AI You Can Prove — the vocabotics capability brochure

Most AI companies ask you to believe them. This brochure is built so you don't have to: every capability carries the actual measured number behind it, the date it was measured, and an honesty tier — 🟢 shipped, 🔬 research, 🔭 vision — that says plainly how finished it is. Selling claims here are 🟢 only.

The four capabilities

① It can't bluff. Ask our knowledge system something it can source and it answers with the citation; ask it something it can't and it refuses rather than improvising. Confabulation was driven from 87% to 0.0% on our test corpus, and the no-bluff floor held under a 16-turn adversarial interrogation. The demo: watch it refuse, then cite Canberra — with provenance — from a knowledge store compressed to 0.70 GB. (🟢 2026-07-02)

② It stays fast when the context is huge. Our wave-based model architecture decodes at 2× llama.cpp's speed at 128,000 tokens of context — flat where a transformer climbs. Long-context regime specifically; not a claim of being fastest everywhere. (🟢 2026-07-02)

③ Proven-correct code, any chip, AI-written. Everything is written in a small language built for machines to write and machines to check. Every compile runs the program twice — native machine code and an independent typed interpreter — and the results must agree, value for value. The gate has never been disabled. The corpus holds 1,026 certified-equivalent functions and not one more: on wild, unfiltered C the converter honestly certifies about 1 in 20 and refuses the rest. (🟢 captured 2026-07-10)

④ A capable model on hardware you already own. The cognitive stack runs at a 21 ms step in 377 MiB on one consumer RTX 3090; a real open-weights model runs full interactive generation on our own stack at 151.7 tok/s, token-for-token identical to the reference. Caveat, printed at the same size: that model is 0.5B — 7B runs at parity, and prefill still trails. (🟢 2026-07-02, caveat 🔬)

Trust, certified at three layers

Not "fastest" — a rival can copy a kernel. The claim is narrower and harder:

1. The gate — code proven correct: every compile self-verified, native ≡ interpreter, never disabled. Mechanical trust.
2. The calculated mind — cognition that reasons or refuses: honesty by architecture, not a bolt-on filter. Architectural trust.
3. The cull — the founder deleted 57 projects in one day, and the archive keeps the failures visible. You cannot fake having subtracted. Cultural trust.

The honesty ledger

Every published claim is tiered: 🟢 shipped (measured, gate-clean, dated), 🔬 research (measured, partial, gaps named), 🔭 vision (designed, unbuilt). One law governs movement: the bigger claim goes UP a tier — never down.

The receipts: disproven projects stay published in full (including a retracted ternary-7B result — the retraction is part of the record); the chapter census is published as an audit, not a boast — 570 chapters audited, ~59% confirmed genuinely real, 60 stubs quarantined; and the corpus figure above is one function lower than the previous public number, because a false equivalence was found and quarantined. We printed the smaller number.

Safety by construction — and where we learned it

Run our compiler with a safety profile and it statically rejects code that allocates after initialisation, loops without a provable bound, recurses, exceeds length limits, skimps on assertions, or ignores a checked return — six checkers modelled on NASA's Power-of-Ten rules — and issues a certificate on code that passes. A memory leak is a compile error, not a review finding. (🟢 2026-07-02; WCET certificates are the designed next step, 🔭.)

The discipline comes from fifteen years delivering safety-critical systems for global rail and metro — including a $4m+ metro public-address and passenger- information programme — the world where a wrong announcement in an emergency is a safety incident, not a bad user experience.

What we sell today

• AI Readiness Scorecard — free, five minutes, three concrete next steps. 🟢
• Strategy Audit — from £2,500: where AI genuinely helps your business, and where it doesn't yet. A plain-English plan, not a sales pitch. 🟢
• Compliance-grade AI Audit — for regulated firms: an audit trail an assessor will accept. 🟢
• Training & Workshops — calm, practical sessions for teams and communities. 🟢
• No-Bluff Build — from £25k: cite-or-refuse knowledge tools, agentic workflows with a STOP button. Labelled honestly: the underlying systems are prototypes. 🔬

How to verify us

The close of this brochure is a checklist, not a slogan — about fifteen minutes:

1. /proof — recorded gate transcripts from the live repo, including the one where a real 32-bit wraparound made the gate say DIFFER instead of papering over it.
2. /proof/ledger — the census: 570 chapters audited, repaired, genuine and quarantined, counted in public.
3. /dashboard — the flagship figures with tier and caveat attached, recomputed from the archive on every build.
4. /lab — the dated R&D notebook. Read a disproven report in full, then decide what a 🟢 from us is worth.

If any of them disappoints you, you'll have learned something true about us — which is the point.