Skip to content

§ 04 · Practice

Agents that do the work, and show their work.

We build agents that operate inside your existing tools: they launch pipelines, read QC reports, curate literature, draft documents and hand off to a person at the points you choose. Every action is logged and reversible.

§ 04.1 / Scope

Capabilities.

01

Analysis operators

Agents that launch Nextflow runs, watch for failures, retry sensibly and summarise results when a run completes.

02

QC triage

Read MultiQC and pipeline metrics, flag outlier samples, propose re-runs, and explain why in plain language.

03

Curation assistants

Literature screening, variant curation drafts, and structured extraction from papers into your schema.

04

Report drafting

Structured outputs into your templates: methods, results, figure captions, with links back to the data.

05

Tool integration

Model Context Protocol servers for your LIMS, ticketing, Slack, cluster and cloud, with scoped permissions.

06

Safety & oversight

Approval gates, budgets, rate limits, full trace logs, and evaluation and red-teaming before anything touches production.

§ 04.2 / Output

Deliverables.

  • Agents with defined tools, permissions and escalation paths
  • Trace logs and dashboards for every action taken
  • An evaluation suite and a staged rollout plan
  • Training for the team that will run them

Tools & Standards.

nf-core and community standards where they exist, custom software where they do not.

  • Claude Agent SDK
  • MCP
  • LangGraph
  • Pydantic
  • Temporal
  • OpenTelemetry
  • Nextflow
  • Slack

§ 04.3 / Questions

Frequently asked questions.

What can an agent be trusted to do on its own?
We start with read-only and draft-only tasks, then expand autonomy as the evaluation numbers and your team's confidence allow. Destructive actions always require approval.
Do agents need cloud access to our data?
No. Agents can run entirely on your infrastructure, including with on-device models, so no data has to leave.

§ Practice Scoping · 04

Scope a project in ai agents.

Tell us about your assay types, dataset scale, and timelines. We reply with a preliminary scoping memo within two working days.

Scope AI Agents →