⚡ Promptolis Original · Wellness & Health
🛌 CBT-I Sleep Restriction Protocol
Counterintuitive but research-proven: restrict time in bed to match actual sleep, build sleep pressure, gradually expand.
CBT-I Sleep Restriction Protocol — Counterintuitive but research-proven: restrict time in bed to match actual sleep, build sleep pressure, gradually expand. Setup: 2 min to try · Best AI: Opus 4 for protocol calibration. · Cost: Free, MIT-licensed.
Why this is epic
CBT-I (Cognitive Behavioral Therapy for Insomnia) is AASM first-line treatment — not medication. Sleep restriction is the core intervention. Counterintuitive: spending LESS time in bed fixes insomnia.
Mechanism: time in bed awake destroys sleep-efficiency and builds anxiety. Restricting builds sleep pressure (homeostatic drive) + breaks bed-as-awake association. Within 2-4 weeks, sleep consolidates.
Perlis + Morin's research shows 70-80% improvement for chronic insomnia — better than long-term medication.
📑 Page navigation + Key Takeaways Click to expand
📌 Key Takeaways
- What it is: Counterintuitive but research-proven: restrict time in bed to match actual sleep, build sleep pressure, gradually expand.
- Best for: Chronic insomnia (3+ nights/week for months)
- Time investment: 2 min to try setup, 4-8 week protocol output
- Recommended AI model: Opus 4 for protocol calibration.
- Cost: Free forever — MIT-licensed, no signup, no paywall
📑 On this page
- The prompt (copy-ready)
- How to use it (4 steps)
- Example input + output
- Common use cases
- Pro tips + variants
- FAQ
⚙️ At a glance
- Category:
- Wellness & Health
- Setup time:
- 2 min to try
- Output time:
- 4-8 week protocol
- Best AI model:
- Opus 4 for protocol calibration.
- License:
- MIT (free commercial use)
- Last reviewed:
📊 Promptolis Original vs generic AI prompts Click to expand
| Feature | Promptolis | Generic prompts |
|---|---|---|
| Structure: | XML + chain-of-thought | Role-play one-liner |
| Example output: | Real full example | Rare |
| Variants: | 3-7 per prompt | Single |
| Output quality: | +30-50% accurate [Anthropic] | Baseline |
On the other hand, generic prompts work fine for simple lookups. Promptolis Originals shine for nuanced reasoning where precision matters.
The prompt
Example: input → output
Here's how this prompt actually performs. Real input below, real output from Claude Opus 4.
<current-total-sleep>4.5 hours</current-total-sleep> <current-time-in-bed>7 hours (11:30pm-6:30am)</current-time-in-bed> <wake-target>6:30am</wake-target> <type>middle insomnia — wake at 3am</type>
Your Sleep Restriction Window
Bedtime: 1:30am. Wake: 6:30am. Time in bed: 5 hours.
Counterintuitive — later bedtime than current. That's the feature.
Why: current 4.5h sleep + 7h in bed = 64% efficiency (poor). Restricting to 5h in bed forces sleep pressure to concentrate. Target efficiency >85%.
Week 1-4 Protocol
Week 1:
- Bed 1:30am, wake 6:30am, no exceptions (weekend too)
- No napping, no exceptions
- Note: may feel worse before better. Grogginess expected.
- Track actual sleep nightly (rough estimate — don't watch clock)
Week 2:
- Same schedule. Sleep efficiency should start improving.
- Likely consolidating sleep (waking less in middle)
- Still no napping
Week 3:
- If sleep efficiency >85% for week 2 (sleeping ~4.25h of 5h = 85%), extend by 15 min. Bedtime 1:15am.
- If <85%, maintain 1:30am another week.
Week 4:
- If efficiency still >85%, extend another 15 min. Bedtime 1:00am.
- Continue 15-min expansions weekly until target total sleep reached (usually 7 hours = 5.5h bed initially).
Target full protocol: 6-10 weeks to reach 7-hour sleep window with high efficiency.
Expansion Criteria
Expand bedtime by 15 min when:
- Sleep efficiency >85% for 7+ consecutive nights
- Feel significantly less fatigued than week 1
- Not waking during night
DO NOT expand if efficiency below 85%. Patience.
Troubleshooting Common Issues
Week 1 severe grogginess: expected. Buy coffee, power through. Don't nap.
Urge to nap: hardest part. Distract with walk, cold water, light task. Let sleep pressure build for night.
Anxiety at new bedtime: 'I won't sleep enough' thought amplifies insomnia. Cognitive restructuring: 'I'm doing the protocol. Sleep will build.'
Partner disrupts protocol: discuss before starting. Partner support critical. If they're unwilling to respect strict wake time, protocol compromised.
Sleep worsens, not improves: 1% of cases. After week 3 with no improvement, consult sleep physician. Possible underlying sleep apnea or other condition masquerading as insomnia.
If No Improvement at 4 Weeks
CBT-I self-guided has 40-60% success rate; therapist-guided 70-80%. If self-guided at 4 weeks no improvement:
- Find CBT-I-trained therapist (psychology-today-filter or SBSM Society of Behavioral Sleep Medicine directory)
- Sleep physician for polysomnography (rule out apnea, restless legs, other)
- Don't default to medication as primary — CBT-I still preferred long-term
- Address potential contributors: untreated depression / anxiety, chronic pain, hormonal changes (perimenopause especially)
📋 How to use this prompt (4 steps · under 60 seconds) Click to expand
- 1 Copy the prompt above. Click "Copy prompt". XML-structured prompt now on clipboard.
- 2 Open ChatGPT, Claude, or Gemini. One-click launch above. Recommended: Opus 4 for protocol calibration..
-
3
Paste + fill placeholders. Replace
{curly braces}with your context. Specificity = quality. - 4 Run + iterate. Setup: 2 min to try. Output: 4-8 week protocol.
Common use cases
- Chronic insomnia (3+ nights/week for months)
- Middle-insomnia (wake at 3am can't return)
- Sleep-onset insomnia (can't fall asleep)
- Insomnia resistant to sleep-hygiene changes
Best AI model for this
Opus 4 for protocol calibration.
Pro tips
- Week 1 is rough. Sleep deprivation worsens before improving. Commit to 4-week minimum.
- NO napping during protocol. Nap = releases sleep pressure = defeats mechanism.
- Strict wake time. Consistent even weekends.
- CBT-I works best with therapist. Self-guided possible for motivated; professional improves outcomes.
- Insomnia + depression / anxiety: treat both. CBT-I alongside other treatment.
Customization tips
- For very severe insomnia (<4 hours/night): start restriction at 4.5h floor, not less. Complete deprivation is dangerous.
- For shift workers: apply principles adjusted to your schedule. Consistent wake (relative to shift) matters.
- For insomnia + benzodiazepine use: do not stop medication abruptly while starting CBT-I. Work with prescriber on parallel taper.
- For older adults: slightly less restriction (more buffer above actual sleep). Body more sensitive to deprivation.
Variants
Default Protocol
Standard CBT-I sleep restriction
Middle-Insomnia Specific
Wake-in-middle pattern
Sleep-Onset Specific
Can't fall asleep
With Therapist (Adherence Support)
Structured for therapist-guided protocol
Frequently asked questions
Common questions about this prompt and how to get the best results from it.
How do I use the CBT-I Sleep Restriction Protocol prompt?
Open the prompt page, click 'Copy prompt', paste it into ChatGPT, Claude, or Gemini, and replace the placeholders in curly braces with your real input. The prompt is also launchable directly in each model with one click.
Which AI model works best with CBT-I Sleep Restriction Protocol?
Opus 4 for protocol calibration.
Can I customize the CBT-I Sleep Restriction Protocol prompt for my use case?
Yes — every Promptolis Original is designed to be customized. Key levers: Week 1 is rough. Sleep deprivation worsens before improving. Commit to 4-week minimum.; NO napping during protocol. Nap = releases sleep pressure = defeats mechanism.
What does it cost to use this prompt?
The prompt itself is free, MIT-licensed, with no email signup required. You only pay for your AI model subscription (ChatGPT Plus $20/mo, Claude Pro $20/mo, Gemini Advanced $20/mo) — and even those have free tiers that work with most Promptolis Originals.
How is this different from PromptBase or PromptHero?
PromptBase sells prompts in a marketplace ($2-15 each). PromptHero focuses on image-generation prompts. Promptolis Originals are free, MIT-licensed text/reasoning prompts hand-crafted with full example outputs, multiple variants, and a recommended best AI model per prompt. We don't sell anything.
Explore more Originals
Hand-crafted 2026-grade prompts that actually change how you work.
← All Promptolis Originals