Skip to main content
    Use-case library
    Tax

    Tax Research Brief

    Assemble a cited tax-position brief from authoritative sources.

    Retrieval-grounded assistantAutonomy: DraftSpeedQualityMedium effortOrg maturity: AugmentedCFOPartner / MD
    What changed

    Retrieval over an approved corpus of statutes, rulings and guidance now produces a first-draft tax research memo with citations — compressing the research that anchors a position while keeping the reviewer in control.

    How it's built

    Retrieval-grounded assistant (rung 3 of 6). Fetch your evidence, then answer. Fixed path, read-only.

    Not an agent: the sequence of steps is fixed in advance, so the whole path can be tested end to end.

    A language model handles steps 2, 3 and 4. Human: steps 1 and 5.

    Autonomy: T1 · Draft
    Produces a complete output for a human to review and release. Human role: reviews every item and releases it.
    How it is governed
    Cite-or-abstain. Source freshness and access controls inherited from the corpus.
    What the certification exams call this
    • Anthropic (Claude Certified Architect – Foundations (CCAR-F))The augmented LLM: a model with retrieval. source
    • OpenAI (OpenAI agent guidance (Agents SDK, Codex, OpenAI Academy))Data tools that retrieve the context the answer needs. source
    • Google Cloud (Generative AI Leader)Grounding in first-party enterprise data; retrieval-augmented generation (exam §3.3). source
    • Microsoft (AI-901 (Azure AI Fundamentals) and AB-100 (Agentic AI Business Solutions Architect))Knowledge sources and grounding data for Copilot Studio agents (AB-100). source

    How Koko classifies AI · the full ladder is taught in AI & Agentic Delivery Foundations.

    Try it

    Illustrative demo

    Worked example of "Tax Research Brief" on synthetic data — edit the inputs to tailor it. Edit the inputs to tailor the output — it's baked synthetic data, so nothing leaves your browser until you run it live.

    Synthetic demo company (a ~$5B high-growth US AI SaaS) — swap in any name to tailor the output.

    What this run should concentrate on.

    Workflow

    1. 1.HumanFrame the tax question and jurisdictions in scope.
    2. 2.RetrievalRetrieve relevant statutes, rulings and guidance from the approved corpus.
    3. 3.Generative AIDraft the position with citations to each authority.
    4. 4.Generative AISurface contrary authority and open risks.
    5. 5.HumanRoute to a tax professional for review and sign-off.

    Prompt recipe

    For the tax question [...], retrieve the relevant authorities from the provided corpus and draft a research brief stating the position, the supporting authorities (cited), and any contrary authority or uncertainty. Do not assert a conclusion that the cited authorities do not support.
    Try in Ask KokoAI
    Controls required
    • Retrieval restricted to an approved, current source corpus
    • Every assertion cites an authority for verification
    • Tax professional reviews and signs off the position
    • Not tax advice until human-reviewed (disclaimer retained)