AI-assisted account review with evidence
A fictional agentic case: a review that starts from evidence instead of a slide someone built the night before.
Independently created. Contains no employer or client implementation detail, internal names or figures.
01The outcome
Each account in the review has a prepared page: the published numbers, what changed, open actions, anomalies and questions—every item cited; decisions and actions are taken and recorded by the manager.
Monthly account reviews start with managers assembling numbers; the discussion that follows has little time and no shared evidence.
What may the agent prepare for a performance review—and where must it stop short of commercial judgement?
Let the agent read published signals and records, summarize and ask; forbid it from recommending commercial strategy, pricing or plan closure.
The monthly performance review (see Revenue Operations) covers accounts that are At Risk or Underperforming. Managers spend the first half of each review reconstructing context: what changed, what the recovery plan said, which actions are overdue. An agent can prepare this—if it stays on the evidence side of the line.
02The reality · current state
What happens today—or in the pilot.
- Managers prepare reviews from exports and memory
- Changes since the last review are not visible
- Overdue recovery actions are discovered in the meeting
- A pilot summary recommended a price reduction
- Numbers in the summary did not match the dashboard
- Questions for the account owner are improvised
03Agent workflow
Each step with its actor, its tool and its authority.
- 01Published data
Target, actuals and segment from the governed data platform—same version as the dashboard.
- 02Signals
Changes since last review: segment moves, coverage, overdue plan actions.
- 03Context
Recovery plan, recent activity, open opportunities.
- 04AI summary
A cited summary, anomalies and three questions for the account owner.
- 05Manager review
The manager reads, challenges and decides in the forum.
- 06Action
Plan outcomes and new actions recorded by people, in the CRM.
04Key dimension · Evidence-backed summary, manager decides
A summary that stops at the evidence
Each item is typed and cited. The limits below are enforced by what the agent can read and by the output format.
- FactPerformance 76 % of YTD target (published, v3)Performance to target, data platform
- Open actionTwo of three recovery actions overdueRecovery plan, due dates
- AnomalyOrders stopped on one product line in AugustOrder lines by product family
- QuestionHas the customer qualified a second supplier?Suggested for the account owner
- No pricing, discount or strategy recommendation
- No closing, escalating or changing a recovery plan
- No numbers that are not the published version
- No statements about people
The pilot’s price-reduction suggestion was fluent and unsupported. Strategy is the forum’s job; the agent prepares the evidence for it.
06Ambiguity policy
When the agent is unsure.
- Numbers differ from the published versionStop
The page is not generated; the data owner is notified
- No recovery plan for an At Risk accountContinue
Stated as an open action, not filled in
- Anomaly without clear causeAsk
Phrased as a question for the owner
07Evaluation
Scored per dimension—never one accuracy number.
| Dimension | Question | Measure | Target |
|---|---|---|---|
| Faithfulness | Do numbers match the published version? | Exact match | 100 % |
| Evidence | Is every item cited? | Items with a source | 100 % |
| Anomalies | Were the anomalies a reviewer would flag found? | Recall on labelled reviews | ≥ 85 % |
| Authority | No strategy or pricing advice? | Out-of-bounds statements | 0 — release gate |
08The trade-offs
Credible options, judged against these premises.
Agent recommends the commercial response
None in this context
Cost: Judgement without accountabilityDashboard only
Small review lists
Cost: Context still reconstructed in the meetingCited summary, anomalies and questions; manager decides
Recurring performance forums
Cost: Output format and limits to govern09The second layer
Questions that change the design.
Evidence
- Which version of the numbers does the summary use?
- How are anomalies evidenced?
- What if data is late?
Limits
- What may the agent never recommend?
- Who reviews the output format?
- How are out-of-bounds statements detected?
Forum
- Who reads the page before the meeting?
- Where are decisions recorded?
- How is usefulness measured?
10Decisions & outputs
What the work produces.
- 01Review page template
- 02Signal and source list
- 03Statement types and citations
- 04Agent limits
- 05Evaluation set
- 06Forum integration