---
title: "Turning My Obsidian Vault Into a Local AI Engineer"
category: "talks"
date: "2026-06-29"
time: "1:15pm-2:15pm"
track: "Workshops Day 1"
room: "Track 8"
speakers: ["Filip Makraduli"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "Workshops Day 1"
scheduleRoom: "Track 8"
scheduleLabels: ["Workshops Day 1", "Track 8", "sponsor", "confirmed"]
---
# 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](https://www.youtube.com/watch?v=qdh_x-uRs9g) (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

- Source video: `youtube-qdh_x-uRs9g`
- Slide deck: [[youtube-qdh_x-uRs9g-reconstructed-slides|Reconstructed Slides: The Small Model Infrastructure Nobody Built (So We Did) — Filip Makraduli, Superlinked]] — 10 visible slide image(s); 10 HTML recreation(s).
![[assets/reconstructed-slides/qdh_x-uRs9g/slide-003.jpg]]
![[assets/reconstructed-slides/qdh_x-uRs9g/slide-004.jpg]]
![[assets/reconstructed-slides/qdh_x-uRs9g/slide-005.jpg]]
- Additional slide evidence: [[youtube-qdh_x-uRs9g-slides|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
- [[filip-makraduli]]

## 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](https://www.youtube.com/watch?v=qdh_x-uRs9g) (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

### Speaker And Company Context
- [[filip-makraduli|Filip Makraduli]] — Founding Member of Technical Staff at [[superlinked|Superlinked]].

### Topics Covered
- [[agentic-search]]
- [[agentic-web]]

### 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.