Research & Search

Train AI models to be harmless through self-critique and AI feedback using a set of constitutional principles, without requiring human labels for harmful outputs.

Run interpretability experiments on neural network internals using nnsight, with optional NDIF remote execution for massive models.

Train and analyze Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features for mechanistic interpretability research.

Provides paragraph-level structural blueprints for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys, including page allocation, writing patterns, and venue-specific checklists.

Compiles research inputs—PDFs, code, logs, notes—into structured Agent-Native Research Artifacts with cognitive and physical layers.

Performs a semantic epistemic review of Agent-Native Research Artifacts, scoring six dimensions and producing a constructive report with a recommendation.

Guides researchers through structured ideation frameworks to discover high-impact research directions.

Synthesize user research into a 4-quadrant empathy map (Says, Thinks, Does, Feels) to capture and share user understanding across a team.

Creates a comprehensive end-to-end user journey map with stages, touchpoints, emotions, pain points, and opportunity areas for product design and UX analysis.

Design surveys that collect reliable, unbiased quantitative data to validate hypotheses and measure user attitudes at scale.

Map the end-to-end service delivery system including frontstage actions, backstage processes, and supporting infrastructure.

Map user Jobs-to-Be-Done with functional, emotional, and social dimensions plus outcome expectations to reframe product decisions around user motivations.

Organize qualitative research data into an affinity diagram with themes, clusters, and insight statements.

Design a diary study plan with prompts, duration, participant criteria, and analysis framework to understand user behavior over time in natural contexts.

Create structured user interview scripts with warm-up, core exploration, and wrap-up sections for qualitative research.

Conduct a structured competitive analysis comparing UX patterns, features, strengths, and gaps across rival products.

Analyze card sorting results to inform information architecture and navigation structure. Use after conducting open or closed card sort studies.

Build and maintain a research repository that makes findings findable, reusable, and cumulative across the organization.

Design a usability test plan with tasks, success metrics, participant criteria, and facilitation guide for moderated or unmoderated sessions.

Design click and first-click tests to evaluate navigation clarity and information findability in user interfaces.

Conduct expert heuristic evaluations of digital interfaces using Nielsen's 10 usability heuristics and domain-specific criteria.

Analyzes sector rotation patterns and market cycle positioning using publicly available CSV data, with optional chart image analysis.

Analyze US stocks with fundamental and technical analysis, peer comparisons, and investment reports using real-time market data.

Analyzes recent market-moving news events and their impact on US equity markets and commodities, producing impact-ranked reports using web search and fetch tools.

Quantifies market top probability using O'Neil Distribution Days, Minervini leading stock deterioration, and Monty defensive sector rotation, producing a 0-100 composite score with risk zone classification for tactical 2-8 week timing signals.

Scans US equities for daily +20%/-20% movers, classifies catalysts and chart context, updates forward outcomes, and summarizes cohort patterns for research.

Analyze S&P 500 market breadth charts and CSV data to assess market health, identify trading signals, and generate positioning recommendations for different trader types.

Detect structural macro regime transitions (1-2 year horizon) using cross-asset ratio analysis, analyzing RSP/SPY concentration, yield curve, credit conditions, size factor, equity-bond relationship, and sector rotation to identify regime shifts.

Evaluates US market bubble risk through quantitative data analysis using the Minsky/Kindleberger framework, scoring indicators like Put/Call ratio, VIX, margin debt, breadth, and IPO data.

Analyzes global market conditions across US, European, and Asian indices, forex, commodities, and economic indicators to produce structured market reports with risk sentiment assessment.

Build and maintain a model book for Stockbee-style Momentum Burst setups by ingesting screener candidates, updating 3-day and 5-day forward outcomes with MFE/MAE and stop-hit status, and summarizing cohort statistics to improve setup recognition.

Analyzes Stockbee-style Day 1 Episodic Pivot candidates by scoring catalyst quality alongside price/volume confirmation, gap/range expansion, volume shock, neglect/revaluation context, liquidity, and risk to the EP-day low.

Screen US stocks for Stockbee-style short-term momentum burst setups using 4% breakout, dollar breakout, range expansion, volume expansion, prior range contraction, close-location, failure filters, and risk-distance scoring.

Search the web and fetch content from URLs, returning LLM-friendly markdown.

Scrapes public web data from LinkedIn, Twitter, GitHub, YouTube, and other sources, sends and reads email, performs deep research, generates images, and searches the web through the DeepAPI service.

Facilitates a multi-perspective discussion on Austrian economics between Hayek, Mises, and Claude, analyzing user questions through their distinct philosophical lenses.