Skip to main content
Worked examples

Investigate recurring audit issues across sites

When the same finding keeps appearing at several sites, an agent tests competing explanations against maintenance, inspection and procedure records. The assurance owner decides the response.

By Murali SidLinkedInPublished Updated

A miner audits ground control at six sites. The same kind of finding keeps showing up: slope inspections overdue, or prism data not reviewed. Is there one shared cause, or six local ones? Today an assurance analyst groups findings by their words and reports the repeats to the board. In this design an agent states competing explanations and asks for the records that would test each one. It also looks at the sites that did not have the finding. The assurance owner decides the response. The formal audit record stays untouched by the agent.

Four steps, left to right. Find a pattern: compare findings across sites A, B and C. Ask why: state competing explanations, such as one shared cause or different local causes. Investigate: seek evidence and counterexamples. Report: explain the support and the uncertainty. A banner says similar wording is a clue, not proof of a common cause.
Test whether recurring audit issues share a causeThe agent checks each explanation against the records before anyone calls it a shared cause.Open image at full size ↗
Experience behind this example

The design builds on the author's own topic-modelling work on geotechnical audit gaps across sites.

The systems involved

The work touches seven of the fourteen layers. The full estate is on the energy and resources page.

How it runs today

The trigger is a periodic assurance review, a question from the board, or a serious finding that looks familiar. The work then runs in nine steps.

Geotechnical audits draw on more than findings. They use slope radar and prism data, inspection records, ground control plans and tailings dam reviews. The tailings standard GISTM (August 2020) sets the frame for tailings.

A swimlane with five lanes: assurance, auditors, audit system, site owners, and executive. Step 1: the assurance manager plans the annual program. Step 2: auditors audit and write a report. Step 3: findings are copied into the audit system by hand. Step 4: site owners are assigned actions. Step 5: site owners close actions, often without a check. Step 6: an assurance analyst groups findings by their words. Step 7: the head of assurance reports repeats to the board. Step 8: the executive decides on a systemic fix. This is an approval. Step 9: assurance checks it at the next audit, months later.
Recurring audit issues today: who does whatToday findings are grouped by their words, and the check comes a year later.Open image at full size ↗

Handoffs

Findings pass from auditors to site owners, then to assurance. Assurance reports to the executive and the standard owners. The next audit checks whether the fix worked.

Where reporting comes in

Audit dashboards track open and overdue actions. The board risk or sustainability committee reads the repeat findings. Certification audits for ISO 45001, 14001 and 55001 and regulator inspections use the same records.

Cycle time and volumes

  • The audit program runs once a year (typical, unsourced).
  • Actions fall due in 30 to 90 days (typical, unsourced).

Pain points

  • The same issue is written in different words.
  • Different issues share the same words.
  • Text is copied between reports.
  • Categories differ by auditor.
  • Audit scope changes from year to year.
  • Closure evidence is weak.
  • Findings are not linked to maintenance or inspection records.

How agents run it

The agent tests explanations. It reads the audit system through a read interface, and other records only through internal requests. It writes its own case and evidence requests. It never writes the audit record.

Similar wording alone does not prove a shared cause. The agent checks whether apparent repeats come from changed audit coverage, copied text or different categories. It stops when the evidence supports a bounded answer, or when the explanations stay unresolved.

A swimlane with five lanes: topic model, agent, assurance owner, owning teams, and the case store. Step 1: the topic model groups findings from the audit system. Step 2: the agent states competing explanations and what would disprove each. Step 3: the agent checks for false patterns such as copied wording or changed scope. Step 4: the agent drafts evidence requests. The assurance owner approves the request list. This is an approval. The owning teams reply with EAM, inspection and procedure records. Step 5: the agent looks at sites without the finding. Step 6: the agent reports support, uncertainty and gaps. Step 7: the assurance owner decides and records any systemic issue in the audit system. This is an approval. The case store links every statement to its source.
Recurring audit issues with an agent: who does whatThe agent tests explanations against records. A person writes the audit record.Open image at full size ↗

What stays with a person

  • The audit opinion and the formal findings. They are formal records, in the formal records zone.
  • Closing actions. An accountable owner signs.
  • Changing a standard. That is a management decision.
  • Anything sent to the board or a regulator.

Where the evidence is kept

The case links each statement to its source record. Requests and replies are kept. The formal audit record is untouched by the agent. The agent cannot change its own log either. That is the observability and audit trail capability at work.

What changes in the systems

  • A read interface on the audit system.
  • An "evidence request" action type, or a request queue.
  • A "systemic issue" link field on findings.
  • Site permissions carried into every read the agent makes.
  • A search index over procedures and past findings, held in knowledge and memory.

What does not change

The audit method and the audit record stay as they are. The same people close actions. Certification audits do not change.

Who does this today

No named deployment of a cross-site audit agent was found by 15 October 2026.

  • Intelex with COMET launched investigations and root cause analysis on 27 October 2025. It aims to find systemic failure patterns in incidents [vendor].
  • Cognite with ABB announced agents on ABB's safety and alarm tools on 21 May 2026. Aker BP is the first customer. Aker BP aims for "hundreds of agents by 2026" [vendor]. The release does not say whether its agents can write anywhere.
  • Aker BP with Cognite lists barrier management among its current agent uses (World Oil, 16 September 2025) [vendor].

Where this sits

The four questions place this agent as follows. Its role is assist. Its permissions are read only on the audit system, and it reaches other records only through internal requests. It writes its own case, notes and requests. It never writes the audit record. It runs at delegated tasks (A2) on the autonomy contract, as designed and as permitted. The assurance owner reviews every report. For the decision on a response, the agent only assists (A1). Its impact is small. A wrong pattern costs review time, and the owner catches it before anything is recorded.

On the risk profile it is Tier 2 (enhanced). Production systems of record and internal requests score Medium. It takes no action inside a deterministic zone. It starts at curated learning (L1). People choose the past findings it learns from.

Measure the result

Measure how often experts agree with the report, and the useful issues it finds. Count false systemic conclusions. Measure evidence completeness and investigation effort. Compare against topic models plus expert review. More clusters or more records found is not the result.

Start with a trial

Take two years of findings from one topic, such as ground control, across all sites. Pick a pattern experts already investigated. Run the agent on it, with requests drafted but not sent. Compare its report with what the experts found. Then run it live on the next audit cycle. Register the agent through the agent lifecycle, with a named sponsor.

Evidence and limits

No named deployment of this agent exists. The as-is is typical practice. The cycle times are typical and unsourced.

The vendor products named above aim at patterns in incidents, not audit findings across sites. None reports a measured result for this work.

The topic-model step comes from the author's own work. The agent's evidence requests and counterexample search are a proposal. They have not been tested.

Next step

Score this agent on the risk profile. Then read how evidence from several sources is combined in knowledge and memory.

Explore this topic

Sources were read on 15 October 2026 unless a line says otherwise. [vendor] marks a vendor's claim about its own product or customer.

Cite this page

Written by Murali Sid, Founder and AI Systems Architect, last updated 15 October 2026. Licensed CC BY-SA 4.0, so quote it freely with attribution.

Murali Sid (2026). Investigate recurring audit issues across sites. Agentic Architecture Skills. https://www.agenticarchitectureskills.com/use-cases/systemic-audit-issues

Machine-readable version of this page: /use-cases/systemic-audit-issues.md

On this page