War Story of putting AI Agents into Production [ukr]

Nowadays, everyone is creating AI Assistants to help us in our day-to-day activities and "vibe coding" nice and shiny demo apps. However, when bringing AI Assistants to life in production—especially for use by citizens of a Gov Portal—it becomes clear that creating the AI Agent itself is only 10% of the effort required. The other 90% is spent on addressing cross-cutting concerns and meeting the requirements of different stakeholders.

This talk will be based on the speaker's own experience of putting citizen AI Assistants for a Gov Portal (built on top of an AI Agentic Platform) into production. He will discuss the challenges his team faced, concerns raised by different groups of stakeholders, important NFRs and quality attributes of the solution, and possible approaches to addressing these challenges. The talk will provide useful tips, offer a broader perspective on real-world challenges, and encourage critical thinking.

This talk will be interesting for professionals in various roles who want to gain a broader understanding of real-world challenges and improve their critical thinking.

Among other topics, the speaker will cover:
- Naive chatbot implementation vs. scalable and mature implementation
- Benefits and drawbacks of using an AI Agentic Platform vs. custom implementation
- Choice of Public LLM vs. Private LLM
- Performance and quality challenges
- Infrastructure
- Costs
- Error handling
- UI/UX
- Guardrails and protection against misuse and DDoS attacks
- Observability
- Multilingual support
- Testing and evaluation framework
- PII data handling
- And more...