Financial-Services

Clarity AI

by Clarity AI

Overview

Assess how investment funds may be classified under the European Commission's proposed SFDR 2.0 framework — directly from Claude. Search funds by name, ISIN, or CUSIP and get simulated Article classifications based on Clarity AI's regulatory disclosure data and proprietary modelling of the November 2025 proposal. Ideal for ESG analysts, portfolio managers, and compliance teams preparing for the regulatory transition before final rules are published. This is a live tool that will evolve as we learn more from ongoing EU discussions and guidance.

Tools

fetch_esg_score_by_company

ChatGPT

Fetch the ESG Risk summary (overall, Environmental, Social, Governance scores) for a company inside a portfolio.

get_all_mandates

ChatGPT

List all mandates available in Clarity AI, including their names, descriptions, metrics and thresholds. Each mandate's metrics (with names and descriptions) are included — use them to understand what behavior the mandate enforces, not just the mandate's name. If a mandate name is not specified, use this to enumerate options. Also use this when the user's mandate reference is vague or unrecognized — retrieve the full list, then explicitly state which mandate you matched to the user's reference (or that none was found) before proceeding. If no match is found, list the available mandate names and ask the user which one they mean. Always search all mandate metrics (not just names) when the user references a thematic area (e.g. "weapons", "carbon") — multiple mandates may cover the same theme.

get_all_portfolios

ChatGPT

Retrieve all portfolios (id, name, last access date, AUM, total portfolio value with currency and amount), sorted by name. If a portfolio name is specified by the user, no need to be called when running analysis, tools will find a portfolio using its name. If a portfolio name is not specified, you can use this. This tool only returns the user's own portfolios. There is no access to external funds, peer groups, industry benchmarks, or third-party portfolio data.

get_mandate_breach_summary

ChatGPT

Get a concise list of breaching organizations in a portfolio for a mandate, sorted by breach count and weight, with a short explanation for each failing metric. Use this specifically when the user wants to enumerate breaching companies, count breaches, or identify worst offenders. For pass/fail compliance checks or metric score questions, use run_portfolio_compliance_report instead. All organizations listed are breaching; all metrics listed under each organization are failing (status: FAIL). Portfolio and mandate names can be provided directly and the tool will resolve them. The list of breaching companies is limited to a sample. If a company name is specified, the result includes whether that company is breaching (organizationBreaching field), plus the breach sample for context. When no portfolio is specified, call get_all_portfolios first to enumerate portfolios, then call this tool for each one.

run_portfolio_compliance_report

ChatGPT

The primary tool for any compliance check — use this when the user asks whether a portfolio passes or fails a mandate, asks for a compliance score, or asks about threshold values. Returns the portfolio-level pass/fail result, metric compliance scores (e.g. ESG_RISK:OVERALL at 65.5% vs threshold 75%), and a sample of breaching companies. Portfolio and mandate names can be provided directly and the tool will resolve them. The list of breaching companies is limited to a sample. If a company name is specified, only that company is returned in the breaches.

interpret_sfdr20_result

Claude

Normalize raw SFDR20 flags into category-level assessment evidence.

search_securities

Claude

Search securities by keyword, ISIN, or CUSIP through the upstream Clarity SFDR demo API.

sfdr20_assess_fund_name

Claude

Preferred for fund names, partial names, and natural-language requests. Resolve a fund from free-text (for example S&P 500 or Nordea 1 Global Climate and Environment), then run the SFDR20 check and return an interpreted assessment. Example: use this for 'Show the SFDR 2.0 category assessment evidence for Nordea 1 Global Climate and Environment Fund'.

sfdr20_check

Claude

Deprecated alias for sfdr20_check_by_isin. Keep for backward compatibility only. Do not use for fund names or natural-language requests.

sfdr20_check_by_isin

Claude

Use only when the user already provided an explicit ISIN. Do not use for fund names, partial names, or natural-language fund requests; use sfdr20_assess_fund_name instead.

sfdr20_check_by_query

Claude

Deprecated alias for sfdr20_assess_fund_name. Keep for backward compatibility only. Prefer sfdr20_assess_fund_name for fund names and natural-language requests.

Links

Documentation ↗Privacy Policy ↗

App Stats

Tools

Prompts

Mar 8, 2026

First seen

ChatGPT, Claude

Platforms