--- schema: 1 type: video title: >- The Factory That Dreams: 39 AI Agents, No Framework - Rushabh Doshi, Machinecraft description: >- Most AI demos are built around a toy workflow. Ira was built around a factory. This talk is the story of how a third-generation Indian machinery company built a multi-agent operating system that helps run sales, business development, recruitment, quoting, marketing, production context, email workflows, and organizational memory. Ira is not a chatbot and not a wrapper around a single framework. It is a company brain: 39 bounded specialist agents, Athena as orchestrator, a 17-stage request pipeline, Qdrant for document memory, Neo4j for relationships, Mem0 for long-term semantic memory, Postgres for CRM and recruiting data, Redis for coordination, and Cursor as the operating cockpit. The deeper lesson is architectural: companies do not need generic AI assistants. They need digital brains grounded in their own documents, relationships, processes, and values. I will show how Ira ingests company files through a "digestive system", routes work through a pantheon of agents, verifies claims through immune-system style guardrails, learns through memory and corrections, and "dreams" through a nightly consolidation cycle. I will also explain why we gave Ira a SOUL.md: a philosophical constitution based on Anekantavada, Syadvada, Svadharma, and operational truthfulness. The talk ends with the Fork My Brain thesis: the right way to build company AI is not to sell another SaaS dashboard. It is to send a special-ops AI team inside a company for a week, map the business from the inside out, ingest the right files into Qdrant and Neo4j, wire the operational databases, and leave behind a forkable digital brain that employees can run through Cursor and LLMs. Speakers: - Rushabh Doshi (Machinecraft / Fork My Brain): Rushabh Doshi builds and operates Ira, a multi-agent AI operating system for Machinecraft, an Indian thermoforming machinery manufacturer, combining Cursor, LLMs, retrieval, memory, and business operations into one living company brain. LinkedIn: https://www.linkedin.com/in/rdd0101/ GitHub: https://github.com/doshirush1901 canonical: >- https://liquidgold.cc/channel/aidotengineer/explore/video/the-factory-that-dreams-39-ai-agents-no-framework-r-9f0c74f16bc4 markdown: >- https://liquidgold.cc/channel/aidotengineer/video/the-factory-that-dreams-39-ai-agents-no-framework-r-9f0c74f16bc4.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T07:57:13.220Z' language: null children: [] videoId: jtzh-GBXBWc durationSeconds: 598 publishedAt: '2026-07-11T20:00:27.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 0 endSeconds: 11 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=0' heldReason: rights - ordinal: 1 text: null startSeconds: 11 endSeconds: 133 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=11' heldReason: rights - ordinal: 2 text: null startSeconds: 11 endSeconds: 133 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=11' heldReason: rights - ordinal: 3 text: null startSeconds: 144 endSeconds: 276 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=144' heldReason: rights - ordinal: 4 text: null startSeconds: 144 endSeconds: 276 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=144' heldReason: rights - ordinal: 5 text: null startSeconds: 144 endSeconds: 276 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=144' heldReason: rights - ordinal: 6 text: null startSeconds: 144 endSeconds: 276 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=144' heldReason: rights - ordinal: 7 text: null startSeconds: 276 endSeconds: 289 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=276' heldReason: rights - ordinal: 8 text: null startSeconds: 289 endSeconds: 392 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=289' heldReason: rights - ordinal: 9 text: null startSeconds: 289 endSeconds: 392 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=289' heldReason: rights - ordinal: 10 text: null startSeconds: 289 endSeconds: 392 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=289' heldReason: rights - ordinal: 11 text: null startSeconds: 392 endSeconds: 404 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=392' heldReason: rights - ordinal: 12 text: null startSeconds: 404 endSeconds: 493 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=404' heldReason: rights - ordinal: 13 text: null startSeconds: 404 endSeconds: 493 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=404' heldReason: rights - ordinal: 14 text: null startSeconds: 404 endSeconds: 493 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=404' heldReason: rights - ordinal: 15 text: null startSeconds: 493 endSeconds: 505 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=493' heldReason: rights - ordinal: 16 text: null startSeconds: 493 endSeconds: 505 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=493' heldReason: rights - ordinal: 17 text: null startSeconds: 505 endSeconds: 598 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=505' heldReason: rights - ordinal: 18 text: null startSeconds: 505 endSeconds: 598 watch: 'https://liquidgold.cc/watch/jtzh-GBXBWc?t=505' heldReason: rights --- # The Factory That Dreams: 39 AI Agents, No Framework - Rushabh Doshi, Machinecraft Most AI demos are built around a toy workflow. Ira was built around a factory. This talk is the story of how a third-generation Indian machinery company built a multi-agent operating system that helps run sales, business development, recruitment, quoting, marketing, production context, email workflows, and organizational memory. Ira is not a chatbot and not a wrapper around a single framework. It is a company brain: 39 bounded specialist agents, Athena as orchestrator, a 17-stage request pipeline, Qdrant for document memory, Neo4j for relationships, Mem0 for long-term semantic memory, Postgres for CRM and recruiting data, Redis for coordination, and Cursor as the operating cockpit. The deeper lesson is architectural: companies do not need generic AI assistants. They need digital brains grounded in their own documents, relationships, processes, and values. I will show how Ira ingests company files through a "digestive system", routes work through a pantheon of agents, verifies claims through immune-system style guardrails, learns through memory and corrections, and "dreams" through a nightly consolidation cycle. I will also explain why we gave Ira a SOUL.md: a philosophical constitution based on Anekantavada, Syadvada, Svadharma, and operational truthfulness. The talk ends with the Fork My Brain thesis: the right way to build company AI is not to sell another SaaS dashboard. It is to send a special-ops AI team inside a company for a week, map the business from the inside out, ingest the right files into Qdrant and Neo4j, wire the operational databases, and leave behind a forkable digital brain that employees can run through Cursor and LLMs. Speakers: - Rushabh Doshi (Machinecraft / Fork My Brain): Rushabh Doshi builds and operates Ira, a multi-agent AI operating system for Machinecraft, an Indian thermoforming machinery manufacturer, combining Cursor, LLMs, retrieval, memory, and business operations into one living company brain. LinkedIn: https://www.linkedin.com/in/rdd0101/ GitHub: https://github.com/doshirush1901 Canonical: https://liquidgold.cc/channel/aidotengineer/explore/video/the-factory-that-dreams-39-ai-agents-no-framework-r-9f0c74f16bc4 ยท 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 (0:00 to 2:13) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 1: Document excerpt (2:13 to 4:36) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 2: Document excerpt (4:36 to 6:32) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 3: Document excerpt (6:32 to 8:13) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 4: Document excerpt (8:13 to 9:58) > Held: transcript rights do not permit this chunk's text.