Deployment evaluation · 13

Agronomic outcome

Measure yield, saleable quality, crop damage, treatment efficacy, input use, soil effects and timeliness.

Evidence statusField evidence framework · crop, season, site and operating-envelope validation requiredLast reviewed: 16 August 2026
13

FUURAA thesis

The robot succeeds only when the biological production system improves without unacceptable shifted harm.

Engineering map

Turn the title into engineering objects that can be observed, measured and reviewed.

Each layer states the boundary to establish and the evidence needed for the next decision.

01

Primary outcome

Predefine the crop or soil result that matters most.

02

Trade-offs

Measure quality, damage, inputs, emissions, compaction and labour.

03

Follow-up

Observe effects at the biologically relevant later time.

Verification questions

Write the questions first, then decide whether a demo, test, pilot or operating record can answer them.

Each question needs an object, conditions, denominator, threshold and accountable decision owner.

  1. 01

    Was the primary outcome defined before testing?

  2. 02

    Is the comparator current practice?

  3. 03

    Are delayed damage and retreatment captured?

  4. 04

    Do results repeat across blocks and seasons?

Evidence to preserve

Enable the next reader to reconstruct conditions, results, failures and the decision.

A conclusion alone loses reviewability; raw records, configuration and exclusions matter too.

  1. 01

    Evidence package 1

    Pre-registered outcome and analysis plan

  2. 02

    Evidence package 2

    Crop, soil, input and labour dataset

  3. 03

    Evidence package 3

    Seasonal follow-up and uncertainty

Scope boundary

State what this evidence still cannot be generalised to.

Sources and evidence status

Read standards scope, measurement evidence and application conclusions separately.

Source dates and review status remain visible; external sources open in a new tab.