Skip to main content
Version: 26.1

Use cases

Co-Scientist is an AI assistant for building, running, and managing bioinformatics workflows, available through the Seqera CLI. The sections below walk through common tasks with example prompts you can adapt to your own work:

Develop and debug Nextflow pipelines​

Co-Scientist helps you develop, debug, and understand Nextflow pipelines with AI-powered analysis and code generation. The examples below are prompts you can adapt to your own pipeline.

Understand your pipeline structure​

> Show me the structure of main.nf
> What processes are defined in this pipeline?
> /nf-pipeline-structure

Generate configuration files​

> /nextflow-config

Debug your pipeline​

> /debug
> Why is my pipeline failing?

Review local execution history​

> /nf-run-history

Trace output provenance with data lineage:

> /nf-data-lineage

Generate schema files​

> /nextflow-schema

Convert scripts to Nextflow​

> /convert-python-script

Fix strict syntax​

> /fix-strict-syntax

Migrate old schema definitions​

> /nf-schema-migration

Run pipelines on Seqera Platform​

Use Seqera Platform capabilities to run and manage workflows at scale with AI assistance. The examples below are prompts you can adapt to your own workspace.

List your workflows​

> List my recent workflows

Launch a pipeline​

> Launch the nf-core/rnaseq pipeline with the test profile

Debug failed runs​

> Why did my last workflow fail?
> Get the logs for the failed task in my last run

Debug your most recent run​

> /debug-last-run-on-seqera

Build containers with Wave​

Co-Scientist can create containerized environments using Wave, without the need to write Dockerfiles. The examples below are prompts you can adapt to your own tools.

Create a container with conda packages​

> Create a container with samtools and bwa from bioconda

Create a container with pip packages​

> Build a container with pandas, numpy, and scikit-learn

Get a container for a specific tool​

> I need a container with FastQC version 0.12.1
note

Co-Scientist generates a Wave container URL that you can use directly in your Nextflow pipelines or pull with Docker.

Work with data​

Co-Scientist helps you manage data through Platform data links and access reference datasets. The examples below are prompts you can adapt to your own data.

> List my data links
> Show me the contents of my S3 data link

Download and upload files​

> Generate a download URL for results/final_report.html
> Upload my local results to the data link

Access reference data​

> Find the human reference genome GRCh38
> Search for RNA-Seq test data

Discover and run nf-core modules​

Co-Scientist provides access to over 1,000 nf-core modules for common bioinformatics tasks. The examples below are prompts you can adapt to your own analysis.

Search for modules​

> Find nf-core modules for sequence alignment
> What modules are available for variant calling?

Get module details​

> Show me how to use the nf-core/bwa/mem module

Run a module​

> Run FastQC on my FASTQ files
note

Co-Scientist can generate the exact Nextflow command with the correct parameters for your data.

Edit local project files​

Co-Scientist can interact with files in your current working directory. The examples below are prompts you can adapt to your own project.

Start from your project folder​

cd /path/to/your/project
seqera ai

Ask for help with local tasks​

> Show me the structure of main.nf
> Add a new process to handle quality control
note

Local file operations are controlled by approval modes. By default, Co-Scientist asks for your approval before making changes outside your working directory or running potentially dangerous commands.

Learn more​

  • Modes: Work in build, plan, and goal modes
  • Skills configuration: Discover, create, and install skills
  • Skills: Built-in skills, slash commands, and session limits
  • Command approval: Control which commands run automatically
  • Code intelligence: Language-server support for Nextflow, Python, and R
  • Projects: Organize workspace resources into projects using Platform labels
On this Page