ResearchPod Summary
Omakase is an innovative AI research assistant designed to support scientists over the long haul of their projects. Unlike traditional AI tools that wait for you to ask a question, Omakase is proactive—it watches your project documents as they evolve, figures out what you might need next, queries powerful 'deep research systems' (advanced AI that synthesizes vast literature), and boils down their lengthy reports into actionable suggestions. Delivered via email notifications and a dashboard, these suggestions are tailored to your specific project context, helping you spot concrete next steps like "Read this paper on X method—it addresses the gap in your hypothesis on page 5."
This addresses two big pain points in research: (1) Manually crafting precise queries for complex, ongoing projects is tedious—you have to cram rich context into short prompts. (2) Deep research tools spit out exhaustive reports that are overwhelming to sift through for real actions. Omakase automates both, making AI a true partner in long-horizon scientific work.
Traditional AI interactions are reactive: single-turn queries or multi-turn chats. Proactive agents take initiative, but prior work focused on short sessions (e.g., clarification questions). Omakase pioneers long-horizon proactivity by monitoring evolving project artifacts like shared docs. It infers 'latent needs'—unspoken questions based on your project's state—and acts asynchronously via notifications, not real-time chat. This fits research workflows where needs shift slowly over weeks/months, unlike coding or design tasks.
Key enabler: Project context extraction from lightweight, privacy-friendly sources like a 'Research Interests Document' (your notes + seed papers), avoiding screenshots or chat histories.
Omakase queries deep research systems (e.g., LLM-powered tools like those in [49]) which excel at complex knowledge synthesis but produce verbose outputs. Omakase distills these into actionable suggestions:
The paper recommendations pipeline is LLM-driven:
Alex: Welcome to another episode of ResearchPod. Sam, walk us through the paper you're diving into today.
Sam: This paper describes Omakase, a system that watches researchers' project documents as they change over time. The central problem is that scientists squeeze big project ideas into short questions for AI search tools, then sort through huge walls of text for useful steps.
Alex: So researchers waste time boiling down their whole project into tiny queries, then get buried in long reports?
Sam: Yes. These deep research tools pull info from many papers for full summaries, but researchers must craft precise questions first and dig for ideas like "cite this paper for your baseline experiment." Studies with 42 people show this manual work is tedious. Omakase monitors shared docs like meeting notes or drafts to spot what's needed now. Participants found its automatic questions timely and boiled-down suggestions notably more useful.
Alex: Using actual project files avoids forcing researchers to rewrite everything.
Sam: Right. Unlike paper recommenders that rely on old lists of favorites—which go stale—Omakase tracks evolving docs for fresh context. A study with 28 users confirmed they hate maintaining extra notes just for AI.
Alex: If it's pulling from live documents like meeting notes, how does it figure out the project stage—like early brainstorming versus planning experiments?
Sam: It looks at the document's structure and recent changes, such as new sections on evaluation without results, or shifts in research questions. It compares those to patterns from different project phases—like broad ideas at the start or test details later. Researchers call this project state inference. In one example, it spotted "ideation and early experimental design" from doc revisions.
Alex: Recent edits give a real-time snapshot. But turning those into useful questions must take steps.
Sam: First, it preprocesses the doc into simple text and lists mentioned papers. Then it infers the state and generates stage-specific questions, like metrics others used for similar tests. Top ones go to the deep research tool for reports, which get boiled into ranked suggestions focused on actions—avoiding repeats or overload.
Built through technology probe studies (N=42 total): formative studies (N=28), 10 pipeline iterations, final eval (N=11). Researchers rated inferred queries as useful/timely and Omakase suggestions significantly more actionable than raw deep research reports. Interfaces include a dashboard for suggestion lists (with doc context + QA excerpts) and document views highlighting relevant sections.
As LLMs handle complex tasks, the bottleneck shifts to context and proactivity. Omakase extends RAG-based literature tools (paper recs, synthesis) to whole-project awareness, where literature needs evolve. It previews a future of AI as 'ambient intelligence' for science—always aware, never intrusive—potentially accelerating discovery by surfacing serendipitous insights at the right time. Challenges remain: ensuring query accuracy, handling project ambiguity, and scaling to diverse fields.
AI-generated third-party summary by ResearchPod. Not official content or an endorsement by the paper authors or affiliated organizations.
Alex: What changed from researcher feedback on that pipeline?
Sam: Ten scientists rated iteration one on real projects. State inferences were mostly correct and surfaced blind spots, but volume overwhelmed and phrasing was unclear. They wanted steering, like editing questions or timing. Iteration two added better awareness of recent changes by tracking dates, clearer text from prompt tweaks, and ranking for diverse top picks. A follow-up with eleven researchers preferred current-doc questions as more timely and stage-aligned.
Alex: Even blind, people picked up-to-date ones as better fits.
Sam: Yes. For suggestions versus raw reports—where folks picked promising sections—Omakase's rated higher on concrete steps, like "adopt this baseline," even against reading twice as much raw text. Nine of ten found them easy to scan. The paper suggests distilling reports into project actions is a meaningful step.
Alex: That addresses drowning in text. Users could steer timing, like weekly checks.
Sam: Right—they set frequencies or track specific questions for updates. With eleven researchers, four of ten preferred Omakase's boiled-down ideas over raw reports. They felt like advisor feedback—pointing to overlooked experiment choices—and connected easily back to the project.
Alex: But were there misses?
Sam: Yes—jumping to assumptions about project direction led to off-target ideas. It sometimes pulled from old versions with abandoned topics. The paper notes this as room for improvement, like flagging dropped threads. Privacy came up too—hesitation due to rules or AI access worries. Studies were short-term, so long-term use over full projects needs more testing.
Alex: Balancing awareness with caution is key.
Sam: Shared docs give reliable, privacy-friendlier snapshots than chat logs or screenshots, which mix notes or fade. The paper cautions on risks like over-reliance without verifying.
Alex: Overall, this takes paper-retrieval tools and makes them smarter by tying into changing project documents.
Sam: Precisely. Iterative design with 42 participants refined it into precise, linked suggestions from evolving docs.
Alex: That's a clear takeaway—smarter support without the grind. Thanks, Sam. And thanks for listening to ResearchPod.