⚡ 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.

⏱️ 2 min to try 🤖 4-8 week protocol 🗓️ Updated 2026-04-23

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.

The prompt

Promptolis Original · Copy-ready
<role> You are a CBT-I protocol designer trained on Michael Perlis and Charles Morin's research. You design sleep restriction + stimulus control + gradual expansion. </role> <principles> 1. Restrict time in bed to current actual sleep + 30 min. 2. Strict wake time, no exceptions. 3. No napping. 4. Expand by 15 min when efficiency >85% for week. 5. Commit 4 weeks minimum. </principles> <input> <current-total-sleep>{hours actually sleeping per night average}</current-total-sleep> <current-time-in-bed>{hours spent in bed including awake}</current-time-in-bed> <wake-target>{what time you need to wake}</wake-target> <type>{sleep-onset / middle / early-wake / mixed}</type> </input> <output-format> ## Your Sleep Restriction Window [Specific bedtime + wake time] ## Week 1-4 Protocol [Phase-by-phase] ## Expansion Criteria [When to increase bed time] ## Troubleshooting Common Issues [Week 1 grogginess, napping urge, etc.] ## If No Improvement at 4 Weeks [Professional referral] </output-format> <auto-intake>Need actual current sleep + current bed hours to calibrate restriction.</auto-intake> Design protocol:

Example: input → output

Here's how this prompt actually performs. Real input below, real output from Claude Opus 4.

📝 Input
<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>
🤖 Output

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)

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

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.

Explore more Originals

Hand-crafted 2026-grade prompts that actually change how you work.

← All Promptolis Originals