Work

Everything we sell is something we already run.

This page is our portfolio. Not client logos, not quotes: the systems that produce, distribute, sell and guard our own operation, with their state as it is today. Each is described at the level of the system, never the product behind it.

17systems running in production, unattended
1in build, with its gates written before its features
4parked until the numbers justify switching them back on

Live reference system

Mira, an autonomous X operator.

She finds the conversations worth entering, writes into them in one locked voice, opens researched DMs once per person, answers inbound herself and hands over a booked call. Every ceiling she runs under is enforced in code and published as a ceiling.

Open the system @MiraAiHQ on X

Opener DMs: 4 / day
Quote posts: 2 / day
Inbound responder: Always on
Openers per person: 1, ever

ST-01

Agent layer

One agent layer operates everything below it. It reads the operation as a map, not as a prompt.

Running

Agent context architecture

Workspaces laid out so an agent can read the whole operation: one entry point per system, persistent memory, and every decision recorded where the next run will look for it.

Running

Run ledger and handoff protocol

Every session ends in a verifiable handoff: state, repeatable checks, known traps. The next run starts from evidence, never from memory.

ST-02

Media production

Research, script, voice, footage, edit and upload, unattended, on fixed daily slots.

Running

Long-form documentary studio

A daily episode is researched, scripted, voiced, cut and uploaded without a person in the loop. It cannot publish until it passes gates for pronunciation, footage-to-claim match and measured audio quality.

Running

Short-form vertical clip line

Headline to published clip in one pass. Footage is checked against the story's current state, and any shot that contradicts the claim is a hard block.

Running

Digital publishing engine

Books written, illustrated, typeset and listed as a pipeline. Interior art is applied and the whole book rebuilt on every change, so nothing stale reaches a reader.

Running

Synthetic presenter system

A consistent on-screen persona with a locked identity, upscaled locally at no per-frame cost, used across creative and reception footage.

Running

Performance creative engine

Ad concepts are generated in families, scored, then gated for variety so no two shipped concepts share a hook.

Running

Synthetic voice studio

Reference-engineered narration with matched-window audio forensics. Quality is measured on the waveform, never asserted.

Parked

Generative media experiments

Music and image lanes, parked until the cost card clears.

ST-03

Distribution and growth

Where the output goes, and the guards that stop it going twice.

Running

Search and discovery automation

Keywords harvested from live suggestion surfaces, pages generated to fill the gap, then re-ranked on what the engine actually returns.

Running

Autonomous social operator

A public-facing agent that reads its timeline, replies in character and posts on its own cadence. Running since September 2026.

Running

Social distribution mesh

Scheduled publishing across the major networks plus a federated server we host and operate ourselves.

Running

Partner outreach lane

Deliverability-checked email sequences with cooldown guards, so a partner is never contacted twice in one window.

In build

Continuous broadcast channel

A 24-hour ambient stream assembled from generated audio and footage. In build.

Parked

Cold outreach platform

Self-hosted sending infrastructure, parked pending a vendor settlement.

ST-04

Commerce

Listings that cannot ship half-built.

Running

Marketplace publishing engine

Product pages, art, descriptors and delivery files generated and published across two marketplaces. Slug locks and footer gates hold a listing back until every part exists.

Parked

Utility web network and promo engine

Single-purpose tools and their promotional pages, parked until distribution justifies them.

Parked

Reputation defence system

Monitoring plus an AI voice agent that answers on a client's behalf, parked awaiting a market signal.

ST-05

Infrastructure and safety

Idle compute is a fault. An unguarded endpoint is a fault. An unmeasured model chain is a fault.

Running

Compute governance

A reaper polls two GPU markets every minute, kills anything older than its budget and enforces a hard daily spend cap.

Running

Endpoint sentinels

A camera presence guard on the workstation, key-only hardened servers with intrusion lockout, and a local audit daemon logging every privileged action.

Running

Research infrastructure

Self-hosted metasearch, a fetch relay on a separate network path and a research API, so nothing upstream can rate-limit a pipeline.

Running

Model routing bench

Every model chain is re-benchmarked on its own prompt, three repeats minimum, and ranked on failure mode before it ships.

The evidence rule

We publish operating parameters, dated measurements and systems we actually run. We do not publish results we cannot show the log for, and this site has no testimonial wall for that reason.

If you want to see one of these systems run, ask on the scope call. We will walk a live run log with you, which tells you more than any case study we could write.

Book a scope call