Who this is for
AI Automation is built for any team spending real human hours on work the team already considers "mechanical." Most often: a senior person who keeps doing copy-paste because the system never quite gets it right, a junior person whose week is structured around reformatting reports, a partner who's still triaging email that could have been triaged by a rule. The shared symptom is that everyone involved knows the work is mechanical — and yet it stays manual because nobody has time to fix it properly.
We're a fit when the goal is to compress decision time and remove low-judgment work — not to "add AI" for its own sake. Our discovery starts with the workflow, not the model.
Workflows we automate well
The automation patterns that pay back fastest, whatever business you are in:
Intake & onboarding pipelines
Forms, document collection, conflict checks, KYC, ID verification, file naming, folder creation, calendar invites, welcome emails — chained together with a typed schema so the AI doesn't get to "invent" a field. Human approval before any of it lands in your matter management system.
Report assembly & reformatting
Weekly or monthly reports built from spreadsheet data, CRM exports, and accounting platforms. The system pulls the underlying numbers, formats them per your template, and writes the narrative in your firm's tone. A human reviews and ships.
Email triage & routing
Inbound email classified into review, action, or archive — with extracted action items, suggested replies, and follow-up scheduling. Sensitive matters and judgment calls are always escalated to a human, never auto-replied.
Document review & comparison
Contract review where the AI flags deviations from a playbook, redlines them in track-changes, and writes a one-page summary. The deal team still reviews. The system removes the four hours of reading you did to find the three things that mattered.
Knowledge base & research agents
Retrieval-augmented agents trained on your internal documents, past matters, or sector-specific corpora. Answers carry source citations, and a question the corpus cannot support is flagged rather than guessed at.
Our automation approach
Three principles you'll see in every system we build:
1. Human-in-the-loop by default
Approval gatesEvery step that touches money, identity, communication with a client, or anything legally binding has an explicit human approval gate. We turn the approval gates off only when the firm asks and we've earned the confidence — never as a default.
2. Typed schemas, not free-text
Structured outputsEvery AI step produces a typed object (JSON or Pydantic), validated before downstream steps run. A "hallucinated" field that doesn't fit the schema fails the run and gets reviewed — it doesn't silently corrupt your database.
3. Vendor-neutral on models
No lock-inWe pick model providers based on capability and cost for your specific workflow — not because we have a reseller relationship. Most production systems we ship use a primary provider (OpenAI or Anthropic) with a secondary fallback, and an interface design that lets us swap providers in hours if you ever want to.
Tech stack
The reference stack for an automation engagement:
Python · FastAPI n8n / Make / native code Anthropic Claude OpenAI GPT-4o / o-series Pydantic / Zod schemas Postgres / Pinecone / pgvector Slack / Teams approval surfaces Cloudflare Workers AWS Lambda Langfuse / observabilityWe choose tools based on what your team can run and maintain after we leave. A no-code n8n workflow that your operations lead can edit is often a better answer than a custom Python service nobody can touch — and sometimes it's the other way around. The discovery decides.
Managed AI Partner (MAIP) — two tiers
Every retainer starts with a build. Once at least one workflow is live, Managed AI Partner is the recurring retainer that keeps it healthy and growing. Two tiers, and a simple rule: we do not sell maintenance on automation we have never seen work.
AI Care from $1,500/month
Monitoring, tuning, incident handling. We watch your existing automations for failures, prompt drift, model deprecations, and cost spikes — and flag and fix them early, within the tier's response times. Monthly summary of what ran, what failed, and what changed.
AI Plus from $3,500/month
Everything in AI Care, plus a continuous new-automation pipeline. Each month we identify and ship one new automation with a measurable payback, chosen from a backlog we maintain jointly with you.
How an engagement runs
- Fit call (free, 15 min). A quick look at your top workflow pains, so we can both tell whether a Discovery is worth booking.
- Scoping (1 week). Picked workflow gets a one-page brief: current state, proposed automation, model choice, approval gates, success metric, fixed price, target dates.
- Build (2–4 weeks per workflow). Two-week delivery cycles with end-of-cycle demos. You see the system running on real data before final cut-over.
- Adoption (1 week). Training session, runbook, and a "what to do when it breaks" cheat sheet handed to your team.
- Stewardship (optional). Roll into a Managed AI Partner retainer, or take the keys.
Pricing
The engagement has two parts, in a fixed order. The build is a fixed-fee project per workflow, scoped in writing after Discovery; typical first builds run 3 to 8 weeks. Managed AI Partner is the flat monthly retainer that follows — available only after at least one workflow we built is live. Published anchors are starting at rates; final pricing is confirmed after Discovery. Engagements handling regulated data (HIPAA-adjacent, GDPR-heavy, data-residency requirements) add 20 to 30% above the base tier, scoped in the same written quote.
01 / The buildWorkflow build
Quoted in writing Fixed-fee per workflow · after DiscoveryEvery engagement starts here.
One workflow, scoped on a one-page brief: current state, proposed automation, model choice, approval gates, success metric, price, dates. Built in 3 to 8 weeks with demos every two weeks.
- Fixed price agreed before work starts
- Approval gates by default
- Runbook + handover included
- Take the keys, or roll into MAIP
AI Care from $1,500/month
Starting at $1,500 flat monthlyAnnual prepay available. Save 7%.
Entry recurring tier. Monitoring, LLM cost watch, output spot-checks, incident response, monthly health report. Up to 2 hours per month of patch work. Business-hours SLA.
- Workflow uptime + LLM cost monitoring
- Output spot-checks & incident response
- Up to 2 hrs/mo patch work
- Monthly health report
AI Plus from $3,500/month
Starting at $3,500 flat monthlyAnnual prepay available. Save 10%.
Anchor tier. Everything in Care plus a monthly optimization sprint, output quality dashboards, model upgrade management, and a Quarterly Business Review. Up to 8 hours per month. Priority SLA.
- Everything in AI Care
- Monthly optimization sprint
- Output quality dashboards
- Model upgrade management
- Up to 8 hrs/mo + Quarterly Business Review
How does annual prepay work?
You pay 12 months upfront and we lock the rate for the year, with a courtesy discount applied to the published tier price: 7% on AI Care, 10% on AI Plus. The first 90 days are pro-rata refundable if the engagement does not work out; after 90 days, any unused balance converts to service credits applied against future months, new workflow builds, or inference cost. Annual prepay does not stack with Founding Client concessions; pick one per engagement.
Pricing is confirmed in writing at the end of Discovery. No card collected for the fit call. New workflow builds are quoted as separate projects, not absorbed silently into a retainer.
Guardrails & what we won't do
- We will not build a fully autonomous agent that takes irreversible action on a client's behalf without explicit human approval. Not until the literature catches up with that promise; not on our watch.
- We will not deploy AI-generated decisions into legally binding contexts — pricing, contract acceptance, hiring decisions, regulated advice — without human sign-off.
- We will tell you, in writing, when an automation will save less than it costs to maintain. We are not paid by the workflow.