---
schema: 1
type: video
title: 'Agentic Search for Context Engineering — Leonie Monigatti, Elastic'
description: >-
  Getting context into an LLM is not just a retrieval problem. It is a search
  problem. This workshop digs into the part of context engineering that usually
  gets waved away: how agents actually decide what to pull from files,
  databases, memory, and the web, and why that choice often matters more than
  the model itself. Across semantic search, general-purpose database tools,
  shell-based retrieval, and agent skills, Leonie Monigatti shows where each
  search interface works, where it breaks, and how to combine them into a more
  effective retrieval stack. If you're building agents and trying to make
  retrieval less brittle, this is a practical guide to the real mechanics behind
  agentic search. Workshop repo:
  https://github.com/iamleonie/workshop-agentic-search Speaker info: -
  https://x.com/helloiamleonie - https://www.linkedin.com/in/804250ab/
  Timestamps: 0:00:00 - Introduction and Welcome 0:00:51 - Defining Context
  Engineering and the role of Search 0:02:21 - Historical context: From RAG to
  Agentic RAG 0:04:30 - Context sources (local files, memory, databases, web)
  0:06:30 - Introduction to the Shell tool and its versatility 0:08:50 - Failure
  modes in agentic search 0:10:41 - The importance of tool descriptions and
  parameter design 0:13:53 - Code Demo: Simple semantic search and its
  limitations 0:23:26 - Code Demo: General purpose database query (ESQL) 0:28:36
  - Code Demo: Adding Agent Skills for better interaction 0:34:42 - Code Demo:
  Using the Shell tool for file system retrieval 0:41:26 - Code Demo:
  Integrating custom CLIs (Gina Grap) 0:44:42 - Practical recommendations for
  building a search tool stack 0:49:16 - Q&A Session begins --- Watch along with
  the corrected transcript, summary, timestamps and resources on this talk's
  official AIE page:
  https://ai.engineer/talks/ynJyIKwjonM-agentic-search-for-context-engineering
  Join our upcoming AI Engineer conferences (see https://ai.engineer landing
  page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs
  and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference
  returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS
  2026 in Sydney ---
canonical: >-
  https://liquidgold.cc/channel/aidotengineer/explore/video/agentic-search-for-context-engineering-leonie-monig-f7a1c658d5e0
markdown: >-
  https://liquidgold.cc/channel/aidotengineer/video/agentic-search-for-context-engineering-leonie-monig-f7a1c658d5e0.md
llms: null
parent: 'https://liquidgold.cc/channel/aidotengineer.md'
channel: aidotengineer
updated: '2026-10-24T14:12:03.196Z'
language: null
children: []
videoId: ynJyIKwjonM
durationSeconds: 3793
publishedAt: '2026-05-08T13:00:06.000Z'
searchChunks:
  - ordinal: 0
    text: null
    startSeconds: 62
    endSeconds: 143
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=62'
    heldReason: rights
  - ordinal: 1
    text: null
    startSeconds: 62
    endSeconds: 143
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=62'
    heldReason: rights
  - ordinal: 2
    text: null
    startSeconds: 155
    endSeconds: 279
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=155'
    heldReason: rights
  - ordinal: 3
    text: null
    startSeconds: 155
    endSeconds: 279
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=155'
    heldReason: rights
  - ordinal: 4
    text: null
    startSeconds: 279
    endSeconds: 291
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=279'
    heldReason: rights
  - ordinal: 5
    text: null
    startSeconds: 291
    endSeconds: 394
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=291'
    heldReason: rights
  - ordinal: 6
    text: null
    startSeconds: 405
    endSeconds: 537
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=405'
    heldReason: rights
  - ordinal: 7
    text: null
    startSeconds: 405
    endSeconds: 537
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=405'
    heldReason: rights
  - ordinal: 8
    text: null
    startSeconds: 405
    endSeconds: 537
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=405'
    heldReason: rights
  - ordinal: 9
    text: null
    startSeconds: 550
    endSeconds: 645
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=550'
    heldReason: rights
  - ordinal: 10
    text: null
    startSeconds: 645
    endSeconds: 656
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=645'
    heldReason: rights
  - ordinal: 11
    text: null
    startSeconds: 656
    endSeconds: 833
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=656'
    heldReason: rights
  - ordinal: 12
    text: null
    startSeconds: 957
    endSeconds: 1084
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=957'
    heldReason: rights
  - ordinal: 13
    text: null
    startSeconds: 1195
    endSeconds: 1307
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=1195'
    heldReason: rights
  - ordinal: 14
    text: null
    startSeconds: 1424
    endSeconds: 1539
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=1424'
    heldReason: rights
  - ordinal: 15
    text: null
    startSeconds: 1551
    endSeconds: 1643
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=1551'
    heldReason: rights
  - ordinal: 16
    text: null
    startSeconds: 1643
    endSeconds: 1656
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=1643'
    heldReason: rights
  - ordinal: 17
    text: null
    startSeconds: 1737
    endSeconds: 1840
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=1737'
    heldReason: rights
  - ordinal: 18
    text: null
    startSeconds: 1977
    endSeconds: 2090
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=1977'
    heldReason: rights
  - ordinal: 19
    text: null
    startSeconds: 2101
    endSeconds: 2207
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=2101'
    heldReason: rights
  - ordinal: 20
    text: null
    startSeconds: 2207
    endSeconds: 2219
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=2207'
    heldReason: rights
  - ordinal: 21
    text: null
    startSeconds: 2360
    endSeconds: 2487
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=2360'
    heldReason: rights
  - ordinal: 22
    text: null
    startSeconds: 2498
    endSeconds: 2686
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=2498'
    heldReason: rights
  - ordinal: 23
    text: null
    startSeconds: 2698
    endSeconds: 2956
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=2698'
    heldReason: rights
  - ordinal: 24
    text: null
    startSeconds: 2698
    endSeconds: 2956
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=2698'
    heldReason: rights
  - ordinal: 25
    text: null
    startSeconds: 2967
    endSeconds: 3100
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=2967'
    heldReason: rights
  - ordinal: 26
    text: null
    startSeconds: 2967
    endSeconds: 3100
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=2967'
    heldReason: rights
  - ordinal: 27
    text: null
    startSeconds: 3319
    endSeconds: 3424
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=3319'
    heldReason: rights
  - ordinal: 28
    text: null
    startSeconds: 3436
    endSeconds: 3537
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=3436'
    heldReason: rights
  - ordinal: 29
    text: null
    startSeconds: 3548
    endSeconds: 3638
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=3548'
    heldReason: rights
  - ordinal: 30
    text: null
    startSeconds: 3650
    endSeconds: 3793
    watch: 'https://liquidgold.cc/watch/ynJyIKwjonM?t=3650'
    heldReason: rights
---


# Agentic Search for Context Engineering — Leonie Monigatti, Elastic

Getting context into an LLM is not just a retrieval problem. It is a search problem. This workshop digs into the part of context engineering that usually gets waved away: how agents actually decide what to pull from files, databases, memory, and the web, and why that choice often matters more than the model itself. Across semantic search, general-purpose database tools, shell-based retrieval, and agent skills, Leonie Monigatti shows where each search interface works, where it breaks, and how to combine them into a more effective retrieval stack. If you're building agents and trying to make retrieval less brittle, this is a practical guide to the real mechanics behind agentic search. Workshop repo: https://github.com/iamleonie/workshop-agentic-search Speaker info: - https://x.com/helloiamleonie - https://www.linkedin.com/in/804250ab/ Timestamps: 0:00:00 - Introduction and Welcome 0:00:51 - Defining Context Engineering and the role of Search 0:02:21 - Historical context: From RAG to Agentic RAG 0:04:30 - Context sources (local files, memory, databases, web) 0:06:30 - Introduction to the Shell tool and its versatility 0:08:50 - Failure modes in agentic search 0:10:41 - The importance of tool descriptions and parameter design 0:13:53 - Code Demo: Simple semantic search and its limitations 0:23:26 - Code Demo: General purpose database query (ESQL) 0:28:36 - Code Demo: Adding Agent Skills for better interaction 0:34:42 - Code Demo: Using the Shell tool for file system retrieval 0:41:26 - Code Demo: Integrating custom CLIs (Gina Grap) 0:44:42 - Practical recommendations for building a search tool stack 0:49:16 - Q\&A Session begins --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/ynJyIKwjonM-agentic-search-for-context-engineering Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney ---

Canonical: https://liquidgold.cc/channel/aidotengineer/explore/video/agentic-search-for-context-engineering-leonie-monig-f7a1c658d5e0 · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md)

> Search chunk text is held until public-source provenance is verified.

## Document chunks

> Missing: no stored document chunks are available.