Documents, understood.
Connecting document processing, retrieval, and language models to turn scattered information into structured reports.
Explore the project
A world observed.
A little more understood.
Something new, built.
I’m Sayeed, a software developer in Cambridge. I work with code, AI, and automation—and care about the people on the other side of the screen.
Connecting document processing, retrieval, and language models to turn scattered information into structured reports.
Explore the project
Video annotation, object detection, and frame-level analysis. A different way of working with the visual world.
Overlay is illustrative, not a detection result.Inside the vision pipelinerequest
↳ authenticate
↳ validate
↳ process
↳ respondCONCEPTUAL REQUEST LIFECYCLEFastAPI services with authentication, validation, and logging. The engineering that lets the visible experience work.
Behind the interfaceLight on a familiar street.
A bird that pauses.
The ordinary, seen again.

What photography can teach us about attention, restraint, and designing software that feels intentional.
Read the note AI Engineering / 3 min readA practical way to separate missing evidence from weak answers—and make RAG improvements measurable.
Read the note AI Engineering / 3 min readWhy splitting documents well requires preserving meaning, not finding a universal token count.
Read the note
A WALK. A QUESTION. A NEW PERSPECTIVE.I’m Muhammad Abu Sayeed. I build software, explore AI, and photograph the world around me. The connection is curiosity: understanding what’s there, and imagining what could be.
A project, an opportunity, or a good question.
I’d like to hear it.