Knowledge / AEC-native data

Tender packs and ITT documents

The invitation to tender and its enclosures: employer's requirements, drawings, specifications, pricing documents, conditions and returnable schedules.

A tender pack is the largest document set a team reads in the shortest time. Employer's requirements, drawings, specifications, pricing documents, conditions, site information and returnable schedules arrive together, often from several authors who did not read each other's work, and the estimating team has the tender window to find what matters before the price is committed. What gets missed at tender gets paid for on site. Structured knowledge makes the pack something a bid team can question directly, with every answer traceable to the document and page it came from.

What teams need to ask of it

  • What is the full scope, including the items mentioned once in a schedule and nowhere else?

  • Where do the employer's requirements, the specification and the drawings contradict each other?

  • Which risks have been transferred to us in the conditions, the preliminaries or the site information?

  • What is the order of precedence between the documents, and which one wins where they disagree?

  • Which returnables and qualifications are required, and what has changed since the last issue of the pack?

  • What is provisional, to be confirmed, or missing from the pack that we would be pricing blind?

  • What did we find on the last tender from this client that we should look for again?

Why generic AI gets it wrong

A tender pack is not one document but a pile of them with a pecking order. A general-purpose model reads the pile and produces a summary that blends the employer's requirements with the specification and the drawings as though they agreed. They usually do not, and the disagreements are precisely what a bid team needs to find, because the order of precedence in the conditions decides which one they will be held to.

Scale is the other failure. The item that costs the most is often a single line in a returnable schedule or a note on a site plan. A model that samples the pack rather than reading all of it will not find that line, and it will not tell you that it did not look. The summary looks complete, because summaries always do.

One question, answered

QUESTION

ANSWER

SOURCES

See it on your data.

See it on your data.

We onboard a focused slice of your project data, configure the ingestion paths, extract a structured context graph, and build a workflow against the resulting structured knowledge layer.

Related to

The tender pack contains the first issue of the employer's requirements, the specification, the drawings and the conditions of contract, and the bill of quantities or pricing document sits inside it. Tender document review is the workflow that runs across the whole pack.

Frequently asked questions

Frequently asked questions

How much of the pack does it read?

Can it compare this tender with previous ones from the same client?

Does it produce the bid, or the review?

Related pages