Vector: AI Target Discovery Scientist Agent
Vector is an AI target discovery scientist that ranks disease targets on genetic, expression and pathway evidence and profiles compounds from live databases.
Last updated:
What does Vector do?
Vector is the Target Discovery Scientist in the xSquads Life Sciences Squad. Prioritises targets and profiles compounds. It works on your own files in the xSquads desktop app, and it drafts rather than sends: anything that leaves your company waits for your approval.
Vector at a glance
- Role
- Target Discovery Scientist
- Squad
- Life Sciences Squad (Health & Life Sciences)
- Works with
- Lumen (Literature Scout), Cohort (Clinical Trials Analyst), Sentinel (Regulatory & Pipeline Analyst), Codon (Bioinformatician), Panel (Scientific Illustrator)
- Who approves the work
- You. Drafts wait for your review before anything is sent or published.
- Skills and live data connectors
- 0 skills, 3 data connectors
- Connections needed
- None beyond the app
Common problems Vector solves
Where this work usually goes wrong, and what Vector does about it.
Target lists ranked by gut feel
The problem: Prioritisation meetings rank targets by who argues best, not by the evidence.
How Vector handles it: Vector ranks targets for a disease using genetic, expression and pathway evidence, and shows the evidence behind each rank.
Compound data scattered across sources
The problem: Potency, selectivity and known liabilities for one compound sit in different databases and papers.
How Vector handles it: Vector profiles compounds on structure, potency, selectivity, known liabilities and clinical status in one view.
Rankings nobody knows how to change
The problem: A ranking gets accepted without anyone knowing what new data would overturn it.
How Vector handles it: Vector compares candidates side by side and states what data would change the ranking.
How Vector is tuned for the job
Vector is not a general chatbot with a new name. It runs with a fixed role, a focus list and skills it reads before each task, so its output is consistent and on point from the first request.
What keeps it fast and accurate
- Pulls live data from the Open Targets, ChEMBL and Owkin plugins.
- Shows the evidence for every rank, so a scientist can challenge a specific point.
- Cites the database record behind every claim, and provides research support only.
Its standing focus
- Rank targets for a disease using genetic, expression and pathway evidence, and show the evidence behind each rank.
- Profile compounds: structure, potency, selectivity, known liabilities and clinical status.
- Compare candidates side by side and state what data would change the ranking.
- Research support only, not medical advice. Always cite the database record, PMID or NCT id behind every claim.
Skills it reads before a task
Vector works through its live data connectors rather than separate skills.
Live data connectors
- open-targets
- chembl
- owkin
Rules it always works by
- Asks one short clarifying question only when a task is truly ambiguous; otherwise it states its assumption and gets on with it.
- Drafts, does not send: anything that leaves your company, such as an email, a post, a ticket reply or a contract, waits for you to review and approve.
- Leads with the answer and keeps caveats to one line, with depth only when you ask for it.
- Cites sources and never invents facts, figures, quotes or links; it says what it could not verify.
- Keeps notes on your preferences, voice and standing decisions in memory and reuses them.
- Reads the relevant skill before a task the skill covers, and follows it.
What you can ask Vector to do
Requests are written in plain language. A few examples:
- Rank targets for idiopathic pulmonary fibrosis
- Profile these three kinase inhibitors side by side
- What evidence links this gene to the disease?
- What data would move target B above target A?
Vector's teammates in the Life Sciences Squad
Add Vector on its own, or import the whole squad so each part of the work goes to the agent built for it.
- LumenLiterature ScoutFinds and synthesises papers and preprints with citations.
- CohortClinical Trials AnalystMaps the trial landscape, designs and critiques protocols.
- SentinelRegulatory & Pipeline AnalystTracks approvals, guidance, competitor pipelines and deals.
- CodonBioinformaticianRuns omics QC and analysis pipelines and manages research data.
- PanelScientific IllustratorTurns findings into publication-ready figures.
Frequently Asked Questions About Vector, the AI Target Discovery Scientist
Which databases does Vector use?
Open Targets, ChEMBL and Owkin, through live data plugins. Every claim cites the database record behind it.
Does Vector replace a discovery team's judgement?
No. Vector ranks and profiles with the evidence shown and states what would change the ranking. Scientists make the call.
How do I add Vector to xSquads?
Open the xSquads app, go to Explore agents, find Vector under the Life Sciences Squad and choose Add Vector. Vector joins your sidebar as its own chat with its skills ready. To get the whole team, import the Life Sciences Squad from Squad templates.
Put Vector to work
Download xSquads, open Explore agents and add Vector. Or have the xSquads team set it up for your team and tune it to how you work.