Handbook · AI for Professionals

AI for Financial Analysts.

AI will not replace your thesis, your judgment about the key assumptions, or your accountability for a recommendation. It will absolutely replace the hours spent reading a 200-page 10-K, transcribing the gist of an earnings call, and drafting the first version of a memo. This handbook is the practical middle ground: where AI genuinely helps financial analysis, the three rules that keep it accurate and compliant, and five workflows you can use this week — with number-verification and the MNPI line front and center, because in a regulated seat those are the ones that matter.

~18 min readno coding5 workflow recipes1 judgment exercise
This is a guide to working with AI tools, written by an engineer — it is not financial, investment, legal, or compliance advice, and it is not a substitute for securities law, your firm's compliance policies and information barriers, or your professional standards (CFA Institute and equivalents). When they conflict with anything here, they win.
01

Where AI actually helps — and where it doesn't

The single most useful mental model: treat AI like a fast, tireless junior analyst who reads and drafts well, does shaky arithmetic, will fabricate figures and sources, and has no idea what MNPI is. You'd happily hand that analyst a filing to summarize or a memo to draft. You would never publish their numbers unchecked, and you'd never let them near material non-public information.

TaskVerdictWhy
Summarizing filings, transcripts, and reports you provideExcellentGrounded in text you gave it — far less room to invent
First-draft memos, commentary, and narrativesExcellentBlank-page problem solved; you supply and verify the substance
Structuring and explaining a model or approachStrongFrameworks and logic — you build and compute the actual model
First-pass qualitative research & question listsStrongGood at "what should I look into?"; every fact verified
Plain-language explanations of conceptsStrongTranslation of correct analysis — which you check
Numbers, calculations, valuations, and citations — unverifiedNever unverifiedModels miscalculate and fabricate figures/sources — see Rule 1
Anything touching MNPI, or an AI "recommendation"NeverCompliance and judgment — see Rules 2 & 3
02

The three non-negotiable rules

Rule 1 — Every number, calculation, and source gets verified. Every one.

Language models generate plausible text, not correct arithmetic or verified records. They will add a column wrong, misread a figure in a filing, invent a metric that isn't disclosed, and cite a report or data point that doesn't exist — all confidently. In finance a wrong number isn't a typo, it's a bad decision or a mispriced trade. Every figure in a model, valuation, or memo must be tied to a verified primary source and re-computed in your own tools. A number from an AI is a hypothesis to check, never a fact to act on.

Rule 2 — MNPI and confidential data never touch an unapproved tool.

Finance runs on strict rules about material non-public information and on information barriers ("Chinese walls"). Pasting MNPI, deal details, client holdings, or confidential research into a consumer AI tool can breach confidentiality, cross an information barrier, and violate firm and securities-law obligations — and the tool may retain and train on it. The discipline: use only firm-approved, enterprise tools with contractual no-training and retention commitments, follow your compliance and information-barrier policies exactly, and treat what you feed an AI as a compliance decision, not a convenience. When in doubt, keep it out.

Rule 3 — The analysis, the recommendation, and the accountability are yours.

An AI can draft the memo, but it does not have a thesis, cannot be held to a standard of care, and must not make or effectively make an investment recommendation or decision. The judgment — which assumptions matter, what the risks are, whether the thesis holds — is the actual value you add, and it stays with you and your firm under your compliance and fiduciary framework. Use AI to accelerate the reading and drafting; own the thinking, the numbers, and the call. Also: don't pass an AI's confident-sounding market claim to a client as fact, and follow all disclosure and suitability rules unchanged.

03

Five workflows you can use this week

Each recipe: what to give the AI, what to ask, and what you must verify by hand. The prompts are starting points — keep the number-verification and MNPI discipline.

1 · Summarize a filing or earnings transcript

  1. Provide the document (a firm-approved tool per Rule 2):
Summarize this [10-K / earnings call transcript]: the key financial results and drivers, management's stated outlook and its changes vs. prior period, notable risks disclosed, and any new or unusual items. Quote exact figures and language from the document — do not calculate anything I didn't ask for, and do not add outside data or estimates.
You verify: every quoted figure against the actual document (the model can misread or transpose numbers), and treat the "drivers" and "risks" as a reading aid — your own analysis of what matters comes next.

2 · Draft an investment memo around your verified numbers

  1. Give your thesis, your verified figures, and the structure:
Draft an investment memo from my inputs: thesis [in my words], key figures [verified, with sources], main risks [my list], and recommendation [mine]. Use only the numbers and claims I provide — do NOT invent metrics, comps, or forecasts. Structure: thesis, business, financials, valuation, risks, conclusion. Flag anywhere I've left a gap rather than filling it in.
You verify: that no number or claim appeared that you didn't supply (Rule 1), and that the memo reflects your thesis and judgment, not a smoothed-over consensus the model drifted toward.

3 · Structure or stress-test a model's logic

  1. Describe the model approach — no computing, just the framework:
I'm building a [DCF] for [a company in this sector]. Walk me through the structure: the key drivers to model, the assumptions that matter most, common mistakes analysts make here, and what to sensitivity-test. Do not produce numbers or a valuation — I'll build and compute the model myself. Just the framework and the traps.
You verify: nothing to "verify" as fact here, but you build and compute every number yourself (Rule 1) — the AI helps you not miss a driver or a mistake, it does not do the math.

4 · First-pass qualitative research and question list

  1. Ask for the map, then do the actual research in real sources:
For [company / industry], what are the key qualitative questions I should investigate for an investment view: competitive dynamics, moat, management, regulatory exposure, and what could break the thesis? Frame them as questions to research. Do not assert facts, figures, or your own conclusions — I'll gather and verify the evidence.
You verify: everything — this is a research checklist, not research. The "frame as questions, no facts" instruction steers the model away from confidently fabricating claims (Rule 1) toward what it's genuinely useful for.

5 · Explain a concept or your analysis in plain language

  1. Write (or verify) the correct analysis, then translate for the audience:
Rewrite this analysis for [a non-specialist client / IC audience]: [your verified analysis]. Keep every substantive point and number exactly. Plain language, no unexplained jargon. End with the key takeaway and the main risk in one line each. Do not add any claim or figure I didn't include.
You verify: that simplification didn't change meaning or a number, and that nothing reads as investment advice beyond what your compliance framework and the audience allow.
04

The judgment exercise: spot the danger

Three scenarios from real practice patterns. Pick what you'd do — the point is calibrating when the rules bite.

1. The AI's summary states: "Revenue grew 18% YoY to $4.2B, with gross margin expanding 220bps." It's specific and it's due to the IC in an hour. Put it in the memo?

2. You have draft deal terms (MNPI) and want AI to help polish the language fast. The quickest path is a free chatbot. Do you use it?

3. A client asks "should I buy this stock?" and the AI produces a confident, well-reasoned buy case. Forward it?

05

Choosing tools: the questions that matter

You don't need to understand the technology to procure it well. You (and compliance) need answers, in writing, to five questions:

QuestionAnswer you want
Is our data used to train your models?No, contractually — not "you can opt out somewhere in settings"
How long are prompts and documents retained?Defined, short, and deletable on request
Where is data processed and stored?A stated jurisdiction compliance can accept
Security and access controls?SOC 2 Type II or equivalent, encryption, per-user controls
Audit logs and admin oversight?Yes — records of who used it for what, for compliance

General-purpose enterprise AI (Claude, ChatGPT's business tiers) covers the summarizing, drafting, and structuring recipes here — none of which compute or decide. Finance-specific tools add data integrations, source-linked answers, and workflow features — evaluate their accuracy and data-handling carefully, and route them through compliance. And your firm's policy and information barriers precede everything here; if there's no AI policy yet, these three rules are a reasonable seed for one.

06

Quick answers

Can I trust AI to do the math in a model?

No — build and compute every number yourself and tie it to a source. Models make confident arithmetic errors and fabricate figures. Use AI to structure and explain; use your tools to compute.

Can I use AI on confidential deal or client data?

Only in firm-approved, enterprise tools with no-training terms, and only per your compliance and information-barrier policy. MNPI and confidential data never go into consumer tools.

Can AI cite sources for me?

Treat every AI citation as unverified — models fabricate references and data points. Verify each against the primary source before relying on it.

Where should a skeptical analyst start?

Recipe 1 — summarizing a filing you provide, then checking every quoted figure. Immediately useful, keeps you in the "verify the numbers" habit, and shows the genuine strength (fast reading of documents you supply).

Finished this one? 0 / 99 Handbooks done

Explore the topic

See this alongside everything else on the same subject — handbooks, system designs, challenges and tools, in one place.