Agriculture
The answer existed. Reaching it just took 15 hours.
A team of experienced scientists deployed a research agent on Forra, expanding their reach from one library to four and compressing days of literature review into a five-minute structured report.
The challenge
Deep expertise, constrained by the speed of literature review.
The company’s scientists regularly need to know if existing research already answers a question before investing time and resources into new studies. Does mycorrhiza help protect raspberry plants from ground freezing? Is there documented evidence on a particular soil treatment? What does the literature say about a specific growing condition?
The team had a thorough approach: open Google Scholar, build a precise search query, scan through results, read abstracts, filter irrelevant papers, cross-reference sources, and synthesize findings into something actionable. The rigor was there. But for a single question, that process routinely took 10 to 15 hours, and was limited to a single source. Relevant research in other scientific libraries was simply out of reach within that timeframe.
The cost wasn’t just time. It was the risk of making decisions without the full picture, of duplicating research that already existed, or of missing a critical finding because no team can manually search four databases at once.
The solution
An agent that searches, filters, understands, and writes.
Mirego built a research agent on Forra that handles the entire front-end of the scientific research process, from query to structured PDF output. The scientist asks a question in plain language. The agent takes it from there. Because Forra handles the infrastructure, the agent was operational in weeks.
Rather than querying a single database, the agent searches across four scientific libraries simultaneously, extending the team’s reach far beyond what any manual process could cover. It filters for relevance, reads and understands the content, and synthesizes the findings into a structured research report delivered as a ready-to-use PDF.
The scientist’s role shifts from searcher to reviewer. Instead of spending a day building a literature review, they receive a complete, sourced synthesis in minutes and can focus their expertise on interpreting the findings and deciding what to do next.
The outcomes
From a full day of searching to five minutes of reading.
- A research question that previously required 10 to 15 hours of careful literature review is now answered in under 5 minutes.
- Scientists now search 4 scientific libraries simultaneously, extending their reach far beyond Google Scholar alone.
- The agent handles the searching, filtering, and synthesis, delivering a complete PDF report the scientist can act on immediately.
- Scientists can confirm what already exists before investing in new studies, avoiding duplicated effort.
- Critical findings in libraries the team could not previously reach in time are now surfaced automatically.
- Scientists refocus their expertise on interpretation and decision-making, the work that actually requires their training.
Your knowledge base isn’t the problem.
How it is searched or used, is.
Purpose-built AI agents replace a generic assistant, achieving 87.5% accuracy on a validated benchmark versus 12% for Microsoft Copilot.
The power of experience: capturing 30 years of knowledge.
AI transcribes expert interviews, identifies speakers, and turns institutional knowledge into a searchable resource for your entire team.
The expert in their pocket,
on every client floor.
Skilled field technicians deployed a support tool on Forra that puts the full documentation library at their fingertips, with source-traced answers in seconds on any device.
