Public consultation analyzer
Auditable synthesis that retains disagreement and source traceability.
- For
- Policy teams handling public consultations
- Solves
- Large submission volumes hide distinct minority perspectives.
- Delivers
- Consultation evidence report
- Built in
- about 5 weeks of creation time, MVP in 6 days
- Investment
- $11,000 for the MVP, $44,000 for the full product
- Run it
- Inside your business, or as part of your offer to clients
What it does
For policy teams handling public consultations, turn authorized submissions and consultation questions into consultation evidence report.
- Classify responses.
- Preserve minority views.
- Detect duplicates.
- Link quoted evidence.
- Distinguish frequency from importance.
- Export transparent summaries.
What goes in, what comes out
- Authorized submissions
- Consultation questions
AI drafts, people review. Evidence-backed analysis and reporting workspace.
- Consultation evidence report
How it works
The workflow
- InStart with
Authorized submissions and consultation questions
- 1
Agree definitions
- 2
Import authorized data
- 3
Validate coverage and identifiers
- 4
Compute transparent measures
- 5
Group relevant evidence
- 6
Review findings
- 7
Assign investigations or improvements
- 8
Repeat on a comparable period
- OutFinish with
Consultation evidence report
AI does the heavy lifting, people stay in charge
Classify text, summarize evidence and propose explanations to investigate. Compute financial or operational measures with deterministic code. Separate observed patterns from causal claims and preserve examples that contradict the summary.
What your team sees
Key screens: Submission themes, evidence explorer, review log. Open with a compact overview and filters for the relevant period or segment. Let users drill from each theme or metric into underlying records. Keep source definitions and missing-data notes near the result. Use an action panel to assign investigations and record what was learned. In this product, the first view is submission themes, followed by evidence explorer and review log.
Accounts and administration
Dataset permissions, field mappings, metric definitions, source drill-down, saved filters, reviewer annotations, recurring reports and action ownership.
Integrations and data access
Official publications, agency document stores and approved service workflows. Read-only business data exports, reporting databases and task trackers. Reconcile source totals before scheduling recurring data refreshes. These are candidate integration categories, not verified supported connectors.
How we build it
We build with our own AI software development factory, so most implementations take days to a few weeks of creation time, not months. You see working software at every step, and exact timing depends on availability.
- 1
Scoping call
Day 1Thirty minutes on your process, your data and how you want to run it: for your own team, or for your clients. You get a fixed scope and price for the MVP.
- 2
MVP
6 daysOne buyer segment, one recurring use case; first modules: classify responses; preserve minority views. Manual review in the loop. Built by our AI software factory.
- 3
Paid pilot
7 daysAccounts, roles, review states, audit trail and the first integration, hardened for two to three paying pilot customers.
- 4
Full product
3 weeksRemaining modules: link quoted evidence; distinguish frequency from importance; export transparent summaries. Self-serve onboarding, billing, monitoring and the wider integration set.
- 5
Run and improve
MonthlyWe host, monitor and improve it for a fixed monthly fee, or hand it over to your team. How the retainer works.
Why we start with an MVP
An MVP, or minimum viable product, is the smallest version that your users can actually work with. It is not a cheap version of the full solution. It is a test, built to answer the questions that decide whether the rest is worth building.
- Pick the riskiest assumption. Here: will policy teams handling public consultations use it to solve "large submission volumes hide distinct minority perspectives"?
- Build only what tests it. One team, one use case, a few core modules. People do the rest by hand for now.
- Run a paid pilot. Analyze one historical period and review findings with the responsible domain owner.
- Measure, then decide. Track reviewer agreement and evidence coverage. Then expand, change course or stop, with evidence instead of opinions.
MVP scope for this solution. Begin with policy teams handling public consultations and one recurring use case. Build the first two modules: classify responses; preserve minority views. Provide operator assistance for the third module: detect duplicates. Deliver consultation evidence report through a manual review queue. Perform other necessary full-scope functions manually during the pilot. Include all applicable access, accuracy and professional-review controls from the start.
After the MVP. After paid pilots establish value, automate the remaining modules: link quoted evidence; distinguish frequency from importance; export transparent summaries. Add one validated source integration, reusable customer configuration and recurring delivery. Expand to additional teams, document formats or languages only after testing the new scope.
What the build depends on. Stable identifiers, consistent metric definitions, deterministic calculations, source lineage and representative review samples. Poor coverage must remain visible.
Investment
A planning range to start the conversation, not a quote. You pay per phase, so you can stop after the MVP.
- Phase 1
MVP
One buyer segment, one recurring use case; first modules: classify responses; preserve minority views. Manual review in the loop.
- Phase 2
Paid pilot
Accounts, roles, review states, audit trail and the first integration, hardened for two to three paying pilot customers.
- Phase 3
Full product
Remaining modules: link quoted evidence; distinguish frequency from importance; export transparent summaries. Self-serve onboarding, billing, monitoring and the wider integration set.
Indicative total, MVP to full product$44,000about 5 weeks of creation time · start with the MVP from $11,000
Running costs per month
A rough indication of monthly hosting and AI model costs once it is live, not tested. Real costs depend on usage, file sizes and the models chosen.
| Stage | Hosting and infrastructure | AI usage | Total per month |
|---|---|---|---|
| MVP and paid pilotabout 3 customers | $50–$100 | $80–$160 | $130–$260 |
| Full productabout 50 customers | $190–$380 | $880–$1,750 | $1,070–$2,130 |
Run it or resell it
For your own team
Policy teams handling public consultations run it inside the business: authorized submissions and consultation questions in, consultation evidence report out, reviewed by your people.
As part of your offer
Agencies, consultancies and software companies can offer it to their own clients under their brand. We build and maintain it; you sell and deliver it.
Your brand, or this one
Run it under your own brand, or start from this concept style.
- primary
#479127 - accent
#a454c9 - surface
#e8f1e4 - ink
#22201e
- Headings
- Space Grotesk
- Text
- Inter
- Voice
- Plain-spoken, neutral, accountable
Selling it to your own clients: the go-to-market playbook
Pricing to test
Test USD 500-2,000 for an initial analysis of one bounded dataset. Offer USD 250-1,000 monthly for repeat reporting at agreed volume. Data cleanup and specialist analysis are separately priced. These are test ranges.
Message to test
Public consultation analyzer for policy teams handling public consultations. Auditable synthesis that retains disagreement and source traceability. Demonstrate the claim through an analysis of a published historical consultation.
Where to find buyers
Public-sector research consultancies
Lead magnet
An analysis of a published historical consultation
The first 30 days
- Week 1: interview five prospective buyers in this segment: policy teams handling public consultations. Ask to see a recent example of the problem and their current process.
- Week 2: prepare this demonstration using authorized or synthetic material: an analysis of a published historical consultation.
- Week 3: present it through public-sector research consultancies and seek one narrowly scoped paid pilot.
- Week 4: review reviewer agreement, evidence coverage, total delivery effort and a concrete renewal decision before increasing scope.
Paid pilot
Analyze one historical period and review findings with the responsible domain owner. Reconcile headline measures, inspect counterexamples and ask the buyer to choose a concrete follow-up action. For this solution, use authorized submissions and consultation questions and evaluate consultation evidence report. Agree success thresholds with the buyer before starting; collect a baseline for reviewer agreement, evidence coverage. A positive signal is payment and repeat use with acceptable quality and delivery cost, not a favorable demo reaction alone.
Success metrics
Reviewer agreement, evidence coverage
Retention and expansion
Repeat the same definitions each reporting period and track whether findings lead to useful action. Expand data sources without breaking historical comparability.
Why clients would pick it
Domain-specific definitions, trusted source mappings and a history connecting findings to actions and observed results. For this solution, build around auditable synthesis that retains disagreement and source traceability. This advantage requires execution and accumulated customer trust; the base model alone is not a defensible asset.
Alternatives and positioning
Analysts, business intelligence dashboards, spreadsheets and general text summarization tools. Differentiate on this specific proposed advantage: auditable synthesis that retains disagreement and source traceability. Test it against the buyer's current method on the same task. Competitor coverage and uniqueness have not been established.
Main delivery costs
Data preparation, reconciliation, classification, expert interpretation, customer-specific definitions and recurring reporting support.
Safeguards
Preserve official source versions, accessibility and audit records. Confirm agency-specific procurement, records and data handling requirements during discovery. Validate source access and reviewer availability during the pilot. Maintain customer-level access, data deletion controls and a record of final approvals.