AI consulting · agentic deployment · SLM tuning · AI memory
Train big once.
Deploy small forever.
AI that learns your business: small models tuned to your work, with memory that compounds. Move off pay-per-token frontier APIs onto software you own — same-or-better results at a fraction of the cost, every claim backed by published benchmarks.
What we work on daily
High-volume, per-item work — where a tuned small model pays for itself.
Document & record extraction
Legal · medical · financial
Customer support automation
Contact-center, tier-1 deflection
Transcription → summarization
Scribe · meetings · calls
Batch classification
Moderation & routing
Content generation at scale
SEO · product · e-comm
Compliance & security scanning
Per-line review
Outreach personalization
SDR / leads
Translation & localization
Any language pair
The research lane
We're training AI
to manage its own memory.
Most agents forget. Ours don't. We publish what we learn building persistent intelligence — the methodology, the datasets, the benchmarks against frontier models. The same architecture goes into every system we ship.
Training a small Linux-native model to classify, compress, and store conversational memory in real time — replacing frontier API calls in the persistence layer of every agent we build.
An agent that uses its own accumulated decisions as training data, scaffolds eval pairs from its own corrections, and trains its next body without a human in the labeling loop.
Case study — measured, not quoted
Measure your model.
Don't trust the leaderboard.
We ran two leading ≤4B open models — Qwen3-4B and Gemma-4 E4B — head-to-head as a local agent brain on an Apple M4 Mac mini (16 GB), Q4 via ollama. Not leaderboard trivia: an objective, machine-scored harness (grep / parse, 3 trials each) measuring what actually breaks agents in production — routing, clean tool-call JSON, and complete hand-offs.
The three JSON / tool-call tasks are the cliff: Qwen 0/3 on every one, Gemma 3/3 on all fifteen.
Speed didn't decide it — both cleared 24 tok/s, and Qwen was actually faster. Reliability decided it.
Qwen3-4B — even with thinking mode off — refused to emit a clean tool call. It monologues its reasoning in the response body (“We are given a query… Step 1…”) and never produces parseable JSON. Gemma-4 E4B followed the tool-call contract every time (15/15), at comparable speed.
A “smarter” model that won't emit a parseable tool call is useless for an agent. Model selection must be measured on your production criteria — objective, reproducible, machine-checked — not brand or leaderboard. We even caught our own bias: we leaned Qwen; the measurement flipped the decision. Proof over preference is what we sell.
Measured 2026-07-06 on an Apple M4 Mac mini· every number is re-runnable · benchmark reproducible on request.
Fine-tuning capability
The multiplier,
and the minefield.
A properly fine-tuned small model is a force multiplier. Done wrong, it looks like it worked and doesn't. We treat “it works” as a machine-proven claim — never a vibe.
A Qwen3-4B classifier we fine-tuned in-house — 75% → 95% on its task, in a single short run. A 4B model can match or beat a model 30× its size on your narrow domain, running local, offline, and cheap — on hardware as modest as a 6 GB-VRAM laptop. You own the weights and the data.
- Beats models 30× larger — on a narrow, well-scoped domain.
- Local, offline, low-latency — runs on a 6 GB-VRAM laptop — no API bill.
- You own it — the weights and the training data are yours.
- Catastrophic forgetting — It gains your task and loses general ability.
- Overfitting — Memorizes a tiny dataset, fails on anything new.
- Tool-call / format regression — The exact failure above — induced by bad tuning.
- Evaluation on training data — The classic false-green: “97%” on data it already saw.
- Data leakage — Secrets or PII baked into weights you can’t un-bake.
We pick the base model the way we ran the study above — not by brand.
The tuned model must pass objective checks it never trained on before we ship it.
Every claim maps to a re-runnable test — coverage and verification are proven.
Your proprietary data never leaves your hardware.
The one honest trade: fine-tuning is powerful because it's narrow. We scope it, prove it on held-out data, and tell you plainly where the model's competence ends. That honesty is the product.
The deployment model · real-world SLM economics
Train big once.
Deploy small forever.
Renting intelligence by the token is a bill that grows with every customer you serve. Our model flips it: use a big model once — to set the bar and generate the training data — then run a small model you own, local and offline, at near-zero cost per call. Lower operating cost, higher close rate.
A frontier model earns its keep one time: it defines the task, generates and curates the training data, and sets the quality bar. You pay the big model to teach — not to run in production.
A fine-tuned small model hits that bar on your narrow job, then runs local, offline, and fast — at near-zero cost per call. You own the weights. The recurring bill stops, and it keeps working when the internet does not.
accuracy — a 4B we fine-tuned, in one short run
a tuned 4B matching models 30× its size
tool-call reliability that actually completes the action
no API bill once it runs on hardware you own
The per-token invoice that grows with your traffic becomes a one-time training cost plus cheap, owned inference. No frontier bill scaling with every conversation. Runs on hardware as modest as a 6 GB laptop — even offline.
A fast, reliable, always-on model completes the actions that make money — answers the call, books the appointment, captures the lead — instead of stalling on a broken tool call at 3 a.m. Reliability is revenue.
Own your model. Lower the bill. Close more.
Two ways to move: have us build and ship it, or bring us in to advise. Either way, it's measured — we show you the numbers before you commit.
See the full case for SLM →The build lane
Want this engine
working on your problem?
We take on a small number of build engagements every quarter. Same team that's publishing the research. Same architecture, applied to whatever you're shipping.
Agentic backends, structured-data flows, internal tools, vertical SaaS. We architect, we ship, we hand over what works.
Next.js, Postgres, auth, payments, dashboards. Production-grade from day one — the stack we use for our own products.
Progressive Web Apps that ship to iOS, Android, and desktop from one codebase. Offline-first when it matters.
The problem
Sound familiar?
Your AI feature is a wrapper around someone else's API. So is your competitor's.
→ We architect the persistence layer underneath the wrapper. Memory is the moat — and it compounds.
Every session your agent forgets the user. Every conversation starts cold.
→ We build the memory pipeline: extraction, embedding, recall, decay. Your agent gets better every week.
You're burning frontier-model tokens on tasks a small model could do.
→ We fine-tune Linux-native models on your data, swap them in behind the same interface. Same quality, 1/200th the cost.
Your team can ship a feature. You need someone who can ship an agentic system.
→ Architecture, training, infra, evals, production. One team. We publish the methodology so you can audit the work.
Results over idealism
Most AI dies in the pilot.
We build what ships.
The national numbers are sobering — and public. Most AI spend never reaches the P&L. That's the idealism gap: pilots, demos, and AI theater that never touch the bottom line.
of enterprise generative-AI pilots deliver no measurable P&L impact — only ~5% break through.
MIT NANDA · “The GenAI Divide,” 2025 ↗of organizations see any enterprise-level earnings impact from AI — and typically under 5%.
McKinsey · “The State of AI,” 2025 (≈2,000 firms, 105 nations) ↗is where the real ROI sits — automation and engineering, not the demo the budget chased.
MIT NANDA, 2025 ↗We build for the 5%. Our judgment is done by experience, not fresh-graduate idealism — wisdom that has grown past “AI will fix it” and is built on the foundation of shipped results. Here's the proof, not the pitch.
An open-source secret vault for the age of AI agents: the model uses your API keys by name and never sees the value — encrypted at rest, jailed at runtime, sanitized on the way out. Free, Apache 2.0.
phantomvault.riscent.com →The persistence layer that makes an agent remember: extraction, embedding, recall, decay. Agents stop starting cold and get better every week. Memory is the moat — and it compounds.
See the research →Gemma-4 E4B on our tool-call harness — Qwen3-4B managed 6/15
a 4B classifier we fine-tuned, in a single short run
a tuned 4B matching models 30× its size — local and offline
Healthcare · Home Services · Legal · Real Estate · Restaurants · Auto · Fitness · E-commerce
AI visibility — our specialty
Your buyers stopped Googling.
They're asking the models.
People don't scroll ten blue links anymore — they ask Gemini, Claude, or ChatGPT and act on the answer. Here's the catch: an AI can only recommend what it was trained on. If the big three models don't know your business, you're not in the running — you're invisible. And that gap is closing fast.
Gen Z (and 1 in 4 millennials) go to AI over other channels for shopping advice
Commerce / Future Commerce, 2025 ↗Ask an AI “who's the best [your category] near me?” and it names a handful of businesses — chosen from what it was trained on. There is no page two. Being absent isn't neutral; it's being left out of the only answer the buyer sees.
Soon that window narrows further as the models consolidate their sources. Getting into that training data — before your competitors do — is the specialty. It's the front and forefront of where discovery is going.
Nearly even — and AI-driven shopping searches grew +4,700% in a year. The crossover isn't a forecast; it's arriving. Source ↗
Find out what Gemini, Claude, and ChatGPT say about you.
We test what each of the big three models actually says about your business and your category, show you exactly where the gaps are — and then get you into the answers. This is what we do: the same team that measures models and ships fine-tuned ones, pointed at your visibility.
Scan my business →Test it yourself. Ask ChatGPT or Gemini “Tell me about Ryan Bolden and InboundAI365.” The models answer — because we engineered that knowledge into the places they train on. We do exactly the same for your business.
Why us
We build the kind of AI
most teams don't know how to build.
Most AI work today is wrapper code around someone else's API. Ours isn't. We architect persistence, train our own models, publish the methodology, and run it in production. Healthcare was our first vertical — HIPAA-grade voice agents, midnight calls, two languages — and the same architecture now ships across eight industries.
Healthcare · Home Services · Legal · Real Estate · Restaurants · Auto · Fitness · E-commerce
Two ways
to build with us.
We're a consulting agency — no products to buy. Custom builds: we architect and ship your agentic systems, fine-tuned models, and AI software. Consultations: we advise on model selection, memory, and getting your business visible inside the models buyers now ask. Either way, you work with the team publishing the research.
Limited engagements each quarter · Response in 24 hours