AI agents that work inside your systems
A chatbot answers questions, an AI agent completes a task: it plans the steps itself, looks up data in your systems and prepares the result. We develop AI agents for companies with fixed rules and human approval wherever a mistake would cost money.

- Important actions are approved by a person
- Every step the agent takes is recorded
- The agent can only do what it is permitted to
AI agents at a glance
An AI agent is a program built on a language model that breaks a task into steps itself and carries it out with tools: it searches documents, reads and writes to a database, email, accounting system or CRM. A chatbot only answers, an agent acts and writes the result where it belongs. Classic automation needs input in a fixed form, an agent copes with free text. Webforte Technologies s.r.o. (company ID 23364343, Prague) develops custom AI agents for Czech companies, typically for enquiries, back-office documents and research. The agent has only the permissions it needs, passes checkpoints in code, a person approves important actions, and every step is logged. The price comes from a quote after the consultation.
What is an AI agent?
- AI agent
- An AI agent is a program built on a language model that receives a goal and decides for itself which steps will achieve it. It uses tools such as document search, a database or a company system, evaluates the results and continues until the task is done or a rule stops it.
Agentic AI is the general term for systems in which AI plans and carries out steps itself. When several agents work together under one controller (orchestration), it is a multi-agent system.
Language model
Understands instructions in everyday language and decides which step to take next.
Tools
Access to documents, databases and systems through an API, the interface programs use to talk to each other.
Memory
What the agent has already done, what it has found out and the context of the task.
Rules (harness)
Permissions, checkpoints, limits and human approval.
AI agentA model on its own only answers. It becomes an agent only with tools, memory and rules.
Chatbot, automation or AI agent?
All three are sold as AI, but they solve different tasks. Check which type your task really needs.
Swipe the table sideways to see all columns.
| Chatbot, automation or AI agent? | Chatbot | Automation | AI agent |
|---|---|---|---|
| What it does | Answers questions | Runs a predefined sequence of steps | Completes a multi-step task and chooses the approach itself |
| How it decides | From the question and the source material | By rules someone wrote in advance | From the goal, the rules and the results of earlier steps |
| What input it handles | A question in everyday language | Data in a fixed format | An email, a document or an enquiry written in free text |
| Example | Tells a customer the delivery time | Moves every paid order into accounting | Reads an enquiry, looks up prices and stock and prepares a quote for approval |
| When it fits | Repeated questions from customers or employees | A stable process with input in a fixed form | Variable input that needs judgement and work across several systems |
An AI agent is not always the better choice. If classic automation can do the job reliably, it is cheaper to run and easier to check, and we will recommend it.
How AI agents work: orchestration and harness
A bigger task is not done by one universal agent but by several agents with narrow roles. A planner directs them (orchestration) and the whole thing is held together by a harness: software around the model that sets what agents may do, when they stop and who checks them.
Harness
Input
Brief
An email enquiry, a document or a request from your system.
Orchestration
Planner
Breaks the task into steps, assigns them to agents and tracks what is done.
Specialised agents
Each agent does one thing
A narrow role is easier to test and check than one agent for everything. Steps that do not depend on each other run in parallel.
Research
Finds the customer, order history and documents.
Tools
- CRM
- document search
Calculation
Works out the price from the price list and checks availability.
Tools
- price list
- e-shop stock
Draft
Writes the quote using your templates and tone.
Tools
- templates
- email draft
Check in code
Checkpoint
An ordinary program verifies the rules: the totals add up, the customer exists, the claim has a source and the agent has not exceeded a limit.
- Passed: continues
- Failed: back for fixing
Human in the loop
Approval
Before the agent sends a quote or writes to the accounting system, a person reviews and confirms the result.
- Approves
- Returns with a note
Output
Result and log
The output is written to your system. Every step, every tool used and every human decision stays in the log.
Rules around the agents
A language model does not police itself. Reliability depends on the harness we build around it.
Tools
Precisely defined functions through which the agent works with your systems. If it is not among the tools, the agent cannot do it.
Permissions
Set per tool, with reading kept separate from writing. Sensitive actions always go through approval.
Memory
The state of the task and context from your data, so the agent does not repeat finished steps and picks up where it left off.
Record (log)
Every step, tool and output. You can trace why the agent did what it did and fix the mistake in the rules.
Evaluation
A set of test cases from your own work. We check every change to the model or rules against it before it goes live.
Limits
A cap on the number of steps, time and cost per task. When the agent reaches it, it stops and hands the task to a person.
An agent rarely works alone
- AI automation and integrationConnections to accounting, the e-shop and the CRM. When a fixed process is enough, we build automation without an agent.
- Custom applicationsThe agent as part of an internal system or client portal that we develop for you.
- AI chatbotThe window through which a customer or colleague asks a question. If answering is enough, you do not need an agent.
- ChatGPT, Claude and Copilot at workIf you want the whole team to use AI, rolling out a ready-made tool without custom development is often enough.
Not sure which of these you need? Write to us and we will recommend the simplest solution.
How to build an AI agent you can trust
Reliability does not come from the model alone but from the system around it. We use checks in code, sources behind claims and human approval in our own AI tools too.
Start with the task, not the technology
First we describe the task the way a person does it today: inputs, decisions, systems and the places where mistakes happen. Only then do we decide whether automation, one agent or several cooperating agents are needed.
- Step-by-step description of the task
- Decisions that must stay with a person
- A clear measure of a good result
Tools and data through interfaces
The agent works with your systems through APIs or MCP (Model Context Protocol), an open standard for connecting AI to data and tools. We describe each tool so the model knows what it is for and what it must not do with it.
- Connection to accounting, shop, CRM and documents
- Read tools kept separate from write tools
- Access keys are held by the application, the model never sees them
Code checks the rules, not the model
What a program can check, we do not leave to the model: totals, whether the customer exists, required fields, a source for every claim. Our article generator works the same way: findings without a source are dropped by code, and the source list is built by a program, not the model.
- Checkpoints between steps
- Claims with a source link
- What fails goes back for correction or to a person
AI agent security and permissions
An agent that acts in company systems needs rules like a new employee, only stricter. We set this up for every agent we build.
- Permissions
- only what is needed, reading separate from writing
- The agent gets only the tools and data the task requires. Preparing quotes, it may read the price list and create drafts, but not send emails or change prices. Writing is the first candidate for approval.
- Sensitive actions
- a person approves
- Sending to a customer, posting to accounting, a payment or deleting: the agent prepares, a person decides.
- Planted instruction
- cannot bypass approval
- Text in an email or document can contain a planted instruction that the model may not always recognise. So sensitive actions never depend on the model alone: they always wait for a person's approval.
- Record
- every step
- The log holds the input, the tools used, the outputs and the person's decision. It serves for tracing errors and for evaluation.
- Data sent to the model
- minimum
- We send the model only the data a given step needs. We choose the model and where data is processed according to the data the agent works with.
Process: from task to agent in operation
Every step has a deliverable that you can see and comment on.
Consultation and choosing the task
We discuss where you lose the most time and pick the task where an agent pays off first. We also check whether simpler automation would do.
OutputRecommended solution and a non-binding quote
Task map and harness design
We describe inputs, steps, systems and decisions. We design agent roles, tools, permissions, checkpoints and the points where a person approves.
OutputAgent design including permissions and checkpoints
Test set
From your real cases we build a set to measure the agent against, and define which mistake is unacceptable.
OutputSet of test cases and success criteria
Prototype on your data
We build a first version and run it on the test set. We show you the results including the errors and adjust the rules.
OutputEvaluation of the prototype on the test set
Pilot with approvals
The agent runs in live operation, but a person approves everything important. From the log we see where it goes wrong and refine the rules.
OutputAgent in pilot operation with a record of steps
Operation and improvement
Based on the pilot we widen what the agent may do alone, while a person still approves sensitive actions. After every change we re-test on the test set and watch costs.
OutputAgent in operation with regular evaluation
We run multi-step AI ourselves
The article generator in this website's admin works in steps: research, plan, writing by section and checks in code. It drops findings without a source and never publishes on its own, because a person decides on release.
- Own productDotazioAn AI chatbot that answers only from the material you provide and cites a source with every answer. Where it has no material, it does not invent and points to a contact.View
- Own productKurikula.aiCompares a school education programme with the national framework (RVP) and proposes changes, each with an RVP code. The teacher accepts, edits or rejects it, and only approved changes go into the document.View
- Own productChytrej článekA production line for SEO articles from keyword to draft: the draft passes 18 checks and reaches publication only after an editor approves it. Every step is logged.View
When an AI agent makes sense and when it does not
An agent makes sense where people retype and look up data across several systems and the input has no fixed form.
An agent pays off when
- The task repeats, but the inputs have no fixed form: emails, documents, enquiries written in people's own words.
- Someone currently retypes and looks up data across several systems.
- Handling enquiries
- Back office and documents
An agent does not make sense when
- The process is the same every time and the inputs have a fixed format. Classic automation is enough: it is cheaper and easier to check.
- Answering questions is enough. An AI chatbot built on your documents is better suited to that.
- The task comes up only a few times a year and the development would not pay for itself.
- A mistake would be irreversible and nobody has capacity to check the outputs.
Frequently asked questions
Let's talk through your case.
Describe a task that someone currently does by hand across several systems. In a consultation we assess whether automation is enough or an agent is needed, where a person has to decide, and prepare a non-binding quote. We communicate in English.
