1. Claim: “Reads your brainwaves to predict what you want to type before you think it.”

Why it’s weak:

• Logically inconsistent: predicting text “before you think it” is not how neural signals work. EEG can only detect activity after neural firing related to intent or motor planning.
• Non‑invasive EEG has very low spatial resolution and signal‑to‑noise ratio. Current research generally struggles to decode even small vocabularies reliably without heavy training.
• Investors familiar with BCI will recognize this as hype and question credibility.

How to strengthen it:

• Replace with a realistic capability description.
• Example improvement: “Our EEG headband detects neural patterns associated with intended characters and words, enabling hands‑free text input.”
• Add concrete metrics and context: vocabulary size, training time, latency, and test conditions (e.g., “~25 wpm after 2 hours of calibration in controlled trials”).

---

2. Claim: “94% accuracy. Works with any language, any device.”

Why it’s weak:

• Missing critical context: accuracy of what? Character prediction, word prediction, intent classification?
• Accuracy without baseline or task definition is meaningless.
• “Any language” is unlikely because neural decoding systems usually require language models trained per language.
• “Any device” suggests universal compatibility but ignores integration constraints (SDKs, OS limitations).

How to strengthen it:

• Specify the task and evaluation conditions.
• Example improvement:
  “In a closed‑vocabulary test (1,000 words), our system achieves 94% top‑3 prediction accuracy after a 30‑minute calibration session.”
• Clarify scope:
  • “Currently supports English and Spanish; additional languages via language‑model adaptation.”
  • “SDK available for iOS, Android, Windows, and macOS.”

---

3. Claim: “TAM: $180B based on 3.5 billion smartphone users.”

Why it’s weak:

• The math isn’t shown. TAM appears inflated by assuming every smartphone user is a potential BCI buyer.
• Consumer willingness to wear an EEG headband is uncertain and likely far smaller than total smartphone users.
• It conflicts with the cited BCI market estimate ($5.3B), making the TAM look inconsistent.

How to strengthen it:

• Use a realistic bottom‑up market model.
• Segment the market into beachheads:
  • Accessibility (ALS, paralysis communication tools)
  • AR/VR input
  • High‑productivity users
• Example structure:
  • SAM example: “~12M users with severe motor impairments globally”
  • Beachhead: “Assistive communication devices (~$2–3B market)”
  • Expansion: AR/VR input devices and productivity tools.
• Show pricing assumptions (e.g., $300 hardware + subscription).

---

In short, the weakest parts are the overstated technical capability, vague performance metric, and inflated TAM. Tightening claims with realistic neuroscience limits, clear benchmarks, and defensible market sizing would make the pitch far more credible to investors.