The Curriculum / Reader / 3 Expert shared materials
3 EXPERT

3 Expert shared materials

This page compiles 9 files from the repository, verbatim, in reading order. The living version: this folder on GitHub.

3-expert/shared/decision-record-template.md

AI Decision Record Template

Decision title:
Status: proposed / accepted / superseded / retired
Date / owner / approvers:
Decision expiry or review date:

Context

Describe the customer problem, production constraints, and decision boundary. Include the affected workflows, properties or tenants, data classes, dependencies, security and safety considerations, expected volume, latency target, and unit-cost target. Link the relevant system card, evaluations, incident history, and vendor terms.

Options considered

Option Benefits Risks / constraints Evidence Estimated cost Reversibility

Do not compare only model quality. Include operational ownership, data residency, permission model, observability, failure modes, migration effort, and customer impact. For example, an open-weight deployment may lower marginal cost while increasing on-call and security burden.

Decision

State exactly what will be used, by whom, for which cohort, and under which controls. Record the acceptance criteria: offline evaluation threshold, staged rollout plan, SLOs, guardrails, cost cap, and rollback condition. Name the person authorized to stop or reverse the decision.

Consequences and follow-up

List accepted tradeoffs, unresolved risks, documentation updates, migrations, training, and time-bound follow-up actions. Link implementation pull requests, dashboards, feature flags, and launch evidence. A decision record should let a future operator understand why a configuration exists and when it must be reconsidered.

3-expert/shared/incident-post-mortem-template.md

AI Incident Post-Mortem Template

Title:
Incident ID:
Severity / start / end:
Incident lead / communications lead / technical lead:
Affected feature, properties, tenants, and channels:

Executive summary

Describe what users experienced, how many were affected, the worst plausible harm, and the final state. Use concrete language: “The maintenance assistant showed one tenant another tenant’s ticket summary for 17 minutes,” not “there was an issue with retrieval.” State whether any unsafe tool action, legal obligation, or data notification process was triggered.

Timeline

Time Event Evidence / decision
Detection
Containment
Customer communication
Recovery

Impact and scope

List confirmed impact, uncertain impact, and population checked. Segment by property, tenant boundary, model/prompt/retrieval version, provider, region, and release cohort. Include customer contacts, financial effect, support load, and safety or privacy implications.

Technical and control analysis

What changed? What condition allowed the failure? Which controls detected it, failed to detect it, or limited blast radius? Link traces, logs, deployment records, policy decisions, eval evidence, and the exact configuration. Do not attribute root cause to “the model hallucinated”; name the missing validation, ambiguous contract, bad data, unsafe permission, or untested dependency.

Corrective actions

Action Type: containment / corrective / preventive Owner Due date Verification evidence

Lessons and follow-up

Record what should change in the runbook, eval suite, dashboard, release gate, vendor strategy, or training. The incident is closed only after actions are verified, affected users receive required follow-up, and the learning is shared with the relevant team.

3-expert/shared/model-card-template.md

Model Card Template

Model identity

Intended use

Describe target users, supported tasks, operating languages, input limits, and expected environment. State prohibited or unsupported uses plainly.

Training and adaptation

Evaluation

Evaluation Dataset/slices Metric Result Limitations

Include comparison baseline, contamination controls, human-evaluation protocol, calibration, safety/refusal tests, and representative failures.

Risks and mitigations

Describe hallucination, bias, privacy, harmful-content, security, misuse, and distribution-shift risks. Pair every mitigation with its scope and remaining limitation.

Deployment notes

Specify supported quantizations, context limits, inference hardware, expected latency/cost, monitoring, change control, and incident contact.

Version history

Record changed data, weights, behavior, evaluations, and known regressions for every release.

This lesson belongs in a practitioner’s operating system, not a collection of facts to recite. The point is to make a better decision under uncertainty: define the claim, identify the evidence that could change it, name the failure mode, and record the consequence of being wrong. Read it with a live initiative in mind—an internal workflow, customer-facing product, training run, or research bet—and turn the ideas into an explicit test.

Start from the outcome rather than the technology. Specify the user or stakeholder, the task boundary, the data and permissions involved, the success measure, and the unacceptable result. Establish a baseline before changing anything. Then make the smallest reversible move that can distinguish competing explanations. A plausible demo is evidence of possibility, not evidence of reliability, value, or safety.

Keep an evidence log. Separate observations from interpretations, measured performance from anecdotes, and known risks from assumptions. Review representative failures by hand; aggregate metrics can hide the one pattern that matters. For high-impact work, assign a clear owner, predefine an escalation path, and decide what will cause a pause or rollback. Do not outsource accountability to a model, vendor, benchmark, or committee.

The professional standard is legibility. Another capable person should be able to understand why this approach was chosen, rerun the evaluation, find its limits, and improve it without guessing. Build reusable artifacts—datasets, decision records, checklists, incident notes, and release criteria—so each project leaves the next one stronger.

Working exercise

Write a one-page decision memo for a current initiative. State the hypothesis, baseline, evaluation, threshold, owner, risks, and next action. If any of these cannot be stated plainly, the work is not ready to scale.

3-expert/shared/production-ai-checklist.md

Production AI Checklist

Use this checklist as a release gate. Mark each item yes, not applicable, or blocked, with evidence and an owner. A launch is not complete because every box is checked; it is complete when the remaining risk is understood and explicitly accepted.

Product and scope

Data and privacy

Model and prompting

Retrieval and tools

Safety and security

Evaluation and release

Reliability and operations

UX, governance, and follow-through

A failed item is useful information. Do not paper over it with an exception; convert it into a conscious launch decision, a compensating control, a named owner, and an expiry date.

3-expert/shared/red-team-report-template.md

Red-Team Report Template

Assessment name / date / owners:
Systems and versions assessed:
Authorization and rules of engagement:
Test data classification and retention:

Objective and scope

State the harm hypotheses: cross-tenant disclosure, prompt injection through listing documents, unsafe maintenance escalation, tool misuse, identity spoofing, policy bypass, or denial of service. Name the in-scope model, retrieval sources, tools, identities, environments, and explicit exclusions. A red-team report without scope cannot be safely reproduced or prioritized.

Method

Describe attack families, test cases, automation, human review, success criteria, and stop conditions. Preserve exact prompts, documents, identities, configuration, timestamps, and traces in a restricted evidence store. Separate reproducible facts from the tester’s interpretation.

Findings

ID Severity Attack path Preconditions Impact Reproduction Evidence Owner
Critical / high / medium / low

Score severity using exploitability, blast radius, sensitivity of data or action, likelihood, detection time, and effectiveness of existing controls. Demonstrate impact without accessing real customer data or causing irreversible action.

Remediation and retest

For each finding, specify immediate containment, durable fix, compensating control, due date, and retest criteria. A model-prompt adjustment alone is rarely sufficient for a permission-boundary problem. Close a finding only after the exact attack fails, regression tests are committed, telemetry can detect recurrence, and risk acceptance is recorded if any residual exposure remains.

3-expert/shared/safety-case-template.md

Safety Case Template

A safety case is an evidence-backed argument that the residual risk of a specific system and use is acceptable. It is not a policy statement.

1. System and decision

2. Claim

State the claim narrowly: “For [use], under [conditions], the system can be operated with acceptable risk because [controls and evidence].”

3. Hazard register

For each hazard, record the harmed party, severity, likelihood, signals, prevention, mitigation, and residual risk.

Hazard Scenario Preventive controls Detection Response Residual risk

4. Evidence

5. Operating controls

Describe access control, human approvals, runtime policy, logging, monitoring, incident ownership, rollback, and user recourse.

6. Limits and review

List untested conditions, assumptions, expiry date, next review trigger, and the named authority who can suspend the system. Link raw evidence; do not summarize away uncertainty.

This lesson belongs in a practitioner’s operating system, not a collection of facts to recite. The point is to make a better decision under uncertainty: define the claim, identify the evidence that could change it, name the failure mode, and record the consequence of being wrong. Read it with a live initiative in mind—an internal workflow, customer-facing product, training run, or research bet—and turn the ideas into an explicit test.

Start from the outcome rather than the technology. Specify the user or stakeholder, the task boundary, the data and permissions involved, the success measure, and the unacceptable result. Establish a baseline before changing anything. Then make the smallest reversible move that can distinguish competing explanations. A plausible demo is evidence of possibility, not evidence of reliability, value, or safety.

Keep an evidence log. Separate observations from interpretations, measured performance from anecdotes, and known risks from assumptions. Review representative failures by hand; aggregate metrics can hide the one pattern that matters. For high-impact work, assign a clear owner, predefine an escalation path, and decide what will cause a pause or rollback. Do not outsource accountability to a model, vendor, benchmark, or committee.

The professional standard is legibility. Another capable person should be able to understand why this approach was chosen, rerun the evaluation, find its limits, and improve it without guessing. Build reusable artifacts—datasets, decision records, checklists, incident notes, and release criteria—so each project leaves the next one stronger.

Working exercise

Write a one-page decision memo for a current initiative. State the hypothesis, baseline, evaluation, threshold, owner, risks, and next action. If any of these cannot be stated plainly, the work is not ready to scale.

3-expert/shared/slo-worksheet.md

AI SLO Worksheet

Use one worksheet per customer-facing journey. An SLO is an internal target for reliable, valuable behavior. It should be strict enough to protect trust and practical enough that the team can measure and improve it.

Journey:
Users / properties / risk tier:
Owner:
Dependencies: model, retrieval, tools, identity, queues, provider, region.
Review date:

Service-level indicators

Indicator Exact event definition Good event Bad event Data source Owner
Availability
Latency
Quality / groundedness
Safety / escalation
Action completion

Objective and budget

Indicator Objective Window Error budget Exclusions Alert / burn threshold

Avoid a vague “accuracy SLO.” For a leasing assistant, define whether the answer was based on an authorized source, whether it disclosed uncertainty, whether it avoided protected or sensitive inference, and whether the next action was correct. Quality often needs sampled human labels, so state sampling rate, reviewer rubric, lag, and the operational response to a bad result.

Operational plan

Review monthly and after every material incident. If a target cannot drive a decision, it is a report, not an SLO.

3-expert/shared/system-card-template.md

System Card Template

A model card describes a model. A system card describes the complete deployed product: model, prompts, retrieval, tools, users, policies, interfaces, and operations.

System definition

Architecture

Describe input handling, identity/authorization, retrieval, model routing, tool calls, output validation, approval steps, logs, and data retention. Include a diagram link where available.

Behavior and boundaries

List supported tasks, refusal conditions, mandatory escalations, prohibited actions, localization requirements, and user disclosures. Explain what the system must not infer or decide.

Evidence

Claim Evaluation/method Result Owner Expiry

Include real-world monitoring and known failure examples, not only offline scores.

Risk operations

State red-team coverage, policy-engine controls, alert thresholds, incident playbook, rollback method, provider-outage plan, audit trail, and review cadence.

Change log

Every change to model, prompt, retrieval corpus, tools, permissions, or safety policy should have a linked evaluation and approval record.

This lesson belongs in a practitioner’s operating system, not a collection of facts to recite. The point is to make a better decision under uncertainty: define the claim, identify the evidence that could change it, name the failure mode, and record the consequence of being wrong. Read it with a live initiative in mind—an internal workflow, customer-facing product, training run, or research bet—and turn the ideas into an explicit test.

Start from the outcome rather than the technology. Specify the user or stakeholder, the task boundary, the data and permissions involved, the success measure, and the unacceptable result. Establish a baseline before changing anything. Then make the smallest reversible move that can distinguish competing explanations. A plausible demo is evidence of possibility, not evidence of reliability, value, or safety.

Keep an evidence log. Separate observations from interpretations, measured performance from anecdotes, and known risks from assumptions. Review representative failures by hand; aggregate metrics can hide the one pattern that matters. For high-impact work, assign a clear owner, predefine an escalation path, and decide what will cause a pause or rollback. Do not outsource accountability to a model, vendor, benchmark, or committee.

The professional standard is legibility. Another capable person should be able to understand why this approach was chosen, rerun the evaluation, find its limits, and improve it without guessing. Build reusable artifacts—datasets, decision records, checklists, incident notes, and release criteria—so each project leaves the next one stronger.

Working exercise

Write a one-page decision memo for a current initiative. State the hypothesis, baseline, evaluation, threshold, owner, risks, and next action. If any of these cannot be stated plainly, the work is not ready to scale.

3-expert/shared/training-run-checklist.md

Training Run Checklist

Use this before any fine-tune, preference-optimization job, or material retraining. A run that cannot be explained, reproduced, evaluated, and rolled back is not ready.

Decision and scope

Data

Configuration and execution

Evaluation and release

Afterward

Write what changed, what did not, what surprised you, and which next experiment this result justifies. Negative results are assets when their conditions are preserved.

This lesson belongs in a practitioner’s operating system, not a collection of facts to recite. The point is to make a better decision under uncertainty: define the claim, identify the evidence that could change it, name the failure mode, and record the consequence of being wrong. Read it with a live initiative in mind—an internal workflow, customer-facing product, training run, or research bet—and turn the ideas into an explicit test.

Start from the outcome rather than the technology. Specify the user or stakeholder, the task boundary, the data and permissions involved, the success measure, and the unacceptable result. Establish a baseline before changing anything. Then make the smallest reversible move that can distinguish competing explanations. A plausible demo is evidence of possibility, not evidence of reliability, value, or safety.

Keep an evidence log. Separate observations from interpretations, measured performance from anecdotes, and known risks from assumptions. Review representative failures by hand; aggregate metrics can hide the one pattern that matters. For high-impact work, assign a clear owner, predefine an escalation path, and decide what will cause a pause or rollback. Do not outsource accountability to a model, vendor, benchmark, or committee.

The professional standard is legibility. Another capable person should be able to understand why this approach was chosen, rerun the evaluation, find its limits, and improve it without guessing. Build reusable artifacts—datasets, decision records, checklists, incident notes, and release criteria—so each project leaves the next one stronger.

Working exercise

Write a one-page decision memo for a current initiative. State the hypothesis, baseline, evaluation, threshold, owner, risks, and next action. If any of these cannot be stated plainly, the work is not ready to scale.

← README 3 Expert ELI10 companions →