Aden Mann: Operator-grade
AI.

I build applied AI systems for work where being wrong is expensive. I'm Principal, Applied AI at Actuals; before that, four years at Immutable, a US$2.5B web3 company, building its AI and automation capability out of finance operations. Eleven years flying Army helicopters and an MBA came first.

The main theme for me is operations at the hard end: systems that break at bad moments, decisions with real stakes, and the gap between what a tool is supposed to do and what it actually does under pressure. Army aviation went digital partway through my career. Watching that transition up close, including unpacking where it went wrong as an aviation safety investigator, is where I developed a view on how human-machine work actually transfers, and how it fails.

See the systems ↓

01Systems

Built and benchmarked. The numbers are attached.

AutoEvaluation

An optimisation engine that hill-climbs LLM instructions against a scoring function. It keeps what measurably works and reverts what doesn't, so a prompt improves itself while you sleep. Benchmarked against DSPy, TextGrad and MIPRO.

58 → 83 composite / 2h / cost of a coffee

github.com/AdenCJM/AutoEvaluation ↗

$ python3 autoeval.py --target instructions.md
# each iteration: mutate → score → keep or revert
judge   deterministic 39/42 ✓ · agreement 0.91 ✓
result  +25.2 points over baseline, no human in the loop

Parallel Research

One question, four models, answered at once and scored by agreement. Claude, GPT, Gemini and Perplexity run in parallel; a meta-pass marks where they converge and flags where a single model is out on its own.

4 LLMs / 1 command / structured output

github.com/AdenCJM/parallel-research ↗

claude.md 7 findings · gpt.md 6 · gemini.md 8 · pplx.md 9
meta-analysis.md
consensus 5 · unique 4 · contradiction 1 flagged ✓

02Live agent

Running here, in production.

Ask AI Aden

An agent that answers the way I would, running live on this page.

Live

“How do you know a prompt change actually made things better?”

You don't, until you score it. Deterministic checks first, LLM-as-judge for the fuzzy parts. If the composite drops, the change reverts itself.

03Writing

Field notes on agents, evals and judgement.

What Aviation's Automation Transition Tells Us About AI at Work2026-04-05 Coding the Autorotation2026-07-13 Why Claude Is Different2026-03-10 Workflow Archaeology2025-11-15 AI Barnacles2025-02-28 Delete Before You Optimise2025-02-15 All writing →

Spoken at / featured in

Speaker on applied AI and AI strategy, New York, Sydney and Melbourne