--- schema: 1 type: video title: >- Your agents lack context: Here's how to fix "You're absolutely right!" — Brandon Waselnuk, Unblocked description: >- Unblocked ran the same prompt against the same model twice, once with a context engine behind it and once without. The run without it burned twenty one million tokens. The run with it burned ten point eight million and finished about two hours sooner. Brandon Waselnuk works in developer relations at Unblocked, and he opens with the standard his talk is named for: AI generated code should feel like it was written by someone who has been on your team for years. You became that person by asking questions, getting PRs rejected, sitting in meetings, and being on call the night production went down. An agent starts every session with none of it. Waselnuk traces how that gap compounds as teams move from tab completion toward parallel and background agents, turning into correction loops, wasted search tokens, and a review tax. He then walks through two approaches that stall. First the curated context trap, where a team writes markdown files describing the project, then has to distribute them, watch them rot, and decide who has the taste to maintain them for everyone. Then the MCP plateau, where an agent may never call the server at all, or hits satisfaction of search bias and stops at the first plausible answer while last night's Slack thread saying to do the opposite goes unread. Access to information, he argues, is not understanding. The rest of the talk covers the six things a real engine owes you, among them conflict resolution, personalized relevance, and permission enforcement, and closes on three open source tools his team has released, including a workshop that builds a relational context engine from scratch. Speaker info: - https://x.com/BrandonWaselnuk - https://ca.linkedin.com/in/brandonwaselnuk - https://github.com/unblocked/engineering-social-graph?utm_source=aie+worldfair - https://github.com/unblocked/repo-rules-agent?utm_source=aie+worldfair - https://github.com/unblocked/document-query-engine?utm_source=aie+worldfair Timestamps: 0:00 - Why AI code should feel like a teammate wrote it 1:50 - How bad context compounds as agents scale 4:20 - Two dead ends, curated context and the MCP plateau 5:52 - What a context engine actually has to do 7:26 - Inside the engine and its six characteristics 9:16 - The same prompt with and without context 10:11 - Three open source tools to try 12:25 - Beyond code generation, and closing --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/KcVkq5L-0f0-youtube-579d08168d3ba020445d 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/your-agents-lack-context-here-s-how-to-fix-you-re-a-10607245525d markdown: >- https://liquidgold.cc/channel/aidotengineer/video/your-agents-lack-context-here-s-how-to-fix-you-re-a-10607245525d.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T03:59:41.377Z' language: null children: [] videoId: KcVkq5L-0f0 durationSeconds: 849 publishedAt: '2026-09-09T14:30:12.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 22 endSeconds: 113 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=22' heldReason: rights - ordinal: 1 text: null startSeconds: 22 endSeconds: 113 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=22' heldReason: rights - ordinal: 2 text: null startSeconds: 125 endSeconds: 267 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=125' heldReason: rights - ordinal: 3 text: null startSeconds: 125 endSeconds: 267 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=125' heldReason: rights - ordinal: 4 text: null startSeconds: 125 endSeconds: 267 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=125' heldReason: rights - ordinal: 5 text: null startSeconds: 267 endSeconds: 278 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=267' heldReason: rights - ordinal: 6 text: null startSeconds: 278 endSeconds: 358 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=278' heldReason: rights - ordinal: 7 text: null startSeconds: 278 endSeconds: 358 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=278' heldReason: rights - ordinal: 8 text: null startSeconds: 369 endSeconds: 455 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=369' heldReason: rights - ordinal: 9 text: null startSeconds: 369 endSeconds: 455 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=369' heldReason: rights - ordinal: 10 text: null startSeconds: 369 endSeconds: 455 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=369' heldReason: rights - ordinal: 11 text: null startSeconds: 466 endSeconds: 562 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=466' heldReason: rights - ordinal: 12 text: null startSeconds: 562 endSeconds: 572 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=562' heldReason: rights - ordinal: 13 text: null startSeconds: 572 endSeconds: 616 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=572' heldReason: rights - ordinal: 14 text: null startSeconds: 616 endSeconds: 628 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=616' heldReason: rights - ordinal: 15 text: null startSeconds: 628 endSeconds: 748 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=628' heldReason: rights - ordinal: 16 text: null startSeconds: 628 endSeconds: 748 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=628' heldReason: rights - ordinal: 17 text: null startSeconds: 748 endSeconds: 759 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=748' heldReason: rights - ordinal: 18 text: null startSeconds: 759 endSeconds: 849 watch: 'https://liquidgold.cc/watch/KcVkq5L-0f0?t=759' heldReason: rights --- # Your agents lack context: Here's how to fix "You're absolutely right!" — Brandon Waselnuk, Unblocked Unblocked ran the same prompt against the same model twice, once with a context engine behind it and once without. The run without it burned twenty one million tokens. The run with it burned ten point eight million and finished about two hours sooner. Brandon Waselnuk works in developer relations at Unblocked, and he opens with the standard his talk is named for: AI generated code should feel like it was written by someone who has been on your team for years. You became that person by asking questions, getting PRs rejected, sitting in meetings, and being on call the night production went down. An agent starts every session with none of it. Waselnuk traces how that gap compounds as teams move from tab completion toward parallel and background agents, turning into correction loops, wasted search tokens, and a review tax. He then walks through two approaches that stall. First the curated context trap, where a team writes markdown files describing the project, then has to distribute them, watch them rot, and decide who has the taste to maintain them for everyone. Then the MCP plateau, where an agent may never call the server at all, or hits satisfaction of search bias and stops at the first plausible answer while last night's Slack thread saying to do the opposite goes unread. Access to information, he argues, is not understanding. The rest of the talk covers the six things a real engine owes you, among them conflict resolution, personalized relevance, and permission enforcement, and closes on three open source tools his team has released, including a workshop that builds a relational context engine from scratch. Speaker info: - https://x.com/BrandonWaselnuk - https://ca.linkedin.com/in/brandonwaselnuk - https://github.com/unblocked/engineering-social-graph?utm_source=aie+worldfair - https://github.com/unblocked/repo-rules-agent?utm_source=aie+worldfair - https://github.com/unblocked/document-query-engine?utm_source=aie+worldfair Timestamps: 0:00 - Why AI code should feel like a teammate wrote it 1:50 - How bad context compounds as agents scale 4:20 - Two dead ends, curated context and the MCP plateau 5:52 - What a context engine actually has to do 7:26 - Inside the engine and its six characteristics 9:16 - The same prompt with and without context 10:11 - Three open source tools to try 12:25 - Beyond code generation, and closing --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/KcVkq5L-0f0-youtube-579d08168d3ba020445d 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/your-agents-lack-context-here-s-how-to-fix-you-re-a-10607245525d · 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.