AI strategy and governed AI systems, Cape Town

AI that does the work, and asks before it acts.

We map what is worth automating, then build it into the systems you already run. Reads and drafts happen on their own. Anything with consequences waits for a person. Try it below.

Live demoSimulated data. Real rules.

I'm a demo of the assistant we build. Ask me about yesterday's sales, the inbox, stock counts, or say clean up. The data is invented; the rules are real.

78

stores reporting through systems we built, every week.

250

users on a ticketing app with no per-seat licence.

0

unaudited writes. Nothing leaves without a name on it.

07:00

every morning, a brief with the replies already drafted.

07:00Read31 unread, 4 mailboxesautomatic07:00Sorted3 need you, 9 can wait, 19 noiseautomatic07:01Draftedreply to supplier, invoice 4471draft only07:01Proposedsend that replyawaiting approval07:14Approvedby Drewapproval07:14Senteffect=send, loggedautomatic07:15Proposedtrash 212 promotional emailsawaiting approval07:16Trashedrecoverable for 30 daysautomatic08:30ReadPOS daily totals, 78 storesautomatic08:31FlaggedRosebank down 9% on last yearautomatic09:02Readstock counts, 11 of 12 storesautomatic09:03Proposed3 variances to ops task listawaiting approval09:10Approvedby Drewapproval09:10Created3 tasks, effect=create, loggedautomatic07:00Read31 unread, 4 mailboxesautomatic07:00Sorted3 need you, 9 can wait, 19 noiseautomatic07:01Draftedreply to supplier, invoice 4471draft only07:01Proposedsend that replyawaiting approval07:14Approvedby Drewapproval07:14Senteffect=send, loggedautomatic07:15Proposedtrash 212 promotional emailsawaiting approval07:16Trashedrecoverable for 30 daysautomatic08:30ReadPOS daily totals, 78 storesautomatic08:31FlaggedRosebank down 9% on last yearautomatic09:02Readstock counts, 11 of 12 storesautomatic09:03Proposed3 variances to ops task listawaiting approval09:10Approvedby Drewapproval09:10Created3 tasks, effect=create, loggedautomatic

One rule,
every system.

The model may propose. Only a deterministic policy layer may authorise. Only registered tools may execute. Scroll to watch one action go through it.

  1. 1

    Read

    Search, summarise, classify. No approval, because nothing changes.

  2. 2

    Propose

    Draft the email, the ticket, the order. Show exactly what would happen.

  3. 3

    Approve

    A person confirms the exact action. Sends, deletions and payments never skip this.

  4. 4

    Audit

    Every step logged with who approved it, so you can answer for it later.

Reading07:00
  • 31 unread across 4 mailboxes
  • 3 need you
  • 9 can wait
  • 19 noise
automatic

0% through

Two ways
in.

A plan before you spend, or a build because you already know. The plan is written by the people who will build it, so it never promises what cannot ship.

Strategy

  • Use-case discovery and roadmap

    Four weeks with leadership and the people doing the work. A ranked roadmap, the first pilot scoped and priced, and a list of things we would leave alone.

  • Governance and compliance

    A risk assessment, a framework people will follow, and the POPIA, GDPR and ISO material you need. Policies people read, not binders.

  • Team enablement

    Role-specific sessions: what the tools do for finance, ops or support, what must never be pasted into one, and how to check the answers.

Build

  • Ask your data a question

    Plain-language questions over point of sale, ERP, reports and spreadsheets, with every answer traced to the source rows.

  • Operations automation

    Reporting, reconciliation, stock counts, ticketing, document handling. Real software with logins, audit trails and no seat fees.

  • Assistants that act

    Connected to mail, files and tasks. Proposes actions, executes only what a named person approves. Provider-neutral, so no vendor lock-in.

Full service detail

07:00Read31 unread, 4 mailboxesautomatic07:00Sorted3 need you, 9 can wait, 19 noiseautomatic07:01Draftedreply to supplier, invoice 4471draft only07:01Proposedsend that replyawaiting approval07:14Approvedby Drewapproval07:14Senteffect=send, loggedautomatic07:15Proposedtrash 212 promotional emailsawaiting approval07:16Trashedrecoverable for 30 daysautomatic08:30ReadPOS daily totals, 78 storesautomatic08:31FlaggedRosebank down 9% on last yearautomatic09:02Readstock counts, 11 of 12 storesautomatic09:03Proposed3 variances to ops task listawaiting approval09:10Approvedby Drewapproval09:10Created3 tasks, effect=create, loggedautomatic07:00Read31 unread, 4 mailboxesautomatic07:00Sorted3 need you, 9 can wait, 19 noiseautomatic07:01Draftedreply to supplier, invoice 4471draft only07:01Proposedsend that replyawaiting approval07:14Approvedby Drewapproval07:14Senteffect=send, loggedautomatic07:15Proposedtrash 212 promotional emailsawaiting approval07:16Trashedrecoverable for 30 daysautomatic08:30ReadPOS daily totals, 78 storesautomatic08:31FlaggedRosebank down 9% on last yearautomatic09:02Readstock counts, 11 of 12 storesautomatic09:03Proposed3 variances to ops task listawaiting approval09:10Approvedby Drewapproval09:10Created3 tasks, effect=create, loggedautomatic

Recent work

Anonymised. Numbers are the client's own. All work

78

Delivery reconciliation for a 78-store QSR group

Weekly exports from two delivery platforms turned into order-level reporting: late, missed or misreported orders, and what the platforms paid versus what they claimed.

POS

Point of sale you can talk to

The group's POS connected to an assistant, so the ops team asks about yesterday's sales at any store in plain English.

250

Ticketing freed from per-user licences

Repairs and maintenance rebuilt as an installable web app for 250 users across three email domains, with photo capture and offline queueing.

12

Stock counts on phones

Paper and spreadsheets replaced by mobile forms that know which stores belong to which region, feeding the inventory system directly.

Our own product

Azani.

The assistant we built for ourselves and use every day. Every morning at 07:00 it reads a consolidated mailbox, sorts what needs a reply, drafts each one in the owner's voice, and sends a push. Through the day it researches with sources and captures notes, photos and voice memos into tasks and Drive. It sends nothing without a tap.

  • Runs on Google Cloud, Johannesburg, our own project
  • Login passkeys, no passwords
  • Model swappable; Anthropic and OpenAI pass the same tests
  • Model auth identity federation, no stored key
  • Writes send, save, delete: all approval-gated, all logged
  • Retention 90 days, then purged; voice discarded after transcription

Also ours: MedSync, a multi-tenant clinic treatment platform; PocketAlpha, a governed paper-trading workspace; and Echelon, a team of specialised AI agents with an orchestrator and an audit log.

Tell us what eats your team's week.

Book a 30-minute callWe reply within one working day.