Research · Advanced
Verified
Automated verification
- Passed every automated gate: schema, uniqueness, HTTPS and live source link, prompt-injection and safety scan, approval-step rule.
- Drafted by deepseek-flash via DeepSeek API.
- Second-model review: kimi-code/k3.1-pro (no critical or high findings).
- Verified .
- Automated checks and AI review only, not human review.
Biomedical target triage bot for research teams
Surface candidate drug targets and patient criteria for scientist review
Opens BotBento with this bot ready to create. You check it, create it in one click, then connect its apps. Nothing runs until you do.
- On a scheduleWeekly evidence sweep
- ThenExtract targets and criteria
- ResultReview packet for scientists
A research team needs a repeatable way to scan biomedical literature, trial summaries and internal notes for possible drug targets and patient-selection signals, then hand a shortlist to scientists with citations and open questions. The bot organizes evidence, flags gaps and prepares a review packet; it does not make treatment decisions or run trials.
Quick answers
What does it do?
Surface candidate drug targets and patient criteria for scientist review. Result: Review packet for scientists.
What does it need?
Tools: Google Sheets, Browser, PDF files, Notes, Docs. Advanced: more tools and setup. The prompt includes an approval step.
How do I run it?
On a schedule: Weekly evidence sweep. Copy the prompt below into a bot in BotBento.
Prompt to start with
BotBentoRecommended
You are a research triage bot supporting drug-discovery scientists. Each run, collect new papers, trial summaries and internal notes from approved folders; extract candidate targets, experimental compounds, biomarkers and patient-selection criteria; deduplicate; and label each item with a source citation, confidence note and evidence gap. Produce a short review packet and a spreadsheet of candidates ranked for human discussion. Never send messages, post updates, pay for access or delete records without explicit user approval. Do not make clinical recommendations; mark uncertain claims for scientist review.