Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.trubuild.io/llms.txt

Use this file to discover all available pages before exploring further.

Every TruBuild project comes with an AI chat that has read access to whatever you’ve uploaded inside that project. Ask it a question in plain English and it answers with citations back to the source documents. This feature is self-contained. The more you’ve uploaded, the more the chat can answer — but even a single uploaded document is enough to start asking questions. You don’t need to have run any other feature first.

​
Why this matters

In a traditional procurement workflow, “answer a question about the tender” means:
1

Open several files

The reference BOQ Excel, a vendor bid, a Word doc with technical notes.
2

Search through them

Ctrl+F through each document to find the relevant section.
3

Cross-reference

Check evaluator comments, the email thread with the vendor, the technical justification.
4

Compose an answer

Summarize back to whoever asked, usually in an email.
Even for a senior procurement lead who knows their tender inside out, a single “what’s Vendor C’s position on HVAC commissioning support?” is easily a 10-minute answer.

​
With TruBuild chat

Type the question. You get the answer in seconds, with clickable citations to every source document that backs it up.

​
Example questions

Real examples from customer workspaces (each category works standalone — you only need to have uploaded the relevant document type):
  • “What’s the spread on the top 10 items by dollar impact?”
  • “Which vendor priced this package cheapest?”
  • “Summarize all lines where Vendor C is more than 30% above the average.”
  • “What’s the total delta between Round 1 and Round 2 for Vendor B?”
  • “Compare Vendor A and Vendor C’s project management approach in 5 bullets.”
  • “Which vendor has the strongest HSE track record on similar projects?”
  • “What does Vendor D say about commissioning their control system?”
  • “Are there any open queries that could delay award?”
  • “Summarize the clarifications we’ve received from Vendor B so far.”
  • “What are the three biggest risks in this RFP?”
  • “Summarize this document in a paragraph.”
  • “Find all mentions of retention across all uploaded documents.”

​
How it works

The chat is backed by a retrieval system over your project’s uploaded documents:
  1. Your question is analysed to determine which documents are likely relevant
  2. Those sources are retrieved and given to the AI along with your question
  3. The AI composes an answer grounded in the retrieved data
  4. Every claim in the answer is linked back to the specific source
You’ll see citations inline like [HVAC BOQ line 47] or [Vendor C technical, p. 12]. Click any citation to open the source at the exact location.

​
Scopes

The chat is always scoped to a specific project — it can’t accidentally answer questions about a different tender. Within a project, your visibility follows your project role. Ask a question outside your scope and the chat will explain what you’d need access to.

​
Step-by-step

1

Upload something

Any supported document in the project — an RFP, a BOQ, a contractor submission, a PTC response, or a query register.
2

Open chat

Click the chat icon in the project sidebar. Chats are project-scoped; you can have multiple simultaneous conversations (e.g., one per topic).
3

Ask a question

Plain English. Be specific about which document or vendor when it matters.
4

Follow up

Chats are stateful within a conversation — “and what about Vendor B?” knows what you’re asking about.
5

Check citations

Every factual claim has a citation. Click to verify against the source.
6

Export (optional)

Promote a chat summary to a project note, or export the conversation as a PDF for a read-out.

​
Best practices

The chat is excellent for finding things and summarizing. For anything going into a decision, verify against the structured view — the citations make this fast.
In a project with multiple documents, start with “In the RFP, …” or “Looking at Vendor B’s submission, …”. Cuts answer time and reduces wrong-scope answers.
Five minutes in the chat before a meeting produces a much sharper read-out than 30 minutes of file scrolling.
The chat is useful for finding relevant tender context. For final scores, prices, PTC statuses, and award positions, verify against the structured commercial, technical, query, or award screens.

​
Privacy

All chat context stays within your project boundary. Your prompts and the retrieved context are never used to train models or shared across customers.