https://speakerdeck.com/abedmatini 2026-08-12 00:41:34 -0400 From BrowserStack Meetup Cape Town (BBD, Century City, 3 Sep 2026) — Introduction to AI-Native Development Workflows. A human-gated engineering loop: Linear ticket via MCP → reproduce → AI-assisted fix (model-agnostic: Claude, Cursor, Grok) → lint / FE+BE / Playwright → BrowserStack real devices via Playwright SDK + Local tunnel → human check → PR → report back to Linear. Not full automation. Three human gates (pick it up, reproduce, ship). Cheap local proof before cloud devices. MCP is for Linear only. Event: https://luma.com/browse-6tdk From BrowserStack Meetup Cape Town (BBD, Century City, 3 Sep 2026) — Introduction to AI-Native Development Workflows. A human-gated engineering loop: Linear ticket via MCP → reproduce → AI-assisted fix (model-agnostic: Claude, Cursor, Grok) → lint / FE+BE / Playwright → BrowserStack real devices via Playwright SDK + Local tunnel → human check → PR → report back to Linear. Not full automation. Three human gates (pick it up, reproduce, ship). Cheap local proof before cloud devices. MCP is for Linear only. Event: https://luma.com/browse-6tdk Fri, 04 Sep 2026 00:00:00 -0400 https://speakerdeck.com/abedmatini/the-ai-native-development-loop-a-ticket-comes-in-a-verified-change-goes-out https://speakerdeck.com/abedmatini/the-ai-native-development-loop-a-ticket-comes-in-a-verified-change-goes-out A framework-free approach to production RAG: parsing documents locally to avoid the "multimodal tax" of vision-API costs, running hybrid dense + sparse retrieval directly in PostgreSQL with Reciprocal Rank Fusion (no vector database, no LangChain), and wiring up full observability with Langfuse. Covers the schema, the raw SQL, agent mode vs. direct RAG, upload and query-time guardrails, and the economics of architecture-first optimization over prompt engineering. Fully reproducible via GitHub Codespaces. Originally presented at AI Engineer World's Fair 2026, Online Track. A framework-free approach to production RAG: parsing documents locally to avoid the "multimodal tax" of vision-API costs, running hybrid dense + sparse retrieval directly in PostgreSQL with Reciprocal Rank Fusion (no vector database, no LangChain), and wiring up full observability with Langfuse. Covers the schema, the raw SQL, agent mode vs. direct RAG, upload and query-time guardrails, and the economics of architecture-first optimization over prompt engineering. Fully reproducible via GitHub Codespaces. Originally presented at AI Engineer World's Fair 2026, Online Track. Wed, 19 Aug 2026 00:00:00 -0400 https://speakerdeck.com/abedmatini/bypassing-the-multimodal-tax-framework-free-hybrid-rag-raw-sql-rrf-and-live-ui-telemetry https://speakerdeck.com/abedmatini/bypassing-the-multimodal-tax-framework-free-hybrid-rag-raw-sql-rrf-and-live-ui-telemetry A practical roadmap for building RAG systems under real-world South African constraints — POPIA compliance, load shedding, and ZAR/USD cost volatility. Walks through a 7-phase maturity model from simple local RAG through hybrid search, multimodal parsing, multi-step reasoning, GraphRAG, and agentic RAG, plus a governance framework for role-based access control and a benchmarking approach for proving your system isn't hallucinating. Originally presented at DevConf South Africa 2026. A practical roadmap for building RAG systems under real-world South African constraints — POPIA compliance, load shedding, and ZAR/USD cost volatility. Walks through a 7-phase maturity model from simple local RAG through hybrid search, multimodal parsing, multi-step reasoning, GraphRAG, and agentic RAG, plus a governance framework for role-based access control and a benchmarking approach for proving your system isn't hallucinating. Originally presented at DevConf South Africa 2026. Wed, 19 Aug 2026 00:00:00 -0400 https://speakerdeck.com/abedmatini/rag-that-works-in-south-africa-cheap-fast-and-compliant-approaches-any-company-can-implement https://speakerdeck.com/abedmatini/rag-that-works-in-south-africa-cheap-fast-and-compliant-approaches-any-company-can-implement A practical breakdown of when to use Retrieval-Augmented Generation vs. fine-tuning when building GenAI applications — covering the RAG pipeline (chunking, embedding, retrieval, reranking, generation), hybrid search, and a decision framework for choosing between the two approaches. Originally presented at DevFest Cape Town 2025. A practical breakdown of when to use Retrieval-Augmented Generation vs. fine-tuning when building GenAI applications — covering the RAG pipeline (chunking, embedding, retrieval, reranking, generation), hybrid search, and a decision framework for choosing between the two approaches. Originally presented at DevFest Cape Town 2025. Sat, 08 Nov 2025 00:00:00 -0500 https://speakerdeck.com/abedmatini/rag-vs-fine-tuning-choosing-the-right-approach-for-your-genai-app https://speakerdeck.com/abedmatini/rag-vs-fine-tuning-choosing-the-right-approach-for-your-genai-app