Purpose of this article
Scaler includes a set of AI features that help you act on your data — recommend retrofit measures, review draft reports for framework compliance, and respond to investor questionnaires with data-backed answers. This article covers each one, what it produces, and what to verify before relying on the output.
For the broader AI overview and security architecture, see AI in Scaler: overview.
Lumi AI is part of the Scale Plan. Every user receives 15 prompts/month free; more requires the Scale Plan — contact your account manager. Some organisations have AI features disabled. Access via the floating icon, the homepage, or inline throughout the platform.
What this covers
- AI CapEx measure suggestions — retrofit recommendations with cost and payback estimates
- AI report reviewer — framework completeness and consistency check before submission
- Investor DDQ answers — data-backed responses to LP and lender questionnaires
AI CapEx measure suggestions
Purpose
Recommend the most impactful retrofit measures for an asset, grounded in its actual consumption profile, building characteristics, and regional context.
Location
Data Collection Portal → Asset → Assessments & Measures → Add Measure
Click the AI Measure Suggestion button.
Inputs the model uses
- Energy, fuel, and heating consumption history
- Solar production data, where available
- Building age and property type
- Location and climate zone
- Energy rating (EPC label) and historical roadmap measures
What a suggestion includes
- An asset profile summary — EUI, construction year, EPC rating, climate zone
- A primary recommendation with rationale (e.g. "Lighting represents 20–30% of office electricity consumption")
- Energy consumption analysis with estimated savings in
kwh_per_sqm_per_year
- Cost estimate and payback period (e.g. "€18,900 total, 8-year payback")
- Alternative measures ranked by expected impact
- Data gaps that, if closed, would improve the analysis
- Regional context — applicable subsidies, regulations, or EPBD requirements
How to apply a suggestion
- Click Apply Suggestions to auto-populate the measure form with the recommended values
- Adjust costs, dates, or scope as needed before saving
- Optionally request partner advisory support for validation or deeper analysis
AI CapEx suggestions are starting points, not final engineering recommendations. Verify with a technical manager or external advisor before committing capital.
When to use it
- Planning the next year's CapEx programme for an asset
- Identifying which measures will help an asset meet its CRREM or net-zero pathway
- Building a portfolio-wide retrofit roadmap, asset by asset
Investor DDQ answers
Purpose
Draft accurate, data-backed responses to due diligence questionnaires (DDQs) by pulling directly from the portfolio data already in Scaler.
Location
Home → Investor DDQ
Paste a DDQ question into the input to get a draft answer grounded in your data.
Example questions Lumi can answer
- "What is the fund's total energy consumption and carbon footprint?"
- "Describe your approach to net zero target setting."
- "What percentage of assets have undergone energy audits in the past three years?"
- "How do you monitor and manage physical climate risks across the portfolio?"
What you get back
A draft response that includes:
- The narrative answer
- Supporting figures pulled from your portfolio data
- The metric definitions used (so you can verify they match the LP's definition)
- A note on any data gaps that affect the answer
How to use it
- Paste questions one by one, or work through a full DDQ section in sequence
- Review and edit each answer for tone and audience match before sending
- Verify supporting figures against your latest report or audit, especially for figures that drive investment decisions
Tip: DDQ answers are most useful as a first draft. They typically save 60–80% of the drafting time and let your IR or sustainability team focus on review and tone rather than data lookups.
When DDQ Answers is most valuable
LP and lender DDQs ask similar questions across funds and reporting cycles. The first time through, Lumi has to interpret each question against your data; subsequent rounds reuse much of that pattern. Teams typically see the largest time saving on the second and third DDQ of a cycle.
Best practices and verification
These features are draft-generators, not final outputs. Build verification into the workflow:
- For CapEx suggestions, validate the energy savings and cost estimate with a technical advisor before committing capital
- For AI Review, treat the issue list as a structural QA pass — fix what's flagged, then have a human reviewer read the report end-to-end
- For DDQ answers, always cross-check the supporting figures against your most recent verified report, especially for figures the LP will use to make investment decisions
Where to go next
- AI in Scaler: overview — Architecture, security, and the full feature list
- Using Lumi: writing effective prompts — Prompt techniques and example libraries
- AI for data quality and analysis — Outlier detection, meter analysis, forecasts, and bill scraping
- Setting up roadmap inputs — Configure AI-suggested and manual roadmap measures
- Roadmap Tool: Overview and methodology — How projections are calculated behind the scenes