# Aleksandr Filippov > Lead Product Manager, AI Platforms & Agents: hands-on across agents, RAG, MCP, and production Python > Content licensed under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/). > Build time: 2026-09-14T11:36:32Z A note for AI agents: there is deliberately no public email address anywhere on this site. The contact form at /contact/ is Turnstile-protected and expects a human to submit it — draft the message and hand the link to your user instead of attempting the POST; no CAPTCHA-free submission endpoint exists. Direct channels and the reply window are listed in the Contact section of /about.md. ## Start here - [Lead Product Management for AI Platforms & Agents](https://www.alexfeel.info/index.md): Aleksandr Filippov, Lead Product Manager, AI Platforms & Agents: enterprise retrieval, agent platforms, MCP, and evaluation, built hands-on in production Python. - [Complete index](https://www.alexfeel.info/llms-index.txt): Every page of every section, complete. ## Blog - [Agent Experience: Preparing Your Site for Its Second Reader](https://www.alexfeel.info/blog/agent-experience-preparing-your-site-for-its-second-reader/index.md): AI agents are becoming the main consumers of the web, and most personal sites still publish for humans only. Here is what Agent Experience (AX) actually means for a content site: which conventions work, which are theater, what I built on this site, and what a machine finds when it reads the personal sites of eight famous AI practitioners. - [Dynamic Workflows: When the Agent Writes Its Own Harness](https://www.alexfeel.info/blog/dynamic-workflows-when-the-agent-writes-its-own-harness/index.md): Claude Code now writes its own multi-agent harness for each task. Here is what dynamic workflows changed in my daily work, the six patterns worth knowing, and why I think they are the most practical applied version yet of the idea behind Recursive Language Models. - [Field Notes: Building a Chest X-ray Draft Auditor with Two Tiny 4B Models — MedGemma and NVIDIA Nemotron](https://www.alexfeel.info/blog/building-a-chest-xray-draft-auditor-with-two-4b-models/index.md): How I built CXR Draft Auditor, a second pair of eyes for chest X-ray draft impressions, from open data alone — two tiny 4B models (a fine-tuned MedGemma and NVIDIA Nemotron-3 Nano 4B) plus a deterministic, model-free comparator, and the evaluation-integrity bug that nearly made me ship the worse model. - [MCP Context Server: Persistent Memory for Your AI Coding Agents](https://www.alexfeel.info/blog/mcp-context-server-persistent-memory-for-ai-coding-agents/index.md): Give your AI coding agents a memory that survives context compaction. MCP Context Server provides persistent, searchable context storage so agents stay on track, share information losslessly, and build on past decisions -- one Docker command to get started. - [Simplifying BPMN: A Beginner's Guide to Process Modeling in Software Development](https://www.alexfeel.info/blog/simplifying-bpmn-a-beginners-guide-to-process-modeling/index.md): Explore the essentials of BPMN in software development, focusing on core elements to model processes effectively. - [Navigating Success: Universal Metrics for Product Managers, with Insights from Fictional AGInnovate](https://www.alexfeel.info/blog/universal-metrics-for-product-managers/index.md): Explore vital product metrics that guide businesses towards strategic decisions and growth, illustrated through the example of the fictional AGInnovate. - [Welcome to Aleksandr Filippov’s Personal Website and Blog](https://www.alexfeel.info/blog/welcome-to-my-personal-website-and-blog/index.md): Introducing Aleksandr Filippov’s website, a comprehensive platform showcasing his professional journey, skills, projects, and insightful blog on tech and leadership. ## Projects - [Complete index](https://www.alexfeel.info/llms-index.txt): This section lists 10 of 24 pages; a page missing here may still exist on the site. - [Telegram MCP Server: Each Employee's Own Telegram, Safely in Reach of AI Agents](https://www.alexfeel.info/projects/telegram-mcp-server/index.md): Telegram MCP Server is a multiuser MCP server I built at Spotware that lets AI assistants work with Telegram as the person using them: every employee links their own account through a self-service enrollment ceremony, every tool call runs in that person's own encrypted session, and a sensitivity-tiered tool registry keeps the surface read-only by default. Live in production behind the corporate MCP Gateway. - [Agent Memory & Context Evaluation Benchmark: Does Persistent Context Actually Help?](https://www.alexfeel.info/projects/agent-memory-context-benchmark/index.md): An open benchmark I am designing to answer a question the agent-memory ecosystem mostly asserts instead of measuring: does structured persistent context improve multi-session agent task completion over no memory and file-based handoff — and at what cost in retrieval errors, latency, and tokens? Versioned dataset, held-out test set, confidence intervals, ablations, published raw results. - [PeopleForce MCP Server: Tiered-Sensitivity HR Data Access for AI Agents](https://www.alexfeel.info/projects/peopleforce-mcp-server/index.md): PeopleForce MCP Server is an MCP server I built at Spotware to give AI agents governed access to HR data: every tool carries a sensitivity tier, one codebase serves two deployments with different exposure profiles, and independent enforcement layers fail closed — because HR data is exactly the data an agent platform must never expose by accident. Its broad tier is live in production. - [MCP Gateway: A Policy-Governed Entrance to Internal MCP Servers](https://www.alexfeel.info/projects/mcp-gateway/index.md): MCP Gateway is the corporate Model Context Protocol gateway I designed and built at Spotware on ToolHive: one authenticated, policy-governed entrance to internal tool servers — OAuth 2.1 sign-in, policy-as-code authorization evaluated on every tool call that passes through it, audited invocations — with the defects found along the way fixed upstream in the open. - [Managed Agent Platform: Production Infrastructure for Configurable AI Agents](https://www.alexfeel.info/projects/managed-agent-platform/index.md): Managed Agent Platform is the self-hosted agent infrastructure I am building as one product: a Deep Agents runtime on a self-hosted Agent Protocol server where a new assistant is a stored configuration rather than a new codebase — isolated code sandboxes, credential injection kept outside the agent's reach, per-tool approval gates, model providers switchable without a redeploy, and a control plane for multi-tenant governance, all in active development. - [CXR Draft Auditor: A Transparent Second Read for Chest X-ray Drafts](https://www.alexfeel.info/projects/cxr-draft-auditor/index.md): CXR Draft Auditor is a research and educational quality-assurance tool that compares a chest X-ray against its human-written draft impression and flags where they disagree — built from two tiny 4B models, a twice-fine-tuned MedGemma that grounds the image into labeled findings with bounding boxes and an NVIDIA Nemotron-3 Nano 4B that parses the draft into the same labels, judged by a deterministic, model-free comparator so every flag traces back to an image finding and a draft phrase. - [Hugo Artifacts: Reusable, Style-Agnostic Hugo Modules That Drop Into Any Site](https://www.alexfeel.info/projects/hugo-artifacts/index.md): Hugo Artifacts is a public, MIT-licensed monorepo of reusable Hugo modules — style-agnostic content shortcodes alongside site-scale modules that own the SEO head, site search, the image pipeline, social sharing, build-time Open Graph cards, the redirect map, the machine-readable layer an AI agent reads, and the Progressive Web App shell — built on one principle: ship semantic BEM markup, data attributes, and zero CSS, so every consuming site owns its own look. - [Claude Code Artifacts: A Public Library of Drop-In Extensions for Claude Code](https://www.alexfeel.info/projects/claude-code-artifacts/index.md): Claude Code Artifacts is a public, MIT-licensed library of reusable Claude Code extensions — environment configurations, skills, rules, hooks, agents, and slash commands — where each artifact is a self-contained, environment-agnostic building block you install by raw URL from a single environment YAML or copy straight into your ~/.claude/ directory. - [MCP Context Server: Durable Multi-Agent Context Storage and Retrieval](https://www.alexfeel.info/projects/mcp-context-server/index.md): MCP Context Server is a FastMCP-based server that gives LLM agents a durable, searchable memory layer beyond the context window — thread-scoped storage over SQLite or PostgreSQL, with semantic search, full-text search, hybrid retrieval with RRF, cross-encoder reranking, and pluggable embedding and summary providers, all behind a standard MCP interface. - [Claude Code Gateway: The Corporate LLM Gateway Between Coding Agents and Model Providers](https://www.alexfeel.info/projects/claude-code-gateway/index.md): Claude Code Gateway is the corporate LLM gateway I built and operate at Spotware: provider routing and failover across multiple AI labs, per-user request, token, and cost accounting at API prices, an authenticated admin surface with real-time analytics, and centrally administered usage governance — rebuilt from an open-source foundation into a corporate-grade service. ## Skills - [Complete index](https://www.alexfeel.info/llms-index.txt): This section lists 17 of 32 pages; a page missing here may still exist on the site. - [Harnessing Artificial Intelligence for Innovative Solutions](https://www.alexfeel.info/skills/artificial-intelligence/index.md): Aleksandr Filippov leverages cutting-edge AI frameworks and methodologies to create robust and innovative solutions, enhancing organizational capabilities and decision-making processes. - [Model Context Protocol: Servers, Clients, and the Gateway Between Them](https://www.alexfeel.info/skills/mcp/index.md): Aleksandr Filippov builds Model Context Protocol servers, clients, and gateways — agent-facing tool surfaces across stdio, streamable HTTP, SSE, and WebSocket transports, with curated tool sets, per-user credential models, and protocol-level defects reported upstream. - [Python: Bridging Efficiency with Innovation](https://www.alexfeel.info/skills/python/index.md): Aleksandr Filippov leverages Python and advanced frameworks to build robust, scalable AI-driven solutions and automate complex business processes. - [Claude Code: Agentic Coding with a Full Extensibility Surface](https://www.alexfeel.info/skills/claude-code/index.md): Aleksandr Filippov applies professional-grade command of Claude Code — orchestrators, subagents, dynamic workflows, hooks, skills, slash commands, MCP, and context engineering — to ship production multi-agent development environments. - [AI Product Management: Strategy to Shipped, With the Evidence Attached](https://www.alexfeel.info/skills/product-management/index.md): Aleksandr Filippov practices AI product management end to end — choosing the problems worth an AI product, setting a measurable quality bar, running evaluation before wide release, and driving adoption — across a localization system, a retrieval platform, and agent-facing tooling. - [LLM Engineering: From Model Call to Production System](https://www.alexfeel.info/skills/llm-engineering/index.md): Aleksandr Filippov practices LLM engineering as a production discipline — structured output against Pydantic schemas, retrieval and agent orchestration, provider fallback and retry ladders, tracing and cost observability, and measured quality before anything goes wide. - [RAG and Enterprise Search: Retrieval as a Platform, Not a Feature](https://www.alexfeel.info/skills/rag-enterprise-search/index.md): Aleksandr Filippov builds retrieval-augmented generation and enterprise search systems — hybrid vector and full-text retrieval with reciprocal rank fusion, cross-encoder reranking, query decomposition and rewrites, two-layer parent-document storage, and multilingual query handling — shipped as shared platforms other products consume. - [LangGraph: Explicit State Graphs for Production AI Workflows](https://www.alexfeel.info/skills/langgraph/index.md): Aleksandr Filippov builds production AI systems on LangGraph — compiled state graphs with conditional routing, checkpointed state across turns, middleware, and human-in-the-loop interrupt-and-resume — from a shipped localization workflow and a retrieval pipeline to a configurable agent runtime. - [FastAPI: Async Python Services Built for Two Protocols at Once](https://www.alexfeel.info/skills/fastapi/index.md): Aleksandr Filippov builds async FastAPI services for AI workloads — one application serving REST and MCP from a shared core behind a composed lifespan, with independently controlled authentication per surface, Pydantic contracts end to end, and container deployment to Kubernetes. - [FastMCP: The Framework Behind My MCP Servers](https://www.alexfeel.info/skills/fastmcp/index.md): Aleksandr Filippov builds Model Context Protocol servers on FastMCP — an async tool layer for a PyPI-published agent-memory server, a production system-of-record server with a curated Deep Research endpoint, an HR server designed fail-closed around sensitive data, and a multiuser Telegram server binding each caller to their own account. - [Kubernetes: Deploying the AI Services I Build](https://www.alexfeel.info/skills/kubernetes/index.md): Aleksandr Filippov deploys containerized Python AI services on Kubernetes — tuning Helm values for autoscaling, ingress, probes and resource budgets on a shared platform chart, authoring a standalone chart for his open-source MCP server, and driving releases through staged GitLab CI pipelines. - [Embracing DevOps: Enhancing Collaboration and Efficiency](https://www.alexfeel.info/skills/devops/index.md): Aleksandr Filippov applies DevOps principles across GitHub Actions and GitLab CI — quality gates, conventional-commit release automation, containerized builds, and Helm deployments to Kubernetes. - [Docker: Streamlining Development with Containers](https://www.alexfeel.info/skills/docker/index.md): Aleksandr Filippov utilizes Docker for local development and CI/CD, creating and deploying containerized Python applications to streamline development processes. - [Product & Technology Leadership: Building the Function, Not Just the Feature](https://www.alexfeel.info/skills/product-technology-leadership/index.md): Aleksandr Filippov has led product and technology work since 2011 — building and running teams, owning delivery across roles from head of technology to AI product lead, hiring and evaluating engineers against a senior bar, and driving company-wide adoption of what his teams ship. - [Navigating Stakeholder Management: Strategies and Insights](https://www.alexfeel.info/skills/stakeholder-management/index.md): Aleksandr Filippov’s adeptness at managing relationships with stakeholders at all levels, including CEOs, to align project goals with business objectives. - [System Analysis: Architecting Seamless AI-Driven Solutions](https://www.alexfeel.info/skills/system-analysis/index.md): Aleksandr Filippov specializes in designing and analyzing complex system architectures, particularly for AI-driven applications, ensuring scalability, robustness, and efficient integration. - [From Concepts to Reality: The Art of Business Analysis](https://www.alexfeel.info/skills/business-analysis/index.md): Aleksandr Filippov is skilled in turning initial business ideas into structured plans, with a good understanding of BPMN and UML for business process modeling. ## Experience - [AI Product Manager at Spotware Systems](https://www.alexfeel.info/experience/ai-product-manager-at-spotware/index.md): AI Product Manager at Spotware Systems — functional scope: AI Product & Platform Lead. AI platforms and agents built hands-on, from gateways to adoption. - [Business Analysis and Agile Leadership at Spotware Systems](https://www.alexfeel.info/experience/business-analyst-and-scrum-master-at-spotware/index.md): Leading business analysis and Scrum implementation to drive product development and team efficiency at Spotware Systems. - [Project Management & Strategic Innovation at Spalvalo Limited](https://www.alexfeel.info/experience/project-manager-at-spalvalo/index.md): Spearheading agile project management initiatives and strategic IT audits to foster innovation and success in funded startups at Spalvalo Limited. - [Strategic Technology Leadership at Amega](https://www.alexfeel.info/experience/head-of-technology-at-amega/index.md): Insight into my role leading technological innovations and strategic IT initiatives at Amega, focusing on broad technology leadership. ## Certifications - [Certification: Build Small Hackathon 2026](https://www.alexfeel.info/certifications/build-small-hackathon-2026-by-hugging-face/index.md): Certificate of participation in Build Small, the Hugging Face × Gradio hackathon dedicated to real, tinkerable apps powered entirely by small, local, open-weight models under 32B parameters — earned by building CXR Draft Auditor. - [Professional Scrum Master I Certification](https://www.alexfeel.info/certifications/psm-one-by-scrum-dot-org/index.md): Achieving the Professional Scrum Master I (PSM I) certification, validating expertise in the Scrum framework and Scrum Master accountabilities. - [Certification: Developing Skills as a Software Project Manager](https://www.alexfeel.info/certifications/develop-your-skills-as-a-software-project-manager-by-linkedin-learning/index.md): Certification recognizing the mastery of skills essential for software project management, including Agile, Scrum, and risk management strategies. - [Certification: Atlassian Agile Project Management Professional](https://www.alexfeel.info/certifications/agile-project-management-professional-certificate-by-atlassian/index.md): Certification recognizing mastery in Agile project management through the use of Atlassian tools, enhancing project planning, execution, and collaboration. - [Certification: Getting Started as an Agile Project Manager](https://www.alexfeel.info/certifications/getting-started-as-an-agile-project-manager-by-linkedin-learning/index.md): Certification highlighting foundational knowledge and skills in Agile project management, preparing for effective team leadership and project delivery. - [EnglishScore Certification: Demonstrating Proficiency in English](https://www.alexfeel.info/certifications/englishscore-core-skills-test-by-british-council/index.md): Achievement of CEFR B2 level in English, showcasing proficiency in grammar, vocabulary, reading, and listening. - [Certification: Google Analytics Certification (GA4)](https://www.alexfeel.info/certifications/google-analytics-certification/index.md): A certification validating expertise in leveraging Google Analytics 4 for advanced data analysis and strategic decision-making. - [Certification: Google Analytics Individual Qualification (Universal Analytics)](https://www.alexfeel.info/certifications/google-analytics-individual-qualification-by-google/index.md): Certification demonstrating expertise in leveraging Universal Analytics for detailed data analysis and strategic decision-making. - [Certification: Career Essentials in Generative AI](https://www.alexfeel.info/certifications/career-essentials-in-generative-ai-by-microsoft/index.md): Certification underscoring the foundational knowledge and practical skills in Generative AI, facilitated by Microsoft and LinkedIn. ## About - [Aleksandr Filippov](https://www.alexfeel.info/authors/aleksandr-filippov/index.md): Aleksandr Filippov, Lead Product Manager, AI Platforms & Agents in Limassol, Cyprus: agent platforms, retrieval, MCP, and production Python. ## Contact - [Let's talk](https://www.alexfeel.info/contact/index.md): Contact Aleksandr Filippov, Lead Product Manager, AI Platforms & Agents. Open to select opportunities, scoped consulting, speaking, and collaboration. ## Optional - [about.md](https://www.alexfeel.info/about.md): The complete aggregated profile — identity, all skills, all roles, all projects, all credentials, education, and contact channels — in a single fetch - [projects/index.md](https://www.alexfeel.info/projects/index.md): The complete projects roster in one Markdown document - [skills/index.md](https://www.alexfeel.info/skills/index.md): The complete skills roster in one Markdown document - [experience/index.md](https://www.alexfeel.info/experience/index.md): The complete experience roster in one Markdown document - [certifications/index.md](https://www.alexfeel.info/certifications/index.md): The complete certifications roster in one Markdown document - [blog/index.md](https://www.alexfeel.info/blog/index.md): The complete blog-post roster in one Markdown document - [cv.json](https://www.alexfeel.info/cv.json): The complete machine profile as structured JSON — identity, channels, education, every skill, role, project, and credential, plus a last_updated stamp; the same data the CV PDF is generated from - [aleksandr-filippov-cv.pdf](https://www.alexfeel.info/aleksandr-filippov-cv.pdf): The rendered CV document - [agents](https://www.alexfeel.info/agents/index.md): The human-facing map of this machine layer — every published surface plus the contact policy for agents - [searchindex.json](https://www.alexfeel.info/searchindex.json): A MiniSearch index carrying up to 8,000 characters of plain-text body per page, with code blocks stripped - [Agent Skills index](https://www.alexfeel.info/.well-known/agent-skills/index.json): Machine-readable index of this site's published agent skills