Asylum Case Summarisation cuts transcript review by 23 minutes

In Home Office pilots in 2024, decision-makers using the Asylum Case Summarisation tool reviewed interview transcripts 23 minutes quicker per case than a comparison group, a 32% time saving.

  • 1 for an organization

    Decision-makers using the tool reviewed transcripts 23 minutes quicker per case than the comparison group, with no change in decision quality in a dip-sample. The pilots were small and times were self-logged.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

Only the deployer supports the benefit.

Size

No magnitude yet: distribution and frequency are not documented.

Compared with

A comparison group of decision-makers in the same Decision Making Units who worked without the tool. Measured.

The system’s part
The evaluation compared decision-makers using the tool with a comparison group without it in the same units, and it credits the 23-minute difference to the tool. The groups were not randomly assigned, times were self-logged and the pilots were small. The document says that the tool uses a large language model.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Reduced Task Time
System
Asylum Case Summarisation (ACS) tool
Made by
Home Office (the evaluation names no outside supplier)
Used by
Home Office asylum decision-makers in two Decision Making Units
Where
United Kingdom
Stage
In a pilot
Date
Kind
Aggregate result
Broad benefit
Operational improvement (faster data management, decision-making)
Collections
Scrutiny and findings
Last revised
1 November 2026

Sources

  1. Evaluation report, by the organization that used it.

    Home Office. Evaluation of AI trials in the asylum decision making process. Research and analysis, GOV.UK, 29 April 2025.

    On average, the test group reviewed transcripts 23 minutes quicker than the comparison group (a 32% time saving).

Details

AI system

Workflow

The tool used a large language model to extract and summarize information from asylum interview transcripts. Technical specialists reviewed every summary before use and removed the 9% that were inaccurate or had missing information. Decision-makers used the summary as an aid and still worked through the usual decision process.

Follow-up

Conditions for replication

Summaries must be checked for accuracy before decision-makers rely on them. Decision-makers must keep making the decision themselves, with the summary as an aid. A full rollout needs a larger evaluation, as the pilots were small and the units were not representative.

Entry details

Sector

Asylum and immigration administration.

Purpose

The Home Office introduced the Asylum Case Summarisation tool to summarize asylum interview transcripts with a large language model, so that decision-makers can refamiliarize themselves with a case faster.

30 more questions not yet checked

model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this benefit

Peter H. Vartanian. (2026). Asylum Case Summarisation cuts transcript review by 23 minutes (AIBD-1193). Artificial Intelligence Benefits Database, edition of 2 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1193.html (archived at https://doi.org/10.7910/DVN/AADSII, version 9.0)

BibTeX Data Field definitions