First Boot Configuration

Setting up Gatsbi for the first time involves logging in and configuring your AI service provider.

Login Methods

1. Direct Login

• Enter your email address
• Enter your password
• Optional: Check "Remember my password" for convenience

2. Third-Party Account Login

You can also login using:

• Google Account
• LinkedIn Account
• GitHub Account

AI Service Provider Configuration

Setting Up Advanced Models

1. Obtain your API key from OpenAI, Anthropic, or Google
2. Enter the API key in Gatsbi settings
3. Configure proxy (base URL) if needed for restricted regions
4. Test the connection and consider Tier 2 or higher keys (or a reliable third-party proxy service) for better stability under rate limits

Gatsbi Innovator

AI-Powered Science and Engineering Innovation

Workflow Overview

1. Topic Input: Enter your research area or problem statement
2. Systemic Analysis: AI performs comprehensive background research
3. Idea Generation: Receive scored, referenced innovation candidates
4. Idea Expansion: Develop selected ideas into full implementations
5. Output Generation: Create paper manuscripts or patent disclosure drafts

Available Functions

• Start Ideation & Best Practices - Begin your innovation journey and optimize results
• Research Paper Manuscript Drafting - Generate academic manuscripts
• Patent Disclosure Draft Generation - Prepare review-ready disclosure drafts

Start Ideation & Best Practices

Unlock Innovative Ideas with Gatsbi Innovator and Optimize Your Workflow

Part 1: Starting Your Innovation Journey

Step 1: Select Gatsbi Innovator

Ensure "Gatsbi Innovator" is selected in the top-left service menu to activate the ideation engine.

Step 2: Enter Your Research Topic

Step 3: Systemic Analysis

Gatsbi performs multi-step automatic analysis before idea generation:

• Component Analysis and Research Gap Identification
• Technology Trend Assessment
• Feasibility Evaluation
• Innovation Potential Scoring

Step 4: Idea Generation

The system generates 10-20 idea candidates, each including:

Step 5: Idea Expansion

Expand your selected generated idea into comprehensive implementation details. The expansion provides:

• Modeling Approaches: Mathematical formulations, algorithms, and theoretical frameworks
• System Architecture: Module integration relationships and component interactions
• Implementation Methodology: Step-by-step development process and technical requirements
• Technical Specifications: Detailed parameters, constraints, and performance metrics
• Integration Strategy: How different system modules connect and communicate

The expansion transforms a high-level concept into an actionable research plan with concrete technical details.

Part 2: Best Practices & Optimization Tips

Input Optimization Strategies

Working with Automatically Generated Analyses

Control Buttons for Each Analysis Step

Every generated section includes three powerful control buttons:

Advanced Techniques

1. Iterative Refinement

• Focus on core components to narrow down your research subject
• Use "Regenerate with Instructions" to focus on promising directions
• Review and evaluate generated ideas for quality and relevance

2. Multilingual Capabilities

• Input topics in any language
• Core analysis in English ensures accuracy
• Comments translated back to input language

3. Quality Assurance Checklist

• ✓ Verify technical accuracy of proposals
• ✓ Check citation relevance and recency
• ✓ Ensure feasibility aligns with resources
• ✓ Validate novelty claims against literature

Common Pitfalls to Avoid

Pro Tips for Maximum Productivity

1. Focus Your Research: Try focusing on specific systems or modules to find the most suitable innovation points
2. Monitor Analysis Process: Read intermediate analysis steps; use "Regenerate with Instructions" to intervene if results deviate from expectations
3. Systematic Exploration: Expand top 3-5 ideas before deciding; compare their technical feasibility and innovation potential
4. Leverage References: Check cited papers for additional insights, related work, and potential research gaps to explore

Research Paper Manuscript Drafting

AI Paper Manuscript Drafting with Citations, Figures, and More

Key Features

• Structured research paper manuscript generation
• Automated creation of all manuscript elements
• Automatically retrieves and inserts real citations
• Multiple export formats

Automated Elements

Manuscript Generation Process

Step 1: Configure Settings

• Select word count (up to 5,000 words)
• Use word count estimator tool (if unsure)

Step 2: Generate Manuscript

Click "Write a Paper Manuscript" button to start automated generation.

Step 3: Review Generated Content

The system creates comprehensive manuscript elements:

• Title and Abstract
• Introduction with literature review
• Methodology section
• Results with figures and tables
• Discussion and implications
• Conclusion
• References

‹ ›

Page 1 of 10

Export Options

Supported Citation Styles

Unique Advantages

• Advanced language modeling for natural writing
• Minimal user intervention required
• Maintains academic writing standards
• Consistent formatting throughout

Patent Disclosure Draft Generation

Create a structured patent disclosure draft that captures your invention for review by a patent attorney or other qualified professional.

What is a Patent Disclosure?

A patent disclosure draft is a detailed technical document describing an invention before professional review. Its purpose is to:

• Capture invention details, technical background, and implementation examples
• Organize potential novelty and use cases for discussion with a professional
• Provide source material for a patent attorney or IP specialist to review and revise
• Create an internal record to support the next review step

Drafting Process

Step 1: Switch to Patent Mode

Change from "Research" to "Patent" mode in the application.

Step 2: Select Language

Choose from 11 supported languages:

• English
• French
• German
• Chinese Simplified
• Chinese Traditional
• Japanese
• Korean
• Spanish
• Portuguese
• Russian
• Arabic

Step 3: Draft Document

Click the "Write a Patent Disclosure" button to begin drafting.

Key Document Components

‹ ›

Page 1 of 10

Export Options

• DOCX Format: Editable draft for professional review and revision
• Markdown Format: Version-control friendly draft format

Gatsbi Writer

Academic and professional document writing based on your existing research or automated deep research

Key Features

When to Use Gatsbi Writer

• You have completed research with results and data
• You want an automatic research agent to conduct research based on your instructions
• You need to transform rough notes into formal documents
• You want to repurpose research for different formats
• You need professional formatting and structure

Workflow

1. Select "Gatsbi Writer" from the service menu
2. Input your research (text or DOCX file)
3. Review AI-generated summary
4. Choose output format (paper, patent)
5. Export in your preferred format

Write from Research Notes or Existing Results

Transform your existing research into polished manuscripts or patent disclosures, or conduct prior research via search-based deep research and write your paper.

Getting Started

Step 1: Select Gatsbi Writer

Choose "Gatsbi Writer" from the service menu.

Step 2: Provide Research Input

You can provide your research in two ways:

• Type or paste research description directly, or input research instructions and let the deep research agent conduct research for you
• Attach a .DOCX document containing your research, or provide instructions

Step 3: Automatic Research Type Recognition

After you input or attach your prior research materials, Gatsbi Writer automatically identifies the research type (methodological, empirical, or case study) based on your content. If the automatic recognition is incorrect, you can explicitly specify the research type by including it in your title input. For example: "On the effectiveness of online learning: A Case Study" clearly indicates a case study research.

Optional Step: Deep Research Assistance

If your input does not include detailed results or findings, Gatsbi Writer triggers the deep research agent. It performs web-based research to propose research questions, supplement supporting evidence, and derive conclusions.

Step 4: Research Summarization

Gatsbi Writer generates a comprehensive research summary focusing on:

• Methodology details
• Key results and findings
• Critical contributions
• Implications and applications

Minimum Input Requirements (Prior Research Writing)

This section applies when you are writing based on your prior research.

If your prior research consists of a methodology study, i.e. you propose a novel method, model or process to solve a technical problem, the minimum input for Gatsbi Writer is a description of your methodology. You can also provide the experimental results if they are available. If your prior research involves experiments or statistics only, then it will be considered as an experimental study, in which case, the experimental results are required for Gatsbi Writer to work. Similarly, if you want to write a case study paper, you need at least provide either narrative or quantitative findings of the case study to Gatsbi Writer. If any of the required information above is missing, Gatsbi Writer will display a reminder message and prompt you to provide it.

Deep Research Agent

Applicable when you provide only research instructions.

The deep research agent can use web search to propose research questions (if not specified), suggest research methods, gather supporting evidence, and derive conclusions, which will be used for paper writing.

Output Options

After summarization, you can generate:

• Full research manuscript
• Patent disclosure document (only for methodological research)

The Humanizer Plugin

Refine manuscripts with natural, polished academic language.

Key Benefits

• Preserves technical accuracy and logical coherence
• Improves academic writing fluency
• Maintains original meaning and content

How to Use

Step 1: Generate Your Manuscript

First, create your manuscript using Gatsbi's standard tools.

Step 2: Access Humanizer

Click the "Humanizer" button near the export option.

Step 3: Processing

The plugin rewrites text paragraph-by-paragraph to:

• Vary sentence structure
• Add natural transitions
• Introduce stylistic variations
• Enhance readability

Credit System

Comparison

Pro Tips

• Use for final manuscript polishing
• Helpful for improving academic tone before submission
• Review output to ensure meaning preservation

The Plugin Credit System

Understanding and managing credits for advanced Gatsbi features.

What Are Plugin Credits?

Plugin credits are a separate resource system for accessing advanced add-on features like the Humanizer plugin. They:

• Enable premium plugin functionality
• Do not affect core tools (Gatsbi Writer, Gatsbi Innovator)
• Provide flexible usage options

Credit Types

How to Buy Credits

1. Click the Balance area in the top right corner of the paper writing interface
2. Click the "Buy More Credits" button
3. Select credit package
4. Complete secure payment
5. Credits instantly added to account

Credit Consumption Order

The system automatically uses credits in this order:

1. Free monthly credits - Used first
2. Purchased credits - Used when free credits exhausted

Handling Insufficient Credits

Solutions:

• Wait for monthly credit refresh
• Purchase additional credits

Gatsbi Reviewer

AI-Powered Systematic Reviews and Meta-Analyses

Key Capabilities

Review Types Supported

PRISMA Compliance

All reviews follow PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines:

• Structured search strategy
• Clear inclusion/exclusion criteria
• PRISMA flow diagram
• Risk of bias assessment
• Transparent reporting

Import from Zotero

Use your Zotero library as the literature source for a systematic review or meta-analysis.

Start from an Existing Zotero Library

Choose Import literature from Zotero when your reference list has already been collected, screened, or curated in Zotero.

• Use this path when you want Gatsbi Reviewer to work from your existing Zotero records.
• The imported studies become the starting literature set for systematic review or meta-analysis drafting.
• This replaces the automated search and screening step with your own curated Zotero selection.

Select a Library and Collection

You can import from a local or cloud Zotero library, then choose a collection and the papers inside that collection.

• Select the Zotero source: local library or cloud library.
• Choose the relevant collection or subcollection.
• Select the individual papers that should be included in the review workflow.

Complete the Review Protocol

If you import studies from Zotero, complete the full review protocol so the system understands how the papers were searched, screened, and selected before writing the manuscript.

• Fill in the review question, search strategy, inclusion criteria, exclusion criteria, and database/source information.
• Complete the PRISMA table to document the review flow and selection process.

This PRISMA table records the review flow up to Reports assessed for eligibility. The final number of eligible studies is determined after the synthesis process.

Systematic Review

Automatically generate comprehensive Systematic Literature Reviews with AI-powered analysis.

Getting Started

Select Gatsbi Reviewer from the service menu to access systematic review features.

Review Workflow

Enter Research Topic

Start by entering a research topic or review question in the main input box. A concise topic is enough to begin, while a more specific question can help guide the search scope and synthesis.

• Use the topic input for the main research area, population, intervention, outcome, or phenomenon of interest.
• Click the plus (+) menu next to the input box to open additional options.
• Select Configure review protocol when you want to provide more detailed review requirements before search and screening.

Optional: Configure Review Protocol

The review protocol modal lets you provide structured instructions before Gatsbi Reviewer searches and screens the literature. Fields left blank can be inferred automatically, while completed fields give the system more precise boundaries.

• Overview: Define the topic title and research question. Enable the meta-analysis option only if quantitative synthesis is part of the task.
• Filters: Set publication year range, minimum journal impact factor, and minimum number of papers when the review needs stricter search limits.
• Criteria: Add Boolean keywords, select a question formulation framework, and define inclusion or exclusion criteria.
• Databases: Choose one or more literature sources, such as Google Scholar, PubMed, IEEE Xplore, arXiv, ACM Digital Library, Web of Science, Scopus, ScienceDirect, and SpringerLink.

‹ ›

Page 1 of 4

Run Search and Screening

After the topic and optional protocol are submitted, Gatsbi Reviewer searches the selected sources, applies the available filters and criteria, and identifies candidate studies for the review.

• Searches across the selected academic databases and imported references.
• Uses the topic, protocol, keywords, and eligibility criteria to screen candidate literature.
• Organizes studies for user review before manuscript drafting begins.

Review and Curate Studies

Synthesis

Click the Synthesize button to generate structured synthesis outputs before drafting the manuscript. Gatsbi Reviewer creates a Characteristics table for the included studies and evidence tables by theme that organize extracted study information by review themes or study groups.

You can review and edit these synthesis results before moving on to manuscript drafting.

• Edit table values directly when study details need correction.
• Click Add column to create a new data field, or use the delete control to remove columns that are not needed.
• Use Auto fill to let AI populate values for newly added columns based on the included studies.
• Click Manage groups to redefine study groups and, if needed, let AI reorganize studies according to your custom grouping scheme.
• Reorganizing studies with Manage groups regenerates the evidence tables by theme.

Draft Manuscript

After curation and synthesis, Gatsbi Reviewer drafts a systematic review manuscript using the selected studies and the configured protocol.

• Creates a narrative synthesis of findings across included studies.
• Builds structured sections aligned with systematic review conventions.
• Summarizes implications, limitations, and research gaps.
• Formats citations and references from the selected literature.

Key Features

Sample Systematic Review Output

‹ ›

Page 1 of 6

Meta-Analysis with Gatsbi Reviewer

Perform statistical synthesis of quantitative studies with automated data extraction and analysis.

Meta-Analysis Workflow

Enter Research Topic

Start by entering the research topic or review question, then select the Meta-analysis option to enable quantitative synthesis.

• Use the topic input for the main population, intervention or exposure, comparator, and outcome area.
• Keep the Meta-analysis option selected so the workflow extracts quantitative data and prepares statistical synthesis.
• When available, configure the review protocol before search so outcome definitions and eligibility criteria are clear from the start.

Configure Protocol, Search, and Curate Studies

The optional review protocol, search and screening, and study curation steps follow the same workflow as Systematic Review. Use that process to define the protocol, run the literature search, screen candidate studies, and curate the included study set before synthesis.

Synthesis

Gatsbi Reviewer generates coded outcomes for the included studies. The coded outcomes table includes outcome names, effect size measures, and the raw data needed for meta-analytic estimation.

For each outcome, the system calculates the elements needed to build forest plots, including effect size, SE, 95% CI, z, p, and study weight. These values are organized in outcome-specific subtables.

• Review and edit the coded outcomes table before manuscript writing.
• Click Add Study to add missing studies and enter the required outcome data.
• Edits to coded outcomes or added study data trigger recalculation of the forest plot.
• Use Manage outcomes to revise outcome definitions and effect size measure definitions.

Write a Paper Manuscript

After data extraction completes, click the "Write a Paper Manuscript" button to generate your comprehensive meta-analysis manuscript. The system will automatically integrate all statistical results, forest plots, funnel plots, and data tables into a properly formatted academic paper manuscript.

Requirements for Meta-Analysis

• Recommended minimum of 10 studies with quantitative data
• Comparable outcome measures across studies
• Sufficient statistical information (means, SDs, CIs, effect sizes)
• Similar study designs or adjustable for heterogeneity

Sample Meta-Analysis Output

‹ ›

Page 1 of 8

Billing

Payment Methods

Credit/Debit Card (via Stripe)

Manage Subscription

Click the "Subscription Management" button to access the Stripe portal where you can:

• Upgrade your current subscription plan
• Cancel your subscription (Note: Cancellation stops future charges at the next billing date. Your access remains active until then)

Invoices

Stripe automatically generates and sends invoices and receipts to your registered email. To customize your invoice details:

• Preferred method: Enter your company name, VAT number, and other details directly during checkout
• Alternative: Contact Customer Support for manual invoice generation

Customer Support

Get help quickly through multiple support channels.

Contact Methods

Reporting Technical Issues

Response Times

• Typically respond within 24 hours
• During holidays, response time may extend to 48 hours
• Both email and ticket systems follow the same response timeline

Self-Service Resources

• Check this user guide for detailed instructions
• Visit our FAQ section on the website
• Watch tutorial videos on the website