AI Stellar Reports & Documents
Plan, evidence, draft, review and release high-stakes reports with AI, keeping the argument, the facts and the voice yours.
- Level
- Practitioner
- Learning time
- 18 hours
- Price
- $199
- Credential
- Valid 3 years
What changed in this edition.
- The full course is now built: 45 lessons, 7 module pretests and retrieval checks, 7 AI role-play labs and a capstone, replacing the 5 lessons and placeholder pages of v1.
- New modules on evidence and research (Nexus Research, Search, Ask, Mega Parser and the Research Brief standard), review and red-teaming, and confidentiality, version control and release.
- New lessons on plain language, accessible documents, the Strategy Document Standard, board papers and RFP responses, honest charts, and numbers in prose.
- AI role-play labs with an executive sponsor, an over-eager AI drafter, a skeptical red-team reviewer and a compliance counsel, plus a capstone memo scored by AI against a published rubric.
- A full exam bank written to the v2 rules: LOFT forms of 55 selected-response items plus 4 AI-conducted performance tasks, replacing the 10-item sample.
- Hours stated honestly: about 18 hours of seat time, counted lesson by lesson.
What you will be able to do.
- You will be able to analyze a document's readers and decision, choose the right document type and governing standard, and name a load-bearing claim before drafting.
- You will be able to structure an argument top-down with a MECE claim tree, an SCQA opening and headings that assert.
- You will be able to direct an AI drafter with a 5-part brief and instruction specs, choose the model and scope safely, and run a critique loop with auditable change lists.
- You will be able to find, verify and cite evidence using Nexus Search, Ask, Research and Mega Parser, label claim strength and run a pre-release fact-check.
- You will be able to turn data into honest charts, precise numbers and an executive summary a reader can decide from.
- You will be able to write in plain language for several channels and produce accessible documents without losing precision.
- You will be able to run a review ladder, red-team a recommendation, write for the legal and compliance reader and defend the document under questioning.
- You will be able to protect confidentiality, control versions with the Correction & Supersession standard and release documents with a checklist.
Who it's for
- Consultants and analysts who ship written deliverables under deadline
- Operators and managers writing board papers, decision memos and recurring reports
- Founders and finance leads writing investor and stakeholder updates
- Bid teams and proposal writers responding to RFPs and grants
- Researchers and strategy staff producing research briefs and strategy documents
- Communications professionals preparing high-stakes written material
Not covered here
- Visual and slide design (see AI UI/UX Design Systems)
- Creative and long-form fiction writing
- Statistical methodology (the course teaches how to report findings honestly, not how to derive them)
- Legal drafting and legal advice (the course teaches recognition and routing to counsel)
7 modules, 67 lessons.
About 18 hours of learning. Open a module to see every lesson.
-
Audience, claim and structure
Before a paragraph exists, decide who reads, what they must decide, which document type and standard apply, and the one sentence the document argues. Then build the pyramid, the opening and the headings.
- Module 1 pretest: Audience, claim and structure
- The load-bearing claim — what your document is actually arguing
- Audience analysis — who decides, who influences, who can veto
- Choosing the document type — and the standard that governs it
- The pyramid: governing thought first, then support
- SCQA — opening that earns the reader's attention
- Headings that assert and signposts that carry the argument
- Three structural failures and how to repair them
- Outline-first authoring with an AI partner
- Lab 1: Restructure a bottom-up update for an executive sponsor
- Module 1 retrieval check
-
Directing the AI drafter
Brief the model as a contract, choose the model and scope safely, assemble drafts in Nexus Documents from standards, templates, briefs and design systems, write instruction specs, and critique with named rules and change lists.
- Module 2 pretest: Directing the AI drafter
- The 5-part drafting brief — audience, decision, evidence, voice, forbidden moves
- Choosing the model and grounding the draft
- Nexus Documents — standards, templates, briefs and design systems
- Writing an instruction spec the model can follow
- The critique loop — hedging, padding and unsupported claims
- Walkthrough: from brief to first draft in Nexus
- Scenarios: slop, sycophancy and scope creep
- Lab 2: Brief and critique an over-eager AI drafter
- Module 2 retrieval check
-
Evidence and factual integrity
Recognize the four shapes of fabrication, judge source quality and claim strength, find and verify evidence with Nexus Search, Ask, Research and Mega Parser, write briefs to the Research Brief standard, and run the pre-release fact-check.
- Module 3 pretest: Evidence and factual integrity
- The hallucination taxonomy — fact, citation, statistic, attribution
- Evidence, source quality and claim strength
- Finding evidence in your vault: Search, Ask and Files
- Source documents with Mega Parser
- Running grounded research in Nexus Research
- Worked example: a brief that meets the Research Brief standard
- The citation trail and the pre-release fact-check pass
- Lab 3: Fact-check an AI-drafted briefing against its sources
- Module 3 retrieval check
-
Data narratives and executive summaries
Tables and charts do not argue; people do. Choose the insight that serves the decision, chart it honestly, write numbers precisely, put the decision in an executive summary that stands alone, and structure recurring reports around what changed.
- Module 4 pretest: Data narratives and executive summaries
- Tables and charts do not argue — people argue
- The insight-evidence-action triple, worked
- Honest charts and tables
- Numbers in prose: precision, comparison and causation
- The executive summary that stands alone
- Recurring reports: the what-changed frame and Nexus Reports
- Lab 4: Turn a data extract into a one-page narrative for a CFO
- Module 4 retrieval check
-
Formats, style, plain language and accessibility
One argument, many shapes: report, deck, board memo, update, strategy document, proposal. Then the finishing craft: plain language that keeps every obligation, a consistent voice without AI tells, ordered editing passes and documents everyone can read.
- Module 5 pretest: Formats, style, plain language and accessibility
- The four channels — report PDF, exec deck, board memo, investor email
- Strategy documents under the Strategy Document Standard
- Board papers, proposals and RFP responses
- Plain language without losing precision
- Voice consistency and the AI's tells
- Four editing passes: structural, line, copy and proof
- Accessible documents
- Lab 5: Plain-language and accessibility rewrite
- Module 5 retrieval check
-
Review, red-team and defense
Plan who reviews what and in what order, attack the recommendation before the decision, write for the legal and compliance reader, resolve conflicting feedback by evidence and decision rights, and defend the document under questioning.
- Module 6 pretest: Review, red-team and defense
- The review ladder: who checks what, in what order
- Red-teaming and the pre-mortem
- Writing for the legal and compliance reader
- Scenario: conflicting reviewer feedback
- Defending the document under questioning
- Lab 6: Face a skeptical red-team reviewer
- Lab 7: Revise a proposal for the legal and compliance reader
- Module 6 retrieval check
-
Confidentiality, version control and release
Classify before drafting, decide what each model may see, draft where access matches the audience, version and supersede without destroying history, release with a checklist, capture lessons into shared specs, and make sound release-day calls. Ends with the capstone.
- Module 7 pretest: Confidentiality, version control and release
- Confidentiality: classification, models and permissions
- Version control and supersession
- Finishing and release
- Closing the loop: capturing what you learned
- Scenarios: release-day decisions
- Module 7 retrieval check
- Capstone: Produce and defend a decision memo from a source dossier
Practice against someone who pushes back.
Labs run in your browser as AI role-plays. An AI plays the person on the other side of the scenario — with their own goals and objections — and your work is scored against the published rubric. There is nothing to install.
-
Lab 1 · Audience, claim and structure
AI role-play: restructure a chronological project update into a load-bearing claim, claim tree, SCQA opening and assertive headings, and defend it to an executive sponsor who wants to keep the chronology
-
Lab 2 · Directing the AI drafter
AI role-play: brief an over-eager AI drafting assistant with a 5-part brief and run at least two named-rule critique passes on a board memo section
-
Lab 3 · Evidence and factual integrity
AI role-play: fact-check an AI-drafted briefing against a five-source pack, build a claims register and hold firm with the author
-
Lab 4 · Data narratives and executive summaries
AI role-play: turn a renewals table into an insight-evidence-action triple, a 250-word executive summary, a chart specification and alt text for a CFO who wants a bigger headline
-
Lab 5 · Formats, style, plain language and accessibility
AI role-play: rewrite a dense policy update in plain language, fix its accessibility problems and write a staff email, reviewed by an accessibility and communications lead
-
Lab 6 · Review, red-team and defense
AI role-play: answer six objections from an assigned devil's advocate, run a pre-mortem and an assumptions check, and revise the recommendation
-
Lab 7 · Review, red-team and defense
AI role-play: revise a proposal section flagged by compliance counsel, keep it persuasive and route open items to their owners
-
Lab 8 · Confidentiality, version control and release
Capstone: write a decision memo from a seven-item source dossier, then answer an AI-played executive sponsor's questions and late request
Produce and defend a decision memo from a source dossier
Artefact submitted in the capstone lab, AI-scored against the published rubric
Pass mark: 72%
Scored on
- Structure and load-bearing claim20%
- Evidence and citation integrity25%
- Data narrative and executive summary15%
- Style, plain language and accessibility10%
- Review readiness and defense15%
- Confidentiality and release discipline15%
One exam. A credential anyone can verify.
The exam
- Items per form
- 59
- Time allowed
- 120 min
- Pass mark
- 72%
- Performance tasks
- 4
- Attempts included
- 2
- Wait between attempts
- 7 days
- Online and timed, taken on learn.brrain.io.
- Your form is assembled for you from the course's item bank, so no two candidates sit the same paper.
- Performance tasks are conducted by an AI examiner: you work through a realistic scenario and are scored against a published rubric.
The credential
- A verifiable digital badge in your name.
- A public verification page at learn.brrain.io/verify, so an employer or client can confirm it.
- Valid for 3 years.
- Renewal: Every 3 years by passing the then-current exam, with CE modules completed
Frequently asked.
Do I need to install anything for the labs?
No. Labs and the capstone run in your browser on learn.brrain.io as AI role-plays: an AI plays the person on the other side of the scenario, and your work is scored against the rubric published with the course.
How is the exam delivered?
Online and timed: 59 items in 120 minutes, on a form assembled for you from the course's item bank. 4 of the items are performance tasks conducted by an AI examiner: you do the work rather than pick an answer. The pass mark is 72%.
What if I don't pass first time?
You have 2 attempts, with a 7-day wait after an unsuccessful attempt. Further exam attempts can be bought for $199 each.
How long is the credential valid?
3 years. You receive a verifiable digital badge with a public verification page at learn.brrain.io/verify, so anyone can confirm it is genuine.
I hold the v1 credential. Is it still valid?
Yes. Credentials earned on v1 remain valid and verifiable at learn.brrain.io/verify. When you renew, you sit the then-current version of the exam.
Can my company enroll a team?
Yes. Firms can buy a certification bundle for $2,999 per firm per year — see the pricing page — or contact us to arrange enrollment for a larger group.
Related courses.
AI Stellar Reports & Documents
Plan, evidence, draft, review and release high-stakes reports with AI, keeping the argument, the facts and the voice yours.