shows that **there is no universally good memory architecture**. And there is a second reason for caution: memory is an **attack surface** — in one study an attacker planted a persistent false memory with a **98.2% success rate**, using nothing but questions.

Advanced Developer Explainer Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

Subagents and Parallel Work

The most quoted number says a multi-agent setup is **90.2% better** than a single-agent one. The same source also writes that it uses **fifteen times as many tokens**, and that **80% of the performance difference is explained by token consumption alone**. And a 2026 paper showed it formally: **at an equal token budget, the single-agent system wins.** The value of splitting a task is not parallelism — it is **clean context**.

Advanced Developer How-To Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

Permissions: The Least-Privilege Agent

Three things are needed for a data leak: **private data**, **untrusted content** and **an outbound channel**. Any two of them on their own are safe — all three together are not. And this is not theory: according to a study of 7,973 live servers, **40.55% of them expose their tools with no authentication**.

Advanced Business owner How-To Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

Human in the Loop: Where to Put the Approval

The human who approves is not a neutral safety layer. In a 2026 randomised clinical trial, **44 doctors, after twenty hours of AI literacy training**, still performed **14 percentage points worse** whenever the AI handed them a wrong recommendation. Training does not protect against this. What does: **few approval points, but real ones.**

Intermediate Business owner How-To Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

Agent Reliability Math: Why Twenty Steps Fail

0.98 to the twentieth power = **66.8%**. That one multiplication explains the feeling that an agent is "almost right, but it always breaks something somewhere". And the reverse is harsher still: **at twenty steps, a 90% end-to-end success rate demands 99.475% per-step accuracy.** Not 90%. This whole topic lives in the gap between those two numbers.

Intermediate Business owner Explainer Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

No-Code Automation with AI: Which Platform?

Price is not what decides, **the billing unit is**. Five large platforms, five different units — and the same daily automation with twenty steps consumes **900** units on one and **18,000** on another. That is a twentyfold difference for exactly the same work. Plus one correction that many comparisons get wrong: **n8n is not open source.**

Beginner Business owner Comparison n8n Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

Your First Automation That Is Actually Useful

Most companies start where the return is worst. According to a report covering 52 organisations and 153 executives, roughly **70% of the AI budget goes to sales and marketing**, while **back-office processes** delivered faster payback and cleaner cost reduction. And there is one number that rearranges everything: for an automation running once a day, **the platform fee is typically more than a hundred times the model cost.**

Beginner Business owner How-To Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

MCP: How AI Connects to Your Tools

MCP is the standard agents use today to connect to your systems — and two things happened to it over the past year that most write-ups have not caught up with. **It is no longer one company's protocol**, it now lives under the Linux Foundation, and the summer 2026 specification **rewrote its architecture**. Meanwhile the number of vulnerabilities associated with it has more than doubled in a year.

Intermediate Everyone Explainer MCP Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

Tool Use and Function Calling, Explained

The most common misconception about this topic can be refuted in one sentence taken from the vendor documentation: **the model does not call the tool.** It fills in a form and says which one it would like — the call is made by your code. Everything else follows from that: the cost, the error handling, and the reason a single round gets three times more expensive.

Advanced Developer Explainer Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

What an Agent Actually Does, Step by Step

An agent is not magic, it is **a loop**: it asks the model, performs an operation, reads the result back, and starts over. The complete control logic of a production agent that scores above 74% on a benchmark is **roughly a hundred lines of code**. This post walks through one real run — and shows where it breaks.

Beginner Everyone Explainer Agents & Automation

Sep 13, 2026 Bite-Sized AI

Tags

Audience

Everyone Office worker Marketer Creative Business owner Developer

Follow Us

Archives

Tags