Turning My Obsidian Vault Into a Local AI Engineer
Conference Context
- Date/time: 2026-06-29 · 1:15pm-2:15pm
- Track/room: Workshops Day 1 · Track 8
- Speaker(s): Filip Makraduli
- Session type/status: sponsor · confirmed
- Track: Workshops Day 1
- Room: Track 8
- Session type: sponsor
- Status: confirmed
Session Description
Personal knowledge bases are messy, but engineering agents need memory: decisions, docs, TODOs, old PRs, architecture notes, incident notes. This talk shows how I made an Obsidian vault usable by an agent using local-first retrieval and small-model inference. The point is not “chat with notes”; it is how to build durable, inspectable agent memory.
Media Evidence
The Small Model Infrastructure Nobody Built (So We Did) — Filip Makraduli, Superlinked (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).
- Source video:
youtube-qdh_x-uRs9g - Slide deck: Reconstructed Slides: The Small Model Infrastructure Nobody Built (So We Did) — Filip Makraduli, Superlinked — 10 visible slide image(s); 10 HTML recreation(s).
- Additional slide evidence: Slides: The Small Model Infrastructure Nobody Built (So We Did) — Filip Makraduli, Superlinked
- Slide-derived themes for
youtube-qdh_x-uRs9g: makes, embedding, learning, first, principles, models, production, best.
Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.
Media Signals
youtube-qdh_x-uRs9g— 5 slide-derived text signals- Slide-derived themes for
youtube-qdh_x-uRs9g: makes, embedding, learning, first, principles, models, production, best. - Evidence links for
youtube-qdh_x-uRs9g: youtube qdh_x uRs9g, youtube qdh_x uRs9g slides, youtube qdh_x uRs9g reconstructed slides
Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.
Transcript Status
Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.
People
Supporting Slides
- youtube qdh_x uRs9g slides — extracted from the related public AI Engineer video.
Synthesis
Synthesized Breakdown
Turning My Obsidian Vault Into a Local AI Engineer ## Conference Context - Date/time: 2026-06-29 · 1:15pm-2:15pm - Track/room: Workshops Day 1 · Track 8 - Speaker(s): Filip Makraduli - Session type/status: sponsor · confirmed - Track: Workshops Day 1 - Room: Track 8 - Session type: sponsor - Status: confirmed ## Session Description Personal knowledge bases are messy, but engineering agents need memory: decisions, docs, TODOs, old PRs, architecture notes, incident notes. This talk shows how I made an Obsidian vault usable by an agent using local-first retrieval and small-model inference. The point is not “chat with notes”; it is how to build durable, inspectable agent memory. ## Media Evidence The Small Model Infrastructure Nobody Built (So We Did) — Filip Makraduli, Superlinked (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).
Speaker And Company Context
- Filip Makraduli — Founding Member of Technical Staff at Superlinked.
Topics Covered
Derived Links And Source Material
- youtube qdh_x uRs9g — related YouTube source page.
- youtube qdh_x uRs9g slides — slide evidence.
- youtube qdh_x uRs9g reconstructed slides — slide evidence.
Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.
Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.