TendAI

The description states that TendAI is a multi-tenant SaaS platform designed for enterprise procurement and legal departments. It includes:

• An intelligent Next.js workspace, where users can chat with an agent to analyze contracts.
• A multi-agent orchestration system using LangGraph, which routes queries, retrieves chunks, performs risk audits, checks output quality, and verifies citations.
• A knowledge base ingestion portal for uploading policies and templates, parsed using layout-aware engines (e.g., Docling).
• A human-in-the-loop gate, pausing autonomous execution for expert input.
• Grounding & provenance features that cite retrieved chunks to prevent hallucinations.

The system is built with:

• Backend: FastAPI, LangGraph, PostgreSQL
• Frontend: Next.js
• Vector DB: ChromaDB
• LLMs: Codex, GPT-5.6

Inference The product appears to be a document intelligence platform, focused on automating compliance and auditing tasks in procurement.

The author positions TendAI as:

“A Multi-Agent SaaS for enterprise tender intelligence, compliance auditing, and pricing verification.”

This is a self-reported positioning. The description does not indicate prior versions or evolution of the product beyond its hackathon submission.

Inference The author frames this as a solution to inefficiencies in procurement and legal teams, leveraging LLMs and multi-agent workflows.

The description states:

“Procurement and legal departments in organizations waste weeks manually auditing massive tender documents…”

This implies the primary customer is:

• Enterprise procurement or legal teams
• Likely operating in large organizations with complex, high-volume tender processes
• Needing compliance verification and pricing validation

Inference The ICP appears to be large enterprises with formalized procurement workflows, but no evidence of specific customer segments or personas.

No information is provided about:

• Revenue model (e.g., SaaS subscription, per-use, enterprise licensing)
• Pricing structure
• Monetization strategy

Not evidenced.

The project was built using:

• Backend: FastAPI, LangGraph, PostgreSQL
• Frontend: Next.js
• Vector DB: ChromaDB
• LLMs: Codex, GPT-5.6
• Parsing tools: Docling
• Other tech: TypeScript, Python, TailwindCSS

The author states:

“Codex & GPT-5.6: Codex was our primary engineering companion.”

This suggests the team used AI-assisted development.

Inference The technical stack is consistent with a modern SaaS product, built for enterprise-grade use with multi-agent workflows and vector search capabilities.

The description states:

“This project was submitted to the OpenAI 2026 hackathon.”

It also says:

“We built TendAI to automate this cognitive burden...”

There is no evidence of revenue, customers, or product adoption beyond the author’s own account.

Not evidenced.

No mention of competitors or market analysis in the description.

Not evidenced.

• The project is a hackathon submission, not a commercial product.
• No evidence of traction, revenue, or customers.
• The author states that Codex and GPT-5.6 were used for development — this may indicate reliance on proprietary tools with uncertain long-term availability or cost.
• No mention of data privacy, security, or compliance features beyond “security-first SaaS,” which is a common claim without verification.

Inference The product is likely in early-stage prototype or proof-of-concept, not yet ready for enterprise deployment or commercial use.

1. What is the current stage of development? Is it production-ready?
2. Have you conducted any user testing or interviews with procurement/legal teams?
3. How do you plan to monetize this product?
4. What are your plans for scaling beyond a single developer?
5. Are there any existing enterprise customers or pilot programs?