feynman

Design protein sequences around ligand or small-molecule contexts with LigandMPNN-style workflows. Use when a task asks for ligand-aware protein design, residue redesign, constraints, or design ranking.

Run a literature review using paper search and primary-source synthesis. Use when the user asks for a lit review, paper survey, state of the art, or academic landscape summary on a research topic.

Register or audit Feynman-managed model endpoints. Use when a research workflow needs a local or remote model service, endpoint health checks, credential refs, startup scripts, or inference routing.

Find implementable ML training recipes from papers, datasets, docs, and code. Use when the user wants to fine-tune, train, reproduce, or choose a practical ML method, dataset, hyperparameter setup, or benchmark recipe.

Run explicitly chosen research benchmark or replication jobs on Modal's serverless infrastructure. Use when a Feynman research workflow needs burst remote GPU compute and the Modal CLI is available.

Run or plan OpenFold3-style structure prediction workflows. Use when a task asks for open protein or complex prediction, setup, model comparison, or reproducibility around OpenFold-family outputs.

Compare a paper's claims against its public codebase. Use when the user asks to audit a paper, check code-claim consistency, verify reproducibility of a specific paper, or find mismatches between a paper and its implementation.

Shape the scientific story across a manuscript, abstract, figures, and evidence. Use when a task asks for paper structure, figure order, argument flow, missing analyses, or manuscript revision strategy.

Turn research findings into a polished paper-style draft with sections, equations, and citations. Use when the user asks to write a paper, draft a report, write up findings, or produce a technical document from collected research.

Read, extract, and cross-check content across scientific PDFs. Use when a task needs methods, figures, tables, citations, accessions, or claims from multiple places in one or more papers.

Preview Markdown, LaTeX, PDF, or code artifacts when preview commands are visible, or fall back to shell/browser tools. Use when the user wants to review a written artifact, export a report, or view a rendered document.

Answer questions about Feynman's own product behavior, runtime, settings, commands, skills, connectors, and package state. Use when a response would claim what Feynman can do or how it is wired.

Design protein sequences from fixed backbone structures with ProteinMPNN-style workflows. Use when a task asks for backbone-conditioned sequence design, mutation suggestions, fixed residues, or design filtering.

Dispatch Feynman research notebook or experiment jobs to Modal. Use when a task has explicitly chosen Modal for bounded cloud compute, GPU jobs, or reproducible remote execution.

Run Feynman research jobs on SSH, Slurm, or lab hosts. Use when a task needs remote host setup, job submission, log harvest, artifact sync, or GPU/cluster execution outside Modal.

Plan a replication of a paper, claim, or benchmark, and execute only after an explicit environment choice. Use when the user asks to replicate results, reproduce an experiment, verify a claim empirically, or build a replication package.

Run a tough but constructive internal research critique of an AI research artifact. Use when the user asks for a review, critique, feedback on a paper or draft, or wants to identify weaknesses before submission.

Provision and manage GPU pods on RunPod for explicitly chosen long-running research experiments. Use when a Feynman replication, benchmark, or dataset-heavy research run needs persistent GPU compute with SSH access.

Use scGPT-style single-cell foundation model workflows. Use when a task asks for single-cell embeddings, perturbation prediction, cell annotation, batch transfer, or gene-program analysis.

Run scvi-tools single-cell workflows. Use when a task asks for scVI/scANVI setup, latent embeddings, batch correction, differential expression, cell annotation, or reproducible AnnData analysis.