Shreya is a Ph.D. student at UC Berkeley's EPIC Data Lab advised by Aditya Parameswaran. Her research focuses on advancing data systems and human-computer interaction!
This podcast dives into her latest work on the Data Agent Benchmark! This is the first benchmark testing how well agents can perform multi-step queries across multiple database systems!
We also covered DocETL and Semantic Operators, as well as how database principles can shape the future of AI agents, and why context management may be the new data management!
A lot of big takeaways from this one, I hope you find it useful!
YouTube: https://www.youtube.com/watch?v=C-fNVPYZrVg
Spotify: https://spotifycreators-web.app.link/e/juDmrVcp71b"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["shreya","shankar"],"value":"Data Agents with Shreya Shankar \u2013 Weaviate Podcast #135"}},"_tags":["story","author_CShorten","story_47661225","ask_hn"],"author":"CShorten","created_at":"2026-04-06T14:15:31Z","created_at_i":1775484931,"num_comments":0,"objectID":"47661225","points":1,"story_id":47661225,"story_text":"Hey everyone! I am SUPER EXCITED to publish a new episode of the Weaviate Podcast with Shreya Shankar on Data Agents!
Shreya is a Ph.D. student at UC Berkeley's EPIC Data Lab advised by Aditya Parameswaran. Her research focuses on advancing data systems and human-computer interaction!
This podcast dives into her latest work on the Data Agent Benchmark! This is the first benchmark testing how well agents can perform multi-step queries across multiple database systems!
We also covered DocETL and Semantic Operators, as well as how database principles can shape the future of AI agents, and why context management may be the new data management!
A lot of big takeaways from this one, I hope you find it useful!
YouTube: https://www.youtube.com/watch?v=C-fNVPYZrVg
Spotify: https://spotifycreators-web.app.link/e/juDmrVcp71b","title":"Data Agents with Shreya Shankar \u2013 Weaviate Podcast #135","updated_at":"2026-04-06T14:18:08Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"simonpure"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["shreya","shankar"],"value":"Beyond Naive RAG: Practical Advanced Methods by Hamel Husain and Shreya Shankar"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://maven.com/p/945082/beyond-naive-rag-practical-advanced-methods"}},"_tags":["story","author_simonpure","story_44832762"],"author":"simonpure","created_at":"2025-08-08T02:25:10Z","created_at_i":1754619910,"num_comments":0,"objectID":"44832762","points":1,"story_id":44832762,"title":"Beyond Naive RAG: Practical Advanced Methods by Hamel Husain and Shreya Shankar","updated_at":"2026-03-05T22:30:20Z","url":"https://maven.com/p/945082/beyond-naive-rag-practical-advanced-methods"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"pcapp"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["shreya","shankar"],"value":"
Location: Bellevue, WA (Seattle area)\n Remote: Yes, or on-site/hybrid in Eastside/Seattle-area\n Willing to relocate: No\n Technologies: TypeScript, Python, Rust, C++, Kubernetes, Docker, GCP, SQL, Neo4j, LLM evals, OpenCV, ITK, Keras, Unreal Engine, Houdini\n R\u00e9sum\u00e9/CV: https://www.petercappetto.com/resume\n GitHub: https://github.com/pcapp\n Email: peter@petercappetto.com\nCurrent projects: Hobgoblin, a hand-written Rust coding agent that speaks the Agent Client Protocol (https://github.com/pcapp/hobgoblin); Scout, a TypeScript job-search agent that scores postings with several LLMs and stores them in Neo4j; a ComfyUI node pack for visualizing CT scans (https://github.com/pcapp/comfyui-dicom-volume); and a three-node Raspberry Pi Kubernetes cluster (https://vitals.petercappetto.com). I'm also taking Hamel Husain and Shreya Shankar's AI Evals course.
Most recently I was an Engineering Manager on Pok\u00e9mon GO's internal tools at Niantic. Hands-on, I cut tooling traffic by over 80% by adding compression to an unmaintained Kubernetes operator that manages Envoy, and I architected the move of admin tooling off the game server so it could ship outside the game's two-week release cycle.
Before that, five years at PrecisionOS (surgical VR): I built the CT-scan-to-3D-mesh pipeline and the accuracy bench test behind the product's FDA Class II approval, then led the data platform team. Earlier: games and game servers in Unity, Flash, Scala/Akka, C#, and Java.
I have worked with artists much of my career and also enjoy digital content creation in motion design and 3D (currently exploring Cavalry and seeing how Blender compares to Houdini)."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: Who wants to be hired? (November 2026)"}},"_tags":["comment","author_pcapp","story_50338726"],"author":"pcapp","comment_text":"
Location: Bellevue, WA (Seattle area)\n Remote: Yes, or on-site/hybrid in Eastside/Seattle-area\n Willing to relocate: No\n Technologies: TypeScript, Python, Rust, C++, Kubernetes, Docker, GCP, SQL, Neo4j, LLM evals, OpenCV, ITK, Keras, Unreal Engine, Houdini\n R\u00e9sum\u00e9/CV: https://www.petercappetto.com/resume\n GitHub: https://github.com/pcapp\n Email: peter@petercappetto.com\nCurrent projects: Hobgoblin, a hand-written Rust coding agent that speaks the Agent Client Protocol (https://github.com/pcapp/hobgoblin); Scout, a TypeScript job-search agent that scores postings with several LLMs and stores them in Neo4j; a ComfyUI node pack for visualizing CT scans (https://github.com/pcapp/comfyui-dicom-volume); and a three-node Raspberry Pi Kubernetes cluster (https://vitals.petercappetto.com). I'm also taking Hamel Husain and Shreya Shankar's AI Evals course.
Most recently I was an Engineering Manager on Pok\u00e9mon GO's internal tools at Niantic. Hands-on, I cut tooling traffic by over 80% by adding compression to an unmaintained Kubernetes operator that manages Envoy, and I architected the move of admin tooling off the game server so it could ship outside the game's two-week release cycle.
Before that, five years at PrecisionOS (surgical VR): I built the CT-scan-to-3D-mesh pipeline and the accuracy bench test behind the product's FDA Class II approval, then led the data platform team. Earlier: games and game servers in Unity, Flash, Scala/Akka, C#, and Java.
I have worked with artists much of my career and also enjoy digital content creation in motion design and 3D (currently exploring Cavalry and seeing how Blender compares to Houdini).","created_at":"2026-11-02T22:08:53Z","created_at_i":1793657333,"objectID":"50344592","parent_id":50338726,"story_id":50338726,"story_title":"Ask HN: Who wants to be hired? (November 2026)","updated_at":"2026-11-02T22:53:31Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"edmundsauto"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["shreya","shankar"],"value":"Hamel has a ton of great and free content on YouTube. He and Shreya Shankar are a breath of fresh air."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Principles for production AI agents"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://www.app.build/blog/six-principles-production-ai-agents"}},"_tags":["comment","author_edmundsauto","story_44712315"],"author":"edmundsauto","comment_text":"Hamel has a ton of great and free content on YouTube. He and Shreya Shankar are a breath of fresh air.","created_at":"2025-08-02T05:11:23Z","created_at_i":1754111483,"objectID":"44765032","parent_id":44721788,"story_id":44712315,"story_title":"Principles for production AI agents","story_url":"https://www.app.build/blog/six-principles-production-ai-agents","updated_at":"2026-09-17T07:50:59Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"hamelsmu"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["shreya","shankar"],"value":"I think that will be very possible soon! We continue to write about it publicly :) Also thanks to my friends and colleagues who write a lot on this subject that I frequently collaborate with:
- Shreya Shankar https://www.sh-reya.com/\n- Eugene Yan https://eugeneyan.com/\n- Bryan Bischof https://bio.site/Docdonut"},"story_title":{"matchLevel":"none","matchedWords":[],"value":"About AI Evals"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://hamel.dev/blog/posts/evals-faq/"}},"_tags":["comment","author_hamelsmu","story_44430117"],"author":"hamelsmu","comment_text":"I think that will be very possible soon! We continue to write about it publicly :) Also thanks to my friends and colleagues who write a lot on this subject that I frequently collaborate with:
- Shreya Shankar https://www.sh-reya.com/\n- Eugene Yan https://eugeneyan.com/\n- Bryan Bischof https://bio.site/Docdonut","created_at":"2025-07-03T21:24:57Z","created_at_i":1751577897,"objectID":"44459325","parent_id":44458811,"story_id":44430117,"story_title":"About AI Evals","story_url":"https://hamel.dev/blog/posts/evals-faq/","updated_at":"2025-07-18T15:10:24Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"niviksha"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["shreya","shankar"],"value":"This is a very innovative take on infra for ML observability. Shreya Shankar and collaborators at Berkeley came up with https://github.com/loglabs/mltrace, which treads the same ground - perhaps you've looked at it already?"},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Mandala \u2013 Automatically save, query and version Python computations"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/amakelov/mandala"}},"_tags":["comment","author_niviksha","story_40940181"],"author":"niviksha","children":[40957400],"comment_text":"This is a very innovative take on infra for ML observability. Shreya Shankar and collaborators at Berkeley came up with https://github.com/loglabs/mltrace, which treads the same ground - perhaps you've looked at it already?","created_at":"2024-07-12T16:16:05Z","created_at_i":1720800965,"objectID":"40946935","parent_id":40940181,"story_id":40940181,"story_title":"Show HN: Mandala \u2013 Automatically save, query and version Python computations","story_url":"https://github.com/amakelov/mandala","updated_at":"2024-09-20T17:26:28Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"smacke"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["shreya","shankar"],"value":"You're probably referring to nbgather (https://github.com/microsoft/gather), which shipped with VSCode for a while.
nbgather used static slicing to get all the code necessary to reconstruct some cell. I actually worked with Andrew Head (original nbgather author) and Shreya Shankar to implement something similar in ipyflow (but with dynamic slicing and a not-as-nice interface): https://github.com/ipyflow/ipyflow?tab=readme-ov-file#state-...
I have no doubt something like this will make its way into marimo's roadmap at some point :)"},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Marimo \u2013 an open-source reactive notebook for Python"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/marimo-team/marimo"}},"_tags":["comment","author_smacke","story_38971966"],"author":"smacke","comment_text":"You're probably referring to nbgather (https://github.com/microsoft/gather), which shipped with VSCode for a while.
nbgather used static slicing to get all the code necessary to reconstruct some cell. I actually worked with Andrew Head (original nbgather author) and Shreya Shankar to implement something similar in ipyflow (but with dynamic slicing and a not-as-nice interface): https://github.com/ipyflow/ipyflow?tab=readme-ov-file#state-...
I have no doubt something like this will make its way into marimo's roadmap at some point :)","created_at":"2024-01-12T23:05:23Z","created_at_i":1705100723,"objectID":"38975366","parent_id":38975254,"story_id":38971966,"story_title":"Show HN: Marimo \u2013 an open-source reactive notebook for Python","story_url":"https://github.com/marimo-team/marimo","updated_at":"2024-10-01T11:58:11Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"EconoBen"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["shreya","shankar"],"value":"Completely free. Completely virtual. 20 minute stalks. Register today!
List of speakers:
Vicki Boykis\nVincent Warmerdam\nTim Hopper\nLynn Cherny\nMatthijs Brouns\nGuenia Izquierdo\nJD Long\nHelena Sarin\nZachary Blackwood\nJoel Grus\nPeter Sobot\nJeremy Jordan\nShreya Shankar\nJowanza Joseph\nEthan Rosenthal\nRoy Keyes\nRhian Thomas\nCaitlin Hudon\nSean Taylor\nLuca Belli\nBen Labaschin\nJames Kirk\nJulia Silge\nBrandon Rohrer\nPeter Baumgartner\nBrianna McHorse\nKatie Bauer\nJuliet Hougland\nJosh Wills\nRose Weigely\nChris Albon"},"story_title":{"matchLevel":"none","matchedWords":[],"value":"[dead]"}},"_tags":["comment","author_EconoBen","story_32685933"],"author":"EconoBen","comment_text":"Completely free. Completely virtual. 20 minute stalks. Register today!
List of speakers:
Vicki Boykis\nVincent Warmerdam\nTim Hopper\nLynn Cherny\nMatthijs Brouns\nGuenia Izquierdo\nJD Long\nHelena Sarin\nZachary Blackwood\nJoel Grus\nPeter Sobot\nJeremy Jordan\nShreya Shankar\nJowanza Joseph\nEthan Rosenthal\nRoy Keyes\nRhian Thomas\nCaitlin Hudon\nSean Taylor\nLuca Belli\nBen Labaschin\nJames Kirk\nJulia Silge\nBrandon Rohrer\nPeter Baumgartner\nBrianna McHorse\nKatie Bauer\nJuliet Hougland\nJosh Wills\nRose Weigely\nChris Albon","created_at":"2022-09-02T02:32:28Z","created_at_i":1662085948,"objectID":"32685934","parent_id":32685933,"story_id":32685933,"story_title":"[dead]","updated_at":"2024-09-20T11:57:46Z"}],"hitsPerPage":8,"nbHits":27,"nbPages":4,"page":0,"params":"query=%22shreya+shankar%22&hitsPerPage=8&advancedSyntax=true&analyticsTags=backend","processingTimeMS":1,"processingTimingsMS":{"_request":{"queue":95,"roundTrip":15},"total":1},"query":"\"shreya shankar\"","serverTimeMS":97}