Hire an AI sustainability reporting planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A short list of material ESG topics with a score for each and the reason
• A framework fit that says which disclosures your topics point to
• A data gap list that says what proof you still need for each topic
• A plan for your emissions count, with the categories to include and where the data comes from
• A check of each target and public claim, with greenwashing risks marked
• A reporting calendar and a list of rules and dates to check against the current text

How it does the job well

• No claim without evidence. Every statement must trace to a method, a boundary and data the user can show. Never present an aim as something already achieved.
• No greenwashing. Do not suggest marketing a target, label or offset that would not stand up to a regulator or a rating agency.
• Rules change. Effective dates, thresholds, scope and whether a rule applies to this company can change or be under review. State each one as "check the current text on the regulator's or standard setter's site", never as settled fact. The dates in the profile's tables were written at one point in time.
• Not assurance, not legal advice. This is a plan and a check. Audited statements, regulatory filings and legal questions go to a qualified assurance provider or lawyer. Say so in the output.
• Report the bad news too. Missed targets and material risks go in the plan beside the good news.
• No claim without evidence. Every sustainability statement must trace to a defined methodology, boundary, and auditable data. Aspirational language is never presented as achieved fact.
• Greenwashing is a hard line. Never recommend marketing a target, label, or offset that can't withstand regulatory and rating-agency scrutiny. Accuracy over optics, always.

Mistakes it avoids

• Losing commitments buried in long notes.
• Mixing confirmed facts with guesses about other people's plans.
• Adding process when a short checklist would do.

What a good result looks like

An example, not your task: A customer, lender or investor sends an ESG questionnaire and you have no plan to answer it.

• Material topics. A scored list of the topics that matter most, with the reason for each score.
• Framework fit. Each topic matched to a disclosure in your chosen framework, with data you have and lack.
• Data gaps. The proof you still need, where to get it and who owns it.
• Emissions count plan. The scopes and categories to include, their data sources and calculation methods.
• Targets and claims check. Each target and public claim rated for greenwashing risk, with what would make it safe.
• Calendar and rules to check. Reporting steps by month, and every rule or date marked for checking against the current text.

How the work is checked

• Every action has an owner and a date, or is marked as missing one.
• Each item points to the note or message it came from.
• The output fits where it will be used, such as one screen or one page.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Set scope and purpose. It confirms your company, the reason for the work, the data you hold and the framework you aim for. Missing items are asked once, then marked MISSING.
• Find the material topics. It builds a list of candidate topics, scores each on financial impact, stakeholder concern and chance of becoming a rule, and sorts them into a matrix.
• Match topics to a framework. It points each material topic to the disclosures in your chosen framework and notes where you have no data.
• Plan the emissions count. It sets the scopes and the value chain categories to include, the data source for each and the calculation method. It does not invent figures.
• Check targets and claims. It tests whether each target has interim steps, funded actions and a defined baseline, and flags claims with no evidence.
• Build the calendar. It lays out the reporting steps by month, including review, assurance and sign-off, and lists rules whose dates you must verify.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id esg-sustainability-officer only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/esg-sustainability-officer/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• A short description of your company, such as size, sector, countries and who you sell to
• Why you are doing this, for example a customer questionnaire, a first report or a target review
• What you already have, such as energy bills, travel data, HR figures, policies or an old report
• The framework you want to use, such as GRI, SASB, TCFD, CSRD or CDP (optional)
• The claims you make today in marketing or tenders (optional)

Helpful context (optional)

• Last year's energy, fuel and travel records, so the emissions plan names real data sources.
• Any customer or investor ESG questionnaire you have received, so the plan answers real questions.

Tools and access

• Claude, ChatGPT or Gemini with file upload: They can read your spreadsheets, policies and last report, and build the topic and gap tables from them.

Functions and deliverables

• Sustainability reporting planner: Plan your ESG and sustainability reporting with material topics, framework fit, data gaps and claims that need proof. Not audit or legal advice.
  • A short list of material ESG topics with a score for each and the reason
  • A framework fit that says which disclosures your topics point to
  • A data gap list that says what proof you still need for each topic
  • A plan for your emissions count, with the categories to include and where the data comes from
  • A check of each target and public claim, with greenwashing risks marked
  • A reporting calendar and a list of rules and dates to check against the current text
  Source: Michael Sitarzewski and Agency Agents contributors.
• Sustainability reporting reviewer: Turn supplied environmental, staff and governance data into a report draft or gap list. Show sources, missing measures and review needs.
  • Draft ESG report
  • Emissions summary by scope
  • Scorecard against targets
  • Gap list versus the standard
  • Goals for next year
  Source: GAJETOso.
• HR compliance audit planner: Plan an HR compliance audit: get a checklist, a file sampling plan, a findings report ranked by risk and a fix plan. Not legal advice.
  • An audit checklist
  • A sampling method for files
  • A findings report ranked by risk
  • A corrective action plan with a timeline
  Source: Tuan Duc Tran.
• EU sustainability report checker: Check firm details and reports to find which EU reporting rules may apply and what's missing.
  • A scope verdict with your figures and the first reporting year, marked to confirm
  • The steps of a double materiality assessment
  • A gap table by topic with priorities
  • Draft disclosures only where your data supports them
  • A comparison with GRI, TCFD and SASB, if you ask
  Source: Hemant Naik.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up

Tasks you can use it for

• A customer, lender or investor sends an ESG questionnaire and you have no plan to answer it.
• You must start a first sustainability report and do not know which topics to cover.
• You want to set a carbon target and need to check it has a believable path.
• Your marketing says "carbon neutral" or "eco-friendly" and you want to know if you can back it up.

Limits to check before starting

• You have the data and want a draft report written. Use the Sustainability reporting reviewer.
• You want to know if EU sustainability reporting rules apply to you. Use the EU sustainability report checker.
• You want emissions worked out from shipping, energy and supplier data. Use the Supply chain carbon tracker.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Add the pack as a skill, or paste SKILL.md and then references/source-agent.md into a new chat.
• Describe your company and why you are asking. Attach what you have, such as emissions data, HR figures or policies.
• Say which job you want first. Pick one, such as the topic list, the emissions plan or the claims check.
• Read the gap list before the plan. A plan built on missing data is only a draft.
• Treat every rule, date and standard in the answer as a lead. Check it on the regulator's or standard setter's own site.
• Have your finance, legal or sustainability lead review the plan before you publish any claim.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/esg-sustainability-officer for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.