Video library

AI and automation in action

Webinars, demos, case studies and conversations. Watch on your schedule — learn from the people shipping AI systems in production.

10 videos4 categoriesEN · BG

Featured Videos

Build an AI Agent in Microsoft Copilot: Step by Step

Building an AI agent in Microsoft Copilot requires no programming, and Martin Kuvandzhiev, CEO of encorp.ai, walks through the whole process step by step. Together with him you build a real business agent called Invoice Processor: you upload an invoice in the chat, the agent reads it, extracts company, date, invoice number, amount, VAT, type and line items, adds them to a shared register and saves the result to SharePoint. The video covers Agent Builder, describing the agent in plain language, Instructions, Skills, Cloud Files, Knowledge Base, Suggested Prompts, testing with a real invoice, working with Excel, adding Copilot Connectors, and sharing the agent with the whole company with different permissions for using and editing. Martin explains the approach Encorp often uses: AI creates the first version, a person reviews it, and then specific business rules are added. He also lists other agents you could build the same way, such as procurement, HR, sales, compliance and internal policy assistants. Useful for managers and teams on Microsoft 365 who want a shared agent that everyone uses the same way.

Microsoft CopilotCopilot AgentsAgent Builder+5 more
November 3, 2026

Which AI to Start With in 2026: 5 Free AI Assistants Compared

Which AI to start with in 2026 is one of the most common questions Martin Kuvandzhiev, CEO of encorp.ai, hears during corporate AI training sessions, and this video answers it from the very beginning. He compares five popular AI assistants you can use for free, goes through their pros and cons, and explains how to choose the right one for you. Martin also covers how to talk to AI without being a prompt engineer (think of it as a very well-educated new employee who does not know you or your company), what everyday tasks it suits, why it sometimes invents information, and how to verify answers with web search and sources. A key part is safety: what you can share with public AI tools and what you should never upload, such as passwords, bank card data, personal ID numbers, trade secrets and confidential client contracts. The video ends with five settings to change right away, including training opt-outs, temporary chats, anonymization and two-factor authentication, plus advice on when a paid plan makes sense. Ideal for beginners and employees getting started with AI.

free AI assistantsAI for beginnersAI safety+4 more
November 3, 2026

Claude Code in Practice: Building a CRM in 40 Minutes

Claude Code can build real software, and this training shows how to create a CRM application from scratch with it. Martin Kuvandzhiev, CEO of encorp.ai, uses a modern stack of Next.js, Tailwind, Supabase, GitHub, Vercel, Mailgun and the Claude API. You see how AI plans the architecture, writes the code, creates the database, builds authentication, adds AI email writing, runs a security review and uploads the project to GitHub and Vercel. **What you will learn** - Why Claude Code differs from a standard AI chat - Which stack works best for vibe coding - How Plan Mode, Auto Mode, Accept Edits and Bypass Permissions work - Why GitHub is mandatory for AI development and why every project needs Claude.md - How to use Opus, Sonnet, Haiku and sub-agents properly - How to protect API keys, environment variables and .env files - The most common security risks in vibe coding, and how AI can audit code - When vibe coding is fine and when a developer is required The video is for founders, product managers, entrepreneurs, developers, startup teams and no-code/low-code people who want to understand how AI changes the way software products are built.

Claude CodeVibe codingCRM+4 more
November 3, 2026

AI Cybersecurity: Spot Deepfake and Phishing Scams

Martin Kuvandzhiev, CEO of encorp.ai, explains how AI is making phishing, deepfake calls, voice cloning, fake banking sites and IBAN fraud cheaper and harder to detect. Learn the practical checks and procedures businesses need to reduce cyber-fraud risk.

AI CybersecurityDeepfakePhishing+4 more
May 21, 2026

All Videos

Microsoft Copilot in 2026: Is It Finally Good?

Microsoft Copilot in 2026 is finally getting good, according to Martin Kuvandzhiev, CEO of encorp.ai, who gives a complete overview of what it can really do today. A few months ago his answer to "is Microsoft Copilot any good?" was usually "not really"; that is starting to change. The video covers Copilot Chat, AI models and modes (Auto, Quick Response, Think Deeper), Data Sources and Microsoft 365 data, SharePoint and OneDrive, document generation, image generation and editing, Notebooks as a company knowledge base, Agents, Researcher and Analyst. In a realistic task Martin asks Copilot to prepare a business offer for corporate Microsoft 365 Copilot training, first having it ask all the questions it needs, then producing an editable document. He is also candid about what he still dislikes: slow tasks, trouble switching between chats and moments when the interface seems to forget instructions. His verdict: Copilot is worth a serious look, especially if your company lives in Microsoft 365. Useful for decision makers and IT teams comparing Copilot with ChatGPT and Claude.

Microsoft CopilotMicrosoft 365Copilot review+4 more
November 3, 2026

Which AI to Start With in 2026: 5 Free AI Assistants Compared

Which AI to start with in 2026 is one of the most common questions Martin Kuvandzhiev, CEO of encorp.ai, hears during corporate AI training sessions, and this video answers it from the very beginning. He compares five popular AI assistants you can use for free, goes through their pros and cons, and explains how to choose the right one for you. Martin also covers how to talk to AI without being a prompt engineer (think of it as a very well-educated new employee who does not know you or your company), what everyday tasks it suits, why it sometimes invents information, and how to verify answers with web search and sources. A key part is safety: what you can share with public AI tools and what you should never upload, such as passwords, bank card data, personal ID numbers, trade secrets and confidential client contracts. The video ends with five settings to change right away, including training opt-outs, temporary chats, anonymization and two-factor authentication, plus advice on when a paid plan makes sense. Ideal for beginners and employees getting started with AI.

free AI assistantsAI for beginnersAI safety+4 more
November 3, 2026

How to Implement AI in Your Company: 7 Steps (Encorp AIM)

How to implement AI in your company is the question Martin Kuvandzhiev, CEO of encorp.ai, answers with Encorp AIM, the methodology Encorp uses for AI transformation in organizations. It is built on practical experience with companies in banking, fintech, telecommunications, manufacturing and other industries. The video walks through 7 phases (AI Readiness, Mobilization, Analysis and Strategy, Training, Building, Rollout and Scaling, Maintenance), 5 checkpoints and 3 core rules, including starting with the simplest working solution. Martin explains why many AI projects fail, what Shadow AI is and why people and processes matter more than technology. You will also learn how to build an AI strategy and roadmap, choose KPIs, prioritize use cases and quick wins, train employees, build an AI Champions network, measure ROI and scale. A closing section covers EU AI Act and AI Governance basics, such as an AI policy, a register of AI systems, risk assessment and documented training. Aimed at executives and managers planning AI adoption.

AI transformationAI implementationEncorp AIM+5 more
November 3, 2026

Grok Bot Review: Team of AI Agents vs Claude Cowork

This Grok Bot review comes from Martin Kuvandzhiev, CEO of encorp.ai, who tested xAI's new AI agent product for more than a week to see whether it can take over part of his daily work. Instead of a single chat assistant, Grok Bot gives you a team of specialized agents (research, email, sales, calendar, finance, PR) coordinated by a main agent, running in the cloud so tasks continue when your computer is off. In the video Martin explains the difference between Grok and Grok Bot, how agents share memory and pass tasks to each other, and builds his own PR agent that looks for media, podcasts and conferences. He also shows connecting Google Sheets and other apps, the Teach-a-Task feature, and managing work from a phone with voice instructions. He is equally open about the downsides: hallucinations, weak handling of attachments, fast-depleting limits, unclear model selection and open questions about data security. For serious professional work he still prefers Claude Cowork. Useful for managers, founders and AI enthusiasts comparing agent platforms.

Grok BotAI agentsxAI+4 more
November 3, 2026

ChatGPT Work and GPT-5.6 Models: 5 Practical Automations

ChatGPT Work with the GPT-5.6 models is the focus of this video by Martin Kuvandzhiev, CEO of encorp.ai, who shows that ChatGPT is no longer just a chat but a tool that does real work with Projects, Scheduled Tasks, a browser and skills. You will learn how GPT-5.6 Sol, Terra and Luna differ and what tasks suit each, how to organise context by client and topic with Projects, and how shared cloud folders support teamwork with AI. Martin demonstrates setting up Scheduled Tasks for repeatable processes, building a skill for a daily AI digest using different models, turning an Excel table into an interactive dashboard, and automating a morning brief from email and calendar. Chapters also cover the built-in browser with a LinkedIn demo. He is also candid about the limits he saw: bugs, the risk of a ban with aggressive automation, and high token consumption. The video suits entrepreneurs, business leaders, marketers and analysts who want practical AI automation without starting from code. It is in Bulgarian.

ChatGPT WorkGPT-5.6ChatGPT Projects+4 more
November 3, 2026

Kimi K3 Review: Agent Swarm, Deep Research and Real Tests

This Kimi K3 review by Martin Kuvandzhiev, CEO of encorp.ai, tests whether Chinese AI companies are starting to seriously compete with Claude and ChatGPT. Martin used Kimi K3 for Deep Research, financial analysis, Excel files, interactive websites, coding tasks and Agent Swarm, and after about two and a half hours had used only 13% of his plan. The video walks through Kimi Chat, Work mode, Plugins, Skills, Scheduled Tasks, Kimi Code, Deep Research and Kimi Claw, plus Agent Swarm, where Kimi creates and manages a team of specialised AI agents on its own. Real tests include a financial analysis of several large public companies, two-year forecasts and Monte Carlo simulations, an investment dashboard and an Excel file with formulas, a portfolio simulator for allocating 10,000 euro, parallel research and development agents, and a football results prediction model with 20,000 simulations. Martin also gives an important privacy warning: Kimi states that submitted information may be stored and used to improve or train models, so he uses it for public information, prototypes and experiments, not confidential or personal data. It is for professionals and teams evaluating alternatives to Claude and ChatGPT. The video is in Bulgarian.

Kimi K3Agent SwarmDeep Research+4 more
November 3, 2026

Kimi K3 vs Claude vs ChatGPT: Business Tasks Benchmark

A business tasks benchmark of Kimi K3, Claude and ChatGPT is what Martin Kuvandzhiev, CEO of encorp.ai, runs in this video. Instead of abstract benchmarks, he gives the three models the same complex business tasks, the same input files and a predefined scoring system, to see who can do work you would hand to a consultant, analyst or proposal team. Task one is analysing a complex project package: contracts, a Statement of Work, client requirements, security architecture, pricing, email correspondence and a project plan, with 22 deliberately planted contradictions and traps. Task two is building a client-ready proposal deck from discovery notes, an RFP, a service catalog, case studies, pricing model, team bios and a brand guide. Results are judged on accuracy, issues found, hallucinations, argumentation, Bulgarian language, execution time, design and readiness to send to a client. Martin's conclusion: Claude is still his pick for standard business work, while Kimi is impressive for its price but limited by speed and language quality. It is for managers, consultants and teams choosing an AI model for real work. The video is in Bulgarian.

Kimi K3ClaudeChatGPT+4 more
November 3, 2026

Kimi K3 vs Claude vs ChatGPT: Which AI Writes Better Code?

Kimi K3 vs Claude vs ChatGPT is a real zero-shot coding test run by Martin Kuvandzhiev, CEO of encorp.ai. He gives the same task, the same prompt and the same files to three leading AI coding agents: ChatGPT/Codex, Claude Code and Kimi CLI. The goal is a complete, production-ready website for a fictional conference, with a brand guide, logo, speaker and sponsor images, programme, tickets, FAQ and detailed acceptance criteria. Martin compares the results on execution time, design quality, UX and navigation, features, use of the provided assets, responsive behaviour, security issues and readiness to publish. Claude was fastest (12 min 10 s), followed by ChatGPT (18 min 33 s) and Kimi (22 min 8 s). His ranking for this task: ChatGPT, Kimi K3, Claude. He stresses this does not make ChatGPT best for every project, since this was a small, design-heavy site. He also warns not to upload company source code or confidential data to Kimi unless policy allows it. The video is for developers and teams choosing an AI coding assistant. It is in Bulgarian.

Kimi K3Claude CodeChatGPT+4 more
November 3, 2026

Google Gemini's New Features: Screen Sharing, Video, Music

Google Gemini's new features are the focus of this video by Martin Kuvandzhiev, CEO of encorp.ai. After more than six months without using Gemini seriously, because it lacked unique features compared with Claude or ChatGPT, Martin shows what has started to change. He walks through the Gemini models available, when a faster or stronger model makes sense, and how Gemini works with files, Google Drive and OCR on scanned documents in different languages. He then demonstrates real-time screen sharing, where you talk with the AI about what it sees in a shared window, and the Lasso tool for sending a specific part of the screen into the conversation. The demo also covers image generation and editing, including localizing text inside an image into Bulgarian, a 10-second branded intro with sound created from a logo and a short instruction, photo editing and style changes, and music generation. Martin's conclusion: Gemini's multimodal strengths are the best reason to give it another chance. The video is for professionals, marketers and teams comparing AI assistants and looking for practical use cases. The video is in Bulgarian.

Google GeminiAI toolsMultimodal AI+4 more
November 3, 2026

Claude Code vs Codex: Which Writes Better Code in 2026?

Claude Code vs Codex is the question for anyone choosing an AI agent for vibe coding, GitHub reviews and real product development. In this video, Martin Kuvandzhiev, CEO of encorp.ai, compares the two in practice, not only by benchmarks: daily development, large codebases, GitHub pull requests, security reviews, sub-agents, token usage and final code quality. He shows where Claude Code is stronger, where Codex has the edge and why the two do not have to be either-or. The video ends with a side-by-side test: the same landing page built separately with each tool to compare design, implementation, responsive behavior and quality. **What you will learn** - Claude Code works locally; Codex works in a cloud environment and GitHub workflow - Why benchmarks do not always match real work - Why Claude Code uses more tokens and how sub-agents help - Why Codex is strong at pull request reviews, security issues, business logic errors and race conditions - How Claude.md helps on large codebases, and where Codex creates duplicate functions - How to combine both tools The video is for developers, founders, product managers, startup teams and AI enthusiasts.

Claude CodeCodexOpenAI+4 more
November 3, 2026