The original RFQ text before parsing. Use this to verify all information was captured correctly.
Parse an RFQ to see the original text here
Standard pricing structure and assumptions for this project.
Analyze expert profiles against RFQ criteria and get a compatibility score.
Generate expert network style outreach messages based on RFQ criteria.
Analyze expert profiles from LinkedIn URLs or uploaded documents.
Screening criteria from RFQ and analyst notes.
Compliance reminders and notes (e.g., Zintro-excluded companies, former employees constraints, confidentiality).
Project status and notes. Auto-extracted clues from the RFQ are shown below; add updates as the project progresses.
Log RFQ-specific or general feedback. Snapshots include the current RFQ text and structured data (optional).
Export format: JSON array of { id, name, text, createdAt }.
PDFs are auto-converted to text on-device using PDF.js.
One per line. Stored locally; export to share or back up.
Save pricing decisions as training examples to help the AI learn your pricing methodology.
Key is stored locally in your browser. If disabled or no key, hotNews remains empty.
Required for AI Expert Discovery and enhanced Hot News. Get API credentials here
Choose the AI model for RFQ parsing. GPT-4o provides the best balance of accuracy and cost. Note: GPT-5.1 requires organization verification and usage tier 1-5. If you get errors, check with your dev team to confirm API access.
Add competitor expert networks to find experts who are already signed up with them.
These will be used to find experts who mention competitors in their LinkedIn profiles.
Manage the prompt used for generating comprehensive strategy documents. If no custom prompt is set, the default hardcoded prompt will be used.
💡 Tip: Create your prompt in Gemini 3 or ChatGPT 5.1, then paste it here. The app will use this prompt for all strategy document generation.