Agents that show their working.
An estimator spends two days reading a tender before anyone can say whether it is worth bidding. A quantity surveyor takes a client schedule of rates on trust because re-measuring it from the drawings costs more than the error usually does.
Both of those are reading jobs. Demiton agents do the reading and hand back something you can check - every claim cited to the record it came from.
An answer nobody can check is not evidence. Agents read the same registers the five diseases are caught in and hand back the working: every figure with the record it came from, every quantity with the drawing it was measured off. That is what lets an output survive a conversation with a client.
What the five diseases areIncluded on Baseline.
Tender Brief
Composes the tender launch brief: a two-pager telling an estimator or GM everything Civil Memory knows about a tender and how your firm is positioned to pursue it. Scope and quantities, compliance posture, track record against the buyer, risks, and a pursue recommendation.
Every claim in the brief cites the fact or document it came from. Where Civil Memory does not know something, the brief says so rather than filling the gap.
Schedule of Rates Verification
Takes a client schedule of rates and independently re-derives each verifiable quantity from the drawings, then reconciles its own derivation against the schedule and reports where the two disagree.
The measurement is exact, not estimated. Each discrepancy carries the crop of the drawing it was derived from, so a quantity surveyor can check the working rather than trust the output.
They write to the record, not to a chat window
An agent run produces facts in Civil Memory - sourced, dated, attributed to the connector that fetched them. The output is a durable record you can query later, not a message that scrolls away.
Every run is identity-bound and audited
Agents execute under a named user through Microsoft Entra ID, not a shared service account. Every step, tool call and document read is logged. You can see exactly what the agent looked at before it reached a conclusion.
They stop rather than guess
Agents run against a budget of steps, tokens and wall-clock time, and they are built to report a gap rather than invent a figure to fill it. A brief that cannot find a quantity says the harvest is missing.
Agents read what your team does not have time to.
Tender Brief runs on what Baseline already holds. The measurement agents read drawings, so they need a document source connected - SharePoint or Dropbox - which Baseline integrates. Tell us which documents you hold and where, and we will tell you which agents earn their keep.
Common questions
What is a Demiton agent?
A Demiton agent is a defined piece of work that runs against your Civil Memory record and writes its output back as sourced facts. Agents run under a named user identity, are fully audited, and cite the record behind every claim they make.
What does the Tender Brief agent produce?
A cited two-pager on a tender: scope and quantities, your compliance posture, your track record against that buyer, the risks, and a pursue or decline recommendation. Every claim cites the fact or document it came from.
How does Schedule of Rates Verification work?
It independently re-derives each verifiable quantity from the drawings - drawing tables, symbol counts, exact geometric measurement, spacing arithmetic and bar-schedule tonnage - then reconciles those derivations against the client schedule and reports the discrepancies with visual evidence.
What do agents need to run?
Agents are included on Baseline. Agent and model time is sold in hours, not runs, because a cited tender brief takes minutes and verifying quantities out of a drawing set can take most of an hour. Schedule of Rates Verification needs a document source such as SharePoint or Dropbox connected.