Opening soon · preview

How to work with AI agents,
one step at a time.

A practical knowledge base about AI agents: short answers and numbered guides for building, controlling, testing and auditing them. Open to contributors, reviewed by editors, never for sale.

What is an AI agent?How to give an agent only the permissions it needsHow to keep a human in the loop for irreversible actionsHow to defend an agent against prompt injectionHow to set step and cost limits on an agent loop

First guides

Previews of the first pages. Each answers one practical question in numbered steps.

Basics

What is an AI agent?

An AI agent is a language model that works toward a goal in a loop: it plans, calls tools, reads the results and decides the next step.

  1. Name the goal: what should be true when the agent is done?
  2. List the tools it may call (search, files, email, APIs) and nothing more.
  3. Run the loop: plan → act with a tool → read the result → decide again.
  4. Stop on a clear condition: goal reached, step limit hit or a human must decide.
Safety & control

How to give an agent only the permissions it needs

Least privilege limits the damage when an agent misunderstands a task or reads a malicious instruction.

  1. Write down the actions the task really requires.
  2. Create a separate account or API key for the agent, with only those rights.
  3. Prefer read-only access; grant write access per task, not forever.
  4. Keep secrets out of prompts; let a secret manager inject them.
  5. Review and revoke the permissions when the task ends.
Safety & control

How to keep a human in the loop for irreversible actions

Sending, paying, deleting and publishing cannot be undone. Route them through a person.

  1. Mark the irreversible actions in your tool list.
  2. Make the agent prepare the action and show a preview: recipient, amount, content.
  3. Require an explicit approval for each one; approval does not carry over to the next.
  4. Log who approved what and when.
Safety & control

How to defend an agent against prompt injection

Text the agent reads from web pages, emails or files can contain instructions. Treat it as data, never as commands.

  1. Separate instructions (from the user) from content (from tools) in your design.
  2. Do not let tool output trigger sensitive actions without confirmation.
  3. Allow-list the domains and recipients the agent may contact.
  4. Test with planted instructions in documents before going live.
Building

How to set step and cost limits on an agent loop

An agent without limits can loop, repeat work and spend money. Guardrails make a demo production-ready.

  1. Set a maximum number of steps per task.
  2. Set a budget: tokens or money per task and per day.
  3. Define the termination conditions in advance, including "ask a human".
  4. Alert when a limit is hit and keep the partial result.
Building

How to connect an agent to tools with MCP

The Model Context Protocol (MCP) is an open standard that lets AI applications connect to tools and data sources through a common interface.

  1. Pick an MCP server for the system you need (files, database, ticketing, search).
  2. Register the server in your agent client configuration.
  3. Review which tools the server exposes and disable the ones you do not need.
  4. Test each tool with harmless inputs and check the logs.
Testing & audit

How to test an agent before you trust it

An agent is only as good as its behaviour on your real tasks, including the hard and the adversarial ones.

  1. Collect 20–50 real tasks with known good outcomes.
  2. Add edge cases: missing data, ambiguous requests, planted instructions.
  3. Run each task several times; agents are not deterministic.
  4. Score outcome, cost, steps and safety violations separately.
  5. Re-run the set after every model or prompt change.
Testing & audit

How to log and audit what an agent did

If you cannot reconstruct what the agent did, you cannot fix it or answer for it.

  1. Log every tool call with inputs, outputs and timestamps.
  2. Store the prompt and model version used for each run.
  3. Keep human approvals in the same log.
  4. Review a sample of runs every week, not only the failures.

The agent data sheet

Makers will be able to publish one standard sheet per agent. Same fields for everyone, so agents can be compared on facts, not on marketing.

Name & versionWhat the agent is called and which release this sheet describes.
MakerWho builds and answers for it, with contact.
ModelsWhich language models it runs on.
Tools & permissionsWhat it can read, write, send or pay.
Data handlingWhat data it stores, where, for how long.
Human oversightWhich actions need a person's approval.
Known limitsTasks it should not be used for, known failure modes.
Test resultsResults under the public Agentage protocol, with date.

The Agentage test

Independent evaluation under a public protocol, with responsible disclosure.

01Public protocolTest tasks, scoring and environment are published before any test runs.
02Own environment onlyTests run in sandboxes and accounts we control. We never attack anyone's live service.
03Maker sees it firstThe maker receives the results 7–14 days before publication and can respond.
04Right of reply & retestThe maker's response is published with the results; fixed versions can be retested.
05Nothing for saleListings and rankings cannot be bought. No sponsored placement.

House rules: No paid listingsNo attacks on live servicesSources cited on every pageEditorial review before publishingCorrections stay visible

Questions and answers

What is agentage.wiki?

agentage.wiki is a practical, community knowledge base about AI agents, in preparation. It publishes short question-and-answer pages and step-by-step guides on building, controlling, testing and auditing agents. Contributions are open; an editor reviews every page before publication.

Can AI agent makers publish their own data sheet?

Yes. Makers will be able to publish a standard data sheet: models, tools and permissions, data handling, human oversight, known limits and test results. The sheet is factual and the same for everyone; listings cannot be bought.

What is the Agentage test?

The Agentage test is an independent evaluation of AI agents under a public protocol. Tests run only in environments Agentage controls, never against someone else's live service. The maker sees the results 7–14 days before publication and can respond; the response is published with the results.

Who is behind agentage.wiki?

agentage.wiki is founded by Zoltán Varga, a Budapest-based AI ecosystem architect and AI visibility researcher who builds research pipelines, knowledge bases and AI agents. Agentage editorial standards are published on agentage.org.

How can I contribute a guide?

Contributions open with the launch. Each guide answers one practical question in numbered steps, cites its sources and passes editorial review before it goes live. Until then, proposals can be sent through the contact page on vargazoltan.ai.

Building agents for your organization?

Agent design, audits, talks and workshops by the founder, Zoltán Varga.

vargazoltan.ai →

Editorial standards: agentage.org