Representative local application
Help With a Utility Bill
Energy assistance • Local agency, LIHEAP-funded
The Low Income Home Energy Assistance Program is federally funded and delivered through state, tribal and local agencies, each publishing its own application and seasonal dates. This case study shows a representative local application, not any one agency's form.
Source: U.S. Department of Health and Human Services, LIHEAP program information
AccessForce is an independent prototype. It is not affiliated with, nor endorsed by, this agency, and it never changes eligibility requirements or makes eligibility decisions.
Before
The experience people use today
- One bill.
- One season.
- One local office to find.
By the time someone finds the right office, the season may have closed.
People often look for help at the moment of a shut-off notice — the moment when reading dense instructions is hardest.
Which questions apply to you?
The same application asks for different question ranges depending on which programs someone is requesting.
- Regular seasonal assistanceHousehold + income + utility account+ recent bill
- Crisis or shut-off noticeHousehold + income + urgency questions+ shut-off notice
- Heat included in rentHousehold + income + rental questions+ lease information
- Also seeking other helpHousehold + cross-program questions+ referral to food or medical assistance
AI-identified cognitive and process complexity — not a legal accessibility violation.
Document preview
Representative excerptEnergy assistance application — local agency
Season and eligibility window
- Applications are accepted during the announced program season.
- Crisis assistance may have different timing and requirements.
Household and income
- List household members and report income for the period requested.
- Provide documentation of income for each member.
Utility account
- Provide the account number and provider exactly as shown on your bill.
- Attach a recent bill or a shut-off notice if you have one.
Short representative excerpts only — the full published document is linked above.
AXS — Accessibility Experience Score
Putting a number on the experience people face today
AXS — AccessForce Accessibility Experience Score
38 / 100
Illustrative score until audit completed
Local energy assistance application
AXS weighs technical accessibility at 40%, cognitive and content accessibility at 30%, and process accessibility at 30% — so an interface that is technically operable can still score low when the process itself is hard to get through.
How AXS worksAI accessibility audit
Ask AI to examine the experience
AccessForce reads the published application the way different people would have to, and reports what may stand in their way. These are AI-identified opportunities reviewed by a person — not legal findings.
AI redesign
Let Agentforce rebuild the interaction
The eligibility rules and the systems behind them stay exactly as they are. Only the interaction changes.
After
The same service, as a conversation
Help With a Utility Bill — assistant
Hi. I can help you look into help with your utility bill. Before we start, how can I make this easier for you?
Before vs. after
Same public service, different experience
Before
Form-driven
- 🔎 Find the local office yourself
- 📅 Seasonal window buried in instructions
- 🧾 Account numbers copied by hand
- ⚠️ Crisis path hard to spot
- 📄 Income documents for everyone
After
Utility Help for All — conversation-driven
- 💬 Say what's happening
- 🚨 Urgent path surfaced first
- 📍 Local agency found for you
- 📷 Bill read back for confirmation
- 🗒 Plain-language checklist
- ♿ Adaptive accessibility
- 🙋 Human help straight away
Same program rules. Same local decisions.
Help that can be found in time.
Measured
Before and after isn't just visible. It's measurable.
Before
38
AXS / 100
Major Barriers IdentifiedLocal energy assistance application
AccessForce redesign
After
93
AXS / 100
Highly Accessible ExperienceAdaptive Agentforce conversation over the same requirements
+0
Accessibility Experience Points
38 → 93. Illustrative score until audit completed.
Dimension by dimension
Select “Why?” on any dimension to see the finding, the recommendation and the redesign decisions the improvement is credited to.
| Dimension | Before | After | Change | Evidence |
|---|---|---|---|---|
| Visual & Perceivable | 64 out of 100 before | 94 out of 100 after | +30 | |
Severity: MediumImpact area: Visual & Perceivable FindingDense pages ask people to scan long blocks of small print to find what applies to them. AccessForce recommendationPresent one question at a time, at a size and contrast the person can adjust.
Why did the score change?
| ||||
| Screen Reader & Semantic | 56 out of 100 before | 95 out of 100 after | +39 | |
Severity: MediumImpact area: Screen Reader & Semantic FindingDocument structure and field relationships are hard to follow when the experience is read aloud. AccessForce recommendationRebuild the interaction with real headings, labelled controls and a predictable reading order.
Why did the score change?
| ||||
| Motor & Keyboard | 54 out of 100 before | 95 out of 100 after | +41 | |
Severity: MediumImpact area: Motor & Keyboard FindingCompleting the experience assumes precise input and, on paper, handwriting and signatures. AccessForce recommendationMake every step keyboard-operable with large targets, and accept spoken answers.
Why did the score change?
| ||||
| Cognitive Accessibility | 26 out of 100 before | 91 out of 100 after | +65 | |
Severity: HighImpact area: Cognitive Accessibility FindingCrisis instructions sit inside the same dense material as routine instructions. AccessForce recommendationAsk about urgency first and surface the crisis path immediately.
Why did the score change?
| ||||
| Plain Language | 32 out of 100 before | 93 out of 100 after | +61 | |
Severity: HighImpact area: Plain Language FindingGovernment and legal terminology assumes familiarity most applicants don't have. AccessForce recommendationAsk in plain language and explain terms in place, while preserving the original meaning.
Why did the score change?
| ||||
| Process Accessibility | 18 out of 100 before | 88 out of 100 after | +70 | |
Severity: HighImpact area: Process Accessibility FindingThe program is federally funded but locally administered, with different applications and seasonal windows. AccessForce recommendationRoute by area and urgency, then explain the season and the crisis path in plain language.
Why did the score change?
| ||||
| Adaptive & Personalized | 22 out of 100 before | 94 out of 100 after | +72 | |
Severity: HighImpact area: Adaptive & Personalized FindingThe experience is the same for everyone, and assistance has to be discovered before it can be used. AccessForce recommendationAsk about accessibility needs and language first, then adapt the experience to the answers.
Why did the score change?
| ||||
Illustrative score until audit completed. Each change is credited to a specific redesign decision — a score never moves simply because a conversation exists.
Why did the score change?
Process Accessibility
18 → 88+70
Why?
- Irrelevant questions removed from view
- Branching handled dynamically
- Save and resume added
- Help available throughout
- One task presented at a time
- Human escalation available
Cognitive Accessibility
26 → 91+65
Why?
- Reduced information density
- One question at a time
- Plain-language explanations
- “I don't know” supported
- Approximate answers supported where appropriate
- Follow-up items saved rather than blocking progress
Scale
One accessibility engine. Thousands of experiences.
The same audit-and-redesign engine can point at any required experience. The systems of record behind them are never replaced.
- Government
- Healthcare
- Education
- Employment
- Sports
- Travel
- Emergency Response
- Financial Services
Don't make people adapt to forms.
Make forms adapt to people.
AccessForce: Forms for All
Built for Agentforce for Good • AI Fluency Track • Type C