# ADR <number>: <short noun phrase naming the decision>

Status: <Proposed | Accepted | Deprecated | Superseded by ADR <number>> (<YYYY-MM-DD>). Supersedes: <none | ADR <number>>.

Owner: <the person who answers for this record>

How to use this template: the AI Architect course, https://buildingai.in/learning/ai-architect-templates. Number records in sequence and never reuse a number. Keep the record to one or two pages, in the repository at doc/arch/adr-NNN.md. Never edit an accepted record to change the decision: write a new ADR and mark this one superseded.

## Context

State facts in value-neutral language. Name the forces at play (technological, political, social and project-local), including the ones in tension.

Requirements this decision serves. For each: the indicator, the target, the window and conditions, and the measurement point.
- <requirement 1>
- <requirement 2>

Constraints. Mark each one fixed or negotiable and name who can change it.
- <constraint 1: fixed or negotiable, owner>

Options considered. Include configure, buy and build where they apply, and the simplest non-AI option with the reason it is not enough.
- <option 1>
- <option 2>

Evidence. Name the evaluation set and its version, the number of items, the passes, the 95% interval and the date measured. Add the latency percentile and the relative cost of each option. Say what the data do not prove.
- <option 1: passes of n, interval, latency, relative cost>
- <option 2: passes of n, interval, latency, relative cost>

Data sensitivity. Which providers and logs may see which data, and for how long.
- <rule 1>

Expected volume.
- <requests per period>

## Decision

We will <the choice, in full sentences and the active voice>. We will record <the prompt, rubric and model versions> on every request.

## Consequences

Describe the resulting context once the decision is applied, all of it: positive, negative and neutral.

- Positive: <consequence>
- Negative: <consequence>
- Neutral: <consequence>
- Review trigger: <the event or measurement that makes the team revisit this decision>

## Design-review record

- Review date: <YYYY-MM-DD>
- Outcome: <Approved | Approved with conditions | Not approved>
- Conditions, each with an owner and a date: <condition, owner, date>
- Missing evidence, if not approved: <what is missing>
- Checklist answers: <IDs answered No or N/A, each with the reason, owner and date>
- Checklist used: https://buildingai.in/downloads/ai-architect/design-review-checklist.md