--- schema: 1 type: video title: 'From MCP to Scale: Pipelines That Build Themselves — Rafael Levi, Bright Data' description: >- Scraping is not the hard part anymore. Maintaining scrapers is. This session shows what it looks like when an agent uses MCP to inspect a site, understand its structure, generate a production scraper, and keep that pipeline working when the site changes. Using Bright Data's MCP, APIs, and browser infrastructure, the flow moves from one-off extraction to something much more useful: agents that build parsers, save tokens by switching from page parsing to reusable scripts, and repair broken collection jobs without a human getting dragged in at 2am. If you're thinking about web data, automation, or agents that operate beyond a single prompt, this is a practical look at pipeline building at scale. Speaker info: - https://il.linkedin.com/in/rafael-levi - https://github.com/ScrapeAlchemist --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/zTZ0qunQXnM-from-mcp-to-scale-pipelines-that-build-themselves 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/watch/zTZ0qunQXnM' markdown: 'https://liquidgold.cc/watch/zTZ0qunQXnM.md' llms: 'https://liquidgold.cc/watch/zTZ0qunQXnM/llms.txt' parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T09:46:39.771Z' language: null children: [] videoId: zTZ0qunQXnM durationSeconds: 1526 publishedAt: '2026-06-07T14:00:12.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 26 endSeconds: 130 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=26' heldReason: rights - ordinal: 1 text: null startSeconds: 26 endSeconds: 130 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=26' heldReason: rights - ordinal: 2 text: null startSeconds: 26 endSeconds: 130 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=26' heldReason: rights - ordinal: 3 text: null startSeconds: 130 endSeconds: 140 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=130' heldReason: rights - ordinal: 4 text: null startSeconds: 140 endSeconds: 228 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=140' heldReason: rights - ordinal: 5 text: null startSeconds: 239 endSeconds: 328 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=239' heldReason: rights - ordinal: 6 text: null startSeconds: 239 endSeconds: 328 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=239' heldReason: rights - ordinal: 7 text: null startSeconds: 328 endSeconds: 338 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=328' heldReason: rights - ordinal: 8 text: null startSeconds: 338 endSeconds: 418 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=338' heldReason: rights - ordinal: 9 text: null startSeconds: 429 endSeconds: 534 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=429' heldReason: rights - ordinal: 10 text: null startSeconds: 544 endSeconds: 663 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=544' heldReason: rights - ordinal: 11 text: null startSeconds: 544 endSeconds: 663 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=544' heldReason: rights - ordinal: 12 text: null startSeconds: 663 endSeconds: 674 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=663' heldReason: rights - ordinal: 13 text: null startSeconds: 674 endSeconds: 765 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=674' heldReason: rights - ordinal: 14 text: null startSeconds: 867 endSeconds: 963 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=867' heldReason: rights - ordinal: 15 text: null startSeconds: 963 endSeconds: 977 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=963' heldReason: rights - ordinal: 16 text: null startSeconds: 977 endSeconds: 1071 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=977' heldReason: rights - ordinal: 17 text: null startSeconds: 1082 endSeconds: 1188 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=1082' heldReason: rights - ordinal: 18 text: null startSeconds: 1314 endSeconds: 1401 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=1314' heldReason: rights - ordinal: 19 text: null startSeconds: 1314 endSeconds: 1401 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=1314' heldReason: rights - ordinal: 20 text: null startSeconds: 1412 endSeconds: 1526 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=1412' heldReason: rights - ordinal: 21 text: null startSeconds: 1412 endSeconds: 1526 watch: 'https://liquidgold.cc/watch/zTZ0qunQXnM?t=1412' heldReason: rights --- # From MCP to Scale: Pipelines That Build Themselves — Rafael Levi, Bright Data Scraping is not the hard part anymore. Maintaining scrapers is. This session shows what it looks like when an agent uses MCP to inspect a site, understand its structure, generate a production scraper, and keep that pipeline working when the site changes. Using Bright Data's MCP, APIs, and browser infrastructure, the flow moves from one-off extraction to something much more useful: agents that build parsers, save tokens by switching from page parsing to reusable scripts, and repair broken collection jobs without a human getting dragged in at 2am. If you're thinking about web data, automation, or agents that operate beyond a single prompt, this is a practical look at pipeline building at scale. Speaker info: - https://il.linkedin.com/in/rafael-levi - https://github.com/ScrapeAlchemist --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/zTZ0qunQXnM-from-mcp-to-scale-pipelines-that-build-themselves 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/watch/zTZ0qunQXnM · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks --- #### Chunk 0: Document excerpt (0:15 to 2:10) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 1: Document excerpt (2:10 to 3:59) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 2: Document excerpt (3:59 to 5:38) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 3: Document excerpt (5:38 to 7:09) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 4: Document excerpt (7:09 to 8:54) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 5: Document excerpt (8:54 to 11:03) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 6: Document excerpt (11:03 to 12:45) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 7: Document excerpt (12:45 to 14:27) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 8: Document excerpt (14:27 to 16:17) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 9: Document excerpt (16:17 to 17:51) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 10: Document excerpt (17:51 to 19:48) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 11: Document excerpt (19:48 to 21:54) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 12: Document excerpt (21:54 to 23:21) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 13: Document excerpt (23:21 to 25:26) > Held: transcript rights do not permit this chunk's text.