--- schema: 1 type: video title: >- Full Workshop: Build Your Own Deep Research Agents - Louis-François Bouchard, Paul Iusztin, Samridhi description: >- Deep research is one of the best ways to learn how to build real AI systems because it forces you to combine reasoning, planning, autonomy, tools, grounding, and feedback loops in a single end-to-end workflow. In this hands-on workshop, you will build an MCP-powered deep research agent that can plan a research strategy, search the web, analyze YouTube videos, gather grounded evidence, filter for relevance and trustworthiness, and synthesize its findings into a cited research artifact. Rather than treating research as just another chatbot interaction, we will frame it as a goal-directed research loop: one that can search, inspect, pivot, and progressively refine its understanding of a topic. From there, we will connect that research artifact to a lightweight technical writing workflow that turns raw findings into polished, non-sloppy technical multimodal content. This second part of the system is deliberately more constrained: you will see how research and writing require much different architectures, why exploratory work benefits from agentic behavior, and why writing quality often improves with tighter workflows, review loops, and explicit guidance. Along the way, we will show how to choose between prompts, workflows, and agents depending on the task, and how to keep the overall system practical rather than over-engineered. We will also cover observability and evaluation so the system is not only impressive in a demo, but measurable and improvable in practice. Most importantly, the workshop is grounded in experience: it distills what we learned over the past year building and using this research-and-writing pipeline internally. Attendees will leave with their own deep research agent, connecting it to a reliable technical writing workflow, and understanding the engineering tradeoffs behind both. Speaker info: - https://x.com/Whats_AI - https://www.linkedin.com/in/pauliusztin - https://www.linkedin.com/in/samridhivaid/ Timestamps (00:00) Introduction and problem space (LinkedIn content and AI slop) (03:39) Workshop overview and goals (05:01) Speaker introductions (06:09) AI engineering problem space and constraints (30:14) Tech stack and tools (Scraping, Gemini grounding, YouTube/GitHub processing) (33:32) MCP-based research agent architecture overview (34:46) Deep research agent design and tools (40:01) Code walkthrough: MCP server setup and tool registration (43:35) Deep research tool implementation and prompting (45:06) Analyze YouTube video tool implementation (47:39) Compile research tool implementation (53:35) Live demo: Running the research agent (59:56) Agent skills and workflow prompting (1:10:35) Introduction to technical writing workflow (1:15:46) Writing guidelines and control techniques (1:19:06) Few-shot prompting for writing (1:21:28) Evaluator-optimizer pattern (Writer/Reviewer) (1:28:16) Running the writing post skill (1:34:46) Observability and tracing with Opik (1:41:44) LLM Judge implementation and evaluation (1:47:56) Dataset management and F1 score computation --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/mYSRn6PC1mc-build-your-own-deep-research-agent-technical-writer 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/full-workshop-build-your-own-deep-research-agents-l-b5be8d9a8cb3 markdown: >- https://liquidgold.cc/channel/aidotengineer/video/full-workshop-build-your-own-deep-research-agents-l-b5be8d9a8cb3.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T15:05:14.021Z' language: null children: [] videoId: mYSRn6PC1mc durationSeconds: 7023 publishedAt: '2026-04-20T18:45:16.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 25 endSeconds: 229 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=25' heldReason: rights - ordinal: 1 text: null startSeconds: 391 endSeconds: 528 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=391' heldReason: rights - ordinal: 2 text: null startSeconds: 538 endSeconds: 647 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=538' heldReason: rights - ordinal: 3 text: null startSeconds: 755 endSeconds: 766 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=755' heldReason: rights - ordinal: 4 text: null startSeconds: 879 endSeconds: 959 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=879' heldReason: rights - ordinal: 5 text: null startSeconds: 969 endSeconds: 1094 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=969' heldReason: rights - ordinal: 6 text: null startSeconds: 1105 endSeconds: 1186 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=1105' heldReason: rights - ordinal: 7 text: null startSeconds: 1196 endSeconds: 1285 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=1196' heldReason: rights - ordinal: 8 text: null startSeconds: 1541 endSeconds: 1673 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=1541' heldReason: rights - ordinal: 9 text: null startSeconds: 1685 endSeconds: 1818 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=1685' heldReason: rights - ordinal: 10 text: null startSeconds: 1828 endSeconds: 2020 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=1828' heldReason: rights - ordinal: 11 text: null startSeconds: 2096 endSeconds: 2109 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=2096' heldReason: rights - ordinal: 12 text: null startSeconds: 2197 endSeconds: 2284 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=2197' heldReason: rights - ordinal: 13 text: null startSeconds: 2414 endSeconds: 2618 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=2414' heldReason: rights - ordinal: 14 text: null startSeconds: 2719 endSeconds: 2867 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=2719' heldReason: rights - ordinal: 15 text: null startSeconds: 3616 endSeconds: 3743 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=3616' heldReason: rights - ordinal: 16 text: null startSeconds: 3880 endSeconds: 4003 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=3880' heldReason: rights - ordinal: 17 text: null startSeconds: 4567 endSeconds: 4749 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=4567' heldReason: rights - ordinal: 18 text: null startSeconds: 4749 endSeconds: 4761 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=4749' heldReason: rights - ordinal: 19 text: null startSeconds: 4899 endSeconds: 5003 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=4899' heldReason: rights - ordinal: 20 text: null startSeconds: 5013 endSeconds: 5150 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=5013' heldReason: rights - ordinal: 21 text: null startSeconds: 5827 endSeconds: 5956 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=5827' heldReason: rights - ordinal: 22 text: null startSeconds: 5967 endSeconds: 6106 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=5967' heldReason: rights - ordinal: 23 text: null startSeconds: 6232 endSeconds: 6358 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=6232' heldReason: rights - ordinal: 24 text: null startSeconds: 5569 endSeconds: 5693 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=5569' heldReason: rights - ordinal: 25 text: null startSeconds: 5446 endSeconds: 5457 watch: 'https://liquidgold.cc/watch/mYSRn6PC1mc?t=5446' heldReason: rights --- # Full Workshop: Build Your Own Deep Research Agents - Louis-François Bouchard, Paul Iusztin, Samridhi Deep research is one of the best ways to learn how to build real AI systems because it forces you to combine reasoning, planning, autonomy, tools, grounding, and feedback loops in a single end-to-end workflow. In this hands-on workshop, you will build an MCP-powered deep research agent that can plan a research strategy, search the web, analyze YouTube videos, gather grounded evidence, filter for relevance and trustworthiness, and synthesize its findings into a cited research artifact. Rather than treating research as just another chatbot interaction, we will frame it as a goal-directed research loop: one that can search, inspect, pivot, and progressively refine its understanding of a topic. From there, we will connect that research artifact to a lightweight technical writing workflow that turns raw findings into polished, non-sloppy technical multimodal content. This second part of the system is deliberately more constrained: you will see how research and writing require much different architectures, why exploratory work benefits from agentic behavior, and why writing quality often improves with tighter workflows, review loops, and explicit guidance. Along the way, we will show how to choose between prompts, workflows, and agents depending on the task, and how to keep the overall system practical rather than over-engineered. We will also cover observability and evaluation so the system is not only impressive in a demo, but measurable and improvable in practice. Most importantly, the workshop is grounded in experience: it distills what we learned over the past year building and using this research-and-writing pipeline internally. Attendees will leave with their own deep research agent, connecting it to a reliable technical writing workflow, and understanding the engineering tradeoffs behind both. Speaker info: - https://x.com/Whats_AI - https://www.linkedin.com/in/pauliusztin - https://www.linkedin.com/in/samridhivaid/ Timestamps (00:00) Introduction and problem space (LinkedIn content and AI slop) (03:39) Workshop overview and goals (05:01) Speaker introductions (06:09) AI engineering problem space and constraints (30:14) Tech stack and tools (Scraping, Gemini grounding, YouTube/GitHub processing) (33:32) MCP-based research agent architecture overview (34:46) Deep research agent design and tools (40:01) Code walkthrough: MCP server setup and tool registration (43:35) Deep research tool implementation and prompting (45:06) Analyze YouTube video tool implementation (47:39) Compile research tool implementation (53:35) Live demo: Running the research agent (59:56) Agent skills and workflow prompting (1:10:35) Introduction to technical writing workflow (1:15:46) Writing guidelines and control techniques (1:19:06) Few-shot prompting for writing (1:21:28) Evaluator-optimizer pattern (Writer/Reviewer) (1:28:16) Running the writing post skill (1:34:46) Observability and tracing with Opik (1:41:44) LLM Judge implementation and evaluation (1:47:56) Dataset management and F1 score computation --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/mYSRn6PC1mc-build-your-own-deep-research-agent-technical-writer 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/full-workshop-build-your-own-deep-research-agents-l-b5be8d9a8cb3 · 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.