Said Mustafa Said

AI coding assistants and developers both need exact answers about a codebase's structure, not the approximate matches an embedding search returns. Conducks is a CLI and MCP server I built that parses a codebase with Tree-sitter, builds a deterministic graph of its symbols and relationships, and stores it in a local DuckDB vault any tool can query. It replaces a guess about where code lives with a graph-verified answer: a symbol's file, line, callers, and risk score, computed the same way every time, with zero LLMs or embeddings anywhere in the analysis path.

GCE is the engine behind my own portfolio site. It reads my project, research, and education logs plus a skills registry, and computes a career rank and a 12-field capability map from pure math, no manual grading and no language model call anywhere in the scoring path. I built it to replace a gut-feel seniority claim with a number traceable back to evidence, sensor by sensor. It runs as a build script that recalculates my technical identity from source every time I add a project.

mycvpath is a CV tailoring platform I designed, built, and run myself. A user brings a CV and a job posting, and a six-agent LLM pipeline parses both, analyzes the gap between them, rewrites the CV against that specific job, and scores the result, then a separate rendering service turns the output into an ATS-safe PDF or Word document. The same pipeline is exposed as an MCP server, so an external agent such as Claude Desktop, Cursor, or a custom tool-calling agent can drive the whole flow with its own model, or ask mycvpath to run it. It replaces hours of manual CV editing per job application with a few minutes of grounded, automated rewriting, and it proves the same pipeline works both as a consumer product and as agent infrastructure.

A travel agency needed an AI assistant that could answer detailed Umrah and Hajj questions and turn them into bookings, without inventing facts. I built a standalone AI backend from scratch: a custom multi-agent RAG system that answers only from the agency's own catalogue, keeps conversations in memory, and hands ready-to-book leads to the sales flow. It let the agency give accurate, round-the-clock support in two languages, and, by their report, it lifted booking conversion.

A recruitment technology company wanted a model that could write a job posting, draft interview questions, and judge how well a CV fits a role, without paying for a frontier model API call every time. I built a four-stage pipeline that generates a labeled training set with GPT-4o, a job posting, five CVs, and five structured evaluations per posting, then fine-tuned a small open-weights model on it with a LoRA adapter. The result is a working proof of concept that shows the approach fits before committing to a larger training run.

A cloud engineering team wanted to provision AWS resources by describing them in plain English instead of remembering CLI syntax. I built an internal chat agent that does this end to end: it asks for the details it needs, writes the AWS commands, runs them, reads what AWS returns, and corrects itself on errors, one command at a time until the task is finished. This was mid-2024, before agent frameworks were common, so the tool-calling loop and the safety limits were built by hand.

A ride-hailing company's data scientists needed to run the full model lifecycle, notebooks, pipelines, experiment tracking, and a model registry, without sending data to a third-party service. I built a self-hosted MLOps platform on AWS: infrastructure as code that provisions a Kubernetes cluster, then deploys Charmed Kubeflow and Charmed MLflow onto it with an operator framework, wired together behind one dashboard. It is reproducible and runs entirely inside their own AWS account.

A mobile services company's data analysts had to write their own SQL against databases they did not fully know the shape of. I built a Streamlit tool that takes a plain-English question, identifies which database it concerns, reads that database's real schema, and asks Claude 3.5 Sonnet to generate a matching SQL query. The query runs immediately and the result shows up as a table in the same screen.

A restaurant technology company had a large stack of menu documents in inconsistent formats and needed the contents as structured data. I built a vision-model OCR pipeline that reads a menu image, sends it to Claude 3 on AWS Bedrock with a prompt that pins the output schema, and turns the reply into clean JSON with correct Turkish characters. Two model variants, Claude 3 Haiku and Claude 3 Sonnet, were built against the same prompt so the client could weigh extraction quality against cost before picking one for production.

A food ordering and menu-aggregation platform needed its two core databases, order/customer data and the menu catalog, off SQL Server and onto PostgreSQL, while staying live. I ran the migration with AWS DMS, one replication task per table across close to 190 tables, so any single table's failure never blocked the rest. The database move itself was the visible part. The harder part was everything Postgres needed that a migration tool does not carry over: sequences, indexes, and SQL Server's own procedural logic.