SVOY Tech Builds an Internal AI Agent Platform: 200 Tools and 5 Chats

The team at SVOY Tech, a fintech company, has published a write-up on Habr about its internal AI agent platform. The title gives two numbers: about 200 tools and 5 chats. The authors are building their own AI assistant inside the corporate infrastructure rather than a layer on top of a third-party API. The announcement lists three topics: the architecture "under the hood", the set of connected tools, and context management. The analysis itself is in the full article, so below is only what can be read with confidence from the announcement, plus the engineering logic around it.

Prototype vs. platform

The authors' starting point is simple: nobody is surprised by AI integration into workflows anymore, but the gap between a quick prototype and a system inside a company is huge. A prototype on an external API comes together in a couple of days. It answers questions, writes drafts and looks good in a demo. But once an agent needs internal data, access rights and real business processes, a different kind of work begins: integrations, data isolation, control over actions, reproducibility of answers.

The numbers in the title hint at where the main difficulty lies. Two hundred tools means two hundred function descriptions, parameter schemas and error scenarios. If you hand them all to the model at once, the descriptions eat a noticeable share of the context window, and picking the right call becomes less reliable. The announcement does not reveal how the five chats are divided. But the logic is readable: a chat per class of tasks narrows the set of available tools and data, and with it the space of possible errors.

What the announcement tells us

The teaser has few facts, but they are concrete:

• Developer: SVOY Tech, fintech division.
• Format: its own AI assistant and an internal platform of specialized agents.
• Scale of integration: around 200 tools.
• Interface: 5 chats, each for its own business tasks.
• Environment: corporate infrastructure, work with internal data.
• A separate section of the article: context management.

The last item is arguably the most interesting. In agent systems, context is a limited resource. Dialogue history, tool call results, document excerpts and system instructions all share it. Who decides what to keep and what to push out or compress often shapes system quality more than the choice of model does.

What to check if you are building something similar

Until details are available, the announcement works as a checklist of questions for your own project. It is worth asking them before opening the full article.

1. How many tools does the model see in a single request? If all of them at once, it makes sense to group them by task or load them on demand. 2. Is there separation by roles and scenarios? Several specialized chats are easier to test and to restrict by permissions than one universal chat. 3. How is context handled? You need explicit rules: what is stored, what is compressed, what is passed between agents. 4. Where does the data live? For fintech, whether it stays inside the perimeter determines the whole architecture. 5. How is the result measured? Without a set of test tasks and quality metrics, a growing number of tools easily turns into growing chaos.

What matters in SVOY Tech's publication is not the size of the platform but that the company shows its engineering kitchen: how a set of integrations becomes a working system. How convincing the details are will become clear from the full text, but the direction is plain. Corporate AI agents in the financial sector are moving away from a universal chat toward a set of narrow, controlled perimeters with their own context management.