Agent Systems Laboratory

AI agent
architecture.
Research and practice.

How does an idea become a working system? We explore the architecture of AI agents, test solutions and share best practices - along with errors and limitations.

AGENTS EFFECT LAB01 / RESEARCH
Corporate architectural portal Agents Effect Lab
Behind every result —
an architectural decision.
We examine what
makes it work.
ENTRANCEARCHITECTURECONTROLVALUEInside the laboratory

Tools change.
Architecture remains.

We understand the structure of the system: what problem it solves, where it gets the data from, what actions it performs and how the result is checked.

01 / ENTRANCE

Let's start with the task

We determine the useful result, the initial data and the boundaries of the work. The choice of model follows them.

02 / ARCHITECTURE

Let's look at the system

Linking roles, memory and tools. We understand why it is designed this way and what can be replaced.

03 / CONTROL

We check in practice

We compare the answer with the source. We analyze failures, stopping conditions and decisions that remain up to the person.

04 / VALUE

We pass on experience

We show the progress of the research and the basis for the conclusions. We discuss where the approach is useful and where it adds complexity.

Code is a means of implementation. Understanding the process helps you choose products wisely.

Towards building your agent

Agent - assistant
for sales

We are gathering an assistant for the daily tasks of the sales department:revenue and dynamics analysis, analysis of requests based on client correspondenceand preparation of reports. The agent finds the client's needs, application status and next step, supporting the answer with calculations and quotes.

We disclose the sales forecast viabasic estimate of expected demandand replenishment of the warehouse. The agent finds a ready-made calculation based on sales history in analytical documents and helps check its assumptions.

Ten steps lead from the first calculation to event reporting.Additional voice interfaceallows you to dictate a request, confirm the recognized text and listen to the response.

10 steps to build an agentFrom accurate calculations to a working system
01

Step 01. First working agent

We connect the sales table. The agent selects the desired calculation and displays the result along with the source.

02

Step 02. Clear data structure

We set the request and response fields. Dates, names and indicators are brought into a single form and are checked.

03

Step 03. Selecting Actions and Tools

The agent sends a request to the catalogue, sales or dynamics calculation. Each route ends with a clear result.

04

Step 04. Context and memory

The system saves the manager, period and indicator. A short clarification continues the analysis taking into account the previous request.

05

Step 05. Operation and inspection log

Each action receives an identifier. Test cases help you compare results after changes.

06

Step 06. Search by documents

We analyze applications based on client correspondence and documents. The agent finds the terms and agreements, shows the exact quote and source.

07

Step 07. Connecting external systems

We add sales, balances and documents from different sources. Access rights determine the actions an agent can take.

08

Step 08. Repeatable analysis report

We collect calculations and sources into one sequence. The result opens as a ready-made report in the browser.

09

Step 09. Security and startup

We configure roles, confirmation of significant actions and backup. The working instance is validated by a user request.

10

Step 10. Events and notifications

A new file or schedule starts the report. The queue stores the event, retries the operation after a failure, and prevents duplicates.

Bonus!10+1Voice control

The task begins
with your voice.

Dictate a question about sales, requests or demand forecast, check the recognized text and confirm sending. In the agent project, the voice interface transmits the request to the same tools and allows you to listen to the ready response after setting up recognition and voiceover.

Analysis of voice interaction

Example requests

01 / Sales

“What is the total revenue for January 2026 based on sales data?”

02 / Application Analytics · RAG

“What documents are requested in application req-0003 and how did the application end according to the correspondence?”

03 / Sales forecast

“How do balances compare with the forecasted demand for the delivery date based on August data and what assumptions are included in the calculation?”

MeaningRecognize speech and show query text

ControlConfirm the text before sending it to the agent

ResultShow the result with the source and voice the answer

Understand it before
you build it!

From designing the system to checking the result. Open a single question or expand all answers at once.

Open 0 from 20

Let's continue the research

From the task —
to a working agent.

Watch the ten steps of assembling an agent - a sales assistant. Each step adds a new working opportunity.

View 10 steps