FIELD NOTE / Media Infra
The hidden 6 MB Lambda trap: compression after the limit is too late
Why API Gateway compression can make large responses look safe in testing, then still fail when Lambda enforces the raw payload limit first.
Read the noteEngineering notes, research, and projects from building VideoDB systems.
Read field notes and build stories, explore research, or browse working projects from the VideoDB team.
engineering
Technical notes and build stories from the VideoDB team.
Short production lessons, newsletter issues, and long practical posts about building with VideoDB.
latest
Field Notes
Recent production lessons and technical notes.
Browse short notes on infrastructure, reliability, latency, retrieval, and the small fixes that matter in production.
Open field notes pageVLM Evaluation
Claude, chessboards, and spatial reasoning
A small chessboard-to-FEN experiment showed where Claude vision struggles: not global understanding, but exact square-level localization.
Operations
Stop paying the TCP/TLS tax: connection pooling for Python services
Replacing bare requests calls with a shared session is not glamorous. It is table stakes for production services that call the same hosts repeatedly.
Frontend Performance
One CORS header that removed hundreds of milliseconds from repeated API calls
A practical note on preflight caching, custom auth headers, and why OPTIONS requests quietly dominate app latency on slower connections.
Operations
A Postgres backup is not real until you restore it
A short operational checklist for dump validation, restore drills, row checks, and the habits that make backups useful under pressure.
how i built
How I Built
Implementation stories from real VideoDB projects.
Follow practical build paths, architecture choices, API decisions, and tradeoffs from prototypes to working systems.
Open How I Built pageHow I built CallMD: AI call intelligence on top of VideoDB
A practical build story for a local-first call intelligence app that records calls, transcribes speakers, generates live nudges, and exports structured Markdown.
newsletter
The VideoDB Dispatch #001
Why agent runs need playable evidence, thinking tokens in vision models and agentic video streams.
research
Research
Publication-style writing and external research links.
Browse papers, preprints, talks, and research notes from the team.
Open research pageResearch note / May 15, 2026
How to Evaluate Multimodal VLMs for Your Video Use Case
A practical workflow for evaluating video VLM setups with VideoDB and Langfuse, from task definition and dataset design to tracing, scoring, and deployment decisions.
arXiv preprint arXiv:2604.11177 / 2026/4/13
Do Thought Streams Matter? Evaluating Reasoning in Gemini Vision-Language Models for Video Scene Understanding
Benchmarks how internal reasoning traces affect video scene understanding in Gemini models, including where quality gains plateau and how tight budgets increase compression-step hallucination.
projects
Projects
Selected demos, prototypes, repos, and tools.
Explore demos, experiments, and tools from the VideoDB team.
Open projects page
Built with VideoDB / By VideoDB
Call.md
Turn meetings into live agent loops.
Open project page →
Built with VideoDB / By VideoDB
Bloom
An agentic Loom alternative where recordings become inputs for AI.
Open project page →
Built with VideoDB / By VideoDB
Pair Programmer
Give coding agents live screen, voice, and system-audio context.
Open project page →
Built with VideoDB / By VideoDB
Agentic Streams
Agents research the internet and stream clean video briefings.
Open project page →