// AI-era development partner — est. Oslo

Æ g e n t i s k .
Organisations that work with AI and as AI.

// what
Talks · Workshops · Advisory · Hands-on · Tooling
// how
Human-led. Production-grade. Memory as infrastructure.

Try it. Right now.

Describe your codebase in one line. Get a 60-second sample maturity snapshot — the same shape we deliver in a paid review, just shallower.

$ aegis review --stack
// try

Powered by Claude Haiku · this is a sample, not a deliverable. Real review = 6–8 reports, architecture guards, prioritised roadmap.

Five ways to work with us.

Book one — or run the full programme.

What you can get now.

On stage, where the builders are.

// developer communities

javaBin · Agentbrew · JVM, JavaScript and agentic-dev meetups across Oslo and beyond.

// businesses & consultancies

Internal events and brown-bags for engineering & product organisations across the Nordics.

→ recent javaBin Oslo Meetup · meetup.com/javabin/events/314316420

Practical, opinionated, grounded in production — not hype.

The 10× Developer Productivity Workshop.

Transform your team into AI-era developers who ship 10× value — with a sharp eye on AI cost.

// iterative loop
  ┌──────┐   ┌──────┐   ┌────────┐
  │ build│ → │ test │ → │ change │
  └──────┘   └──────┘   └────────┘
                            │
                            ▼
  ┌──────┐   ┌──────────┐   ┌──────┐
  │repeat│ ← │ improve  │ ← │ learn│
  └──────┘   └──────────┘   └──────┘
// what you bring

Your own codebase or idea.

// what you leave with

A Claude that actually knows what it's working on. Personal license to the Skills Library.

// delivered for

Engineering teams across consulting, product and applied-AI organisations.

INDIVIDUAL · OPEN ENROLMENT
9 000 NOK / seat
  • Next cohort · 21 May
  • 15 places only · first-come
  • Personal license to the Skills Library included
  • Bring your own codebase
BUSINESS · TEAM TRAINING
enquire
  • On your codebase, on your premises
  • Tailored curriculum · paired follow-ups
  • Skills Library business license available
  • Half-day to multi-day formats

full workshop page →

I've been on many AI courses that promise a lot and deliver less. This was different. You show up with your own codebase and work with it all day. Before lunch we had written several skills — rules obvious to me, invisible to any AI.

The instructor clearly doesn't just read about AI — he uses the tools daily on real problems. Claude now orients itself quickly in our codebase. Less noise, and an assistant that actually knows what it's working on. After one day we work noticeably smarter with AI.
Ketil Hjerpaasen · Head of Consulting, Item Consulting
// no
Vår visjon i Mynder er nært knyttet til europeisk digital suverenitet. Vi utvikler en ny infrastruktur som gjør at virksomheter trygt kan ta i bruk AI-agenter — med sikkerheten, sporbarheten og compliance-forankringen som kreves når det står noe på spill. Tiden for å eksperimentere er over; nå handler det om å sette agenter i produksjon der de skaper reell forretningsverdi og kutter kostnader. Det er noe hele Europa etterspør.

Etter at Totto kom inn har vi fått en etterlengtet tempoøkning, og leverer nå mer og raskere — uten å gå på akkord med kvalitet eller sikkerhet — tvert imot. Han er i tillegg svært hyggelig og en raus læremester, og det er et privilegium å bygge et agentisk selskap sammen med ham. Han er rett og slett et unikum, og vi er svært heldige som fikk ham med på laget.
Synnøve, CEO Mynder

Make your codebase agent-ready.

// what we assess
  • Organisation and team readiness
  • Tech stacks and codebase fit for agents
  • Which areas can be automated
  • How large is the blast radius
// what you get
  • 6–8 technical reports
  • Architecture guards
  • Security analysis
  • Prioritised roadmap for ægentisk adoption
Available as a one-off engagement or as a monthly retainer for continuous access.

full advisory page →

21 deliverables in 7 days.

21
deliverables
1.75M
NOK · value at Oslo rates
10×
throughput
// 7-day timeline · human-loop checkpoints marked ⌖
  1. D1 scope · index codebase · run synthesis ⌖ kickoff
  2. D2 architecture analysis · threat model
  3. D3 security remediation · paired refactor ⌖ midweek review
  4. D4 frontend + backend fixes · characterisation tests
  5. D5 strategic planning · cost model · skill packaging
  6. D6 test pyramid · deploy pipeline · briefings
  7. D7 handover · demo · train-the-trainer ⌖ sign-off
// 50-week sustained outcome · git log --shortstat
10.7×
velocity multiplier
~12×
per-developer efficiency after 85% headcount departed
100×
test coverage · 40 → 4,000 tests
22.8
PR / FTE / week · DORA Elite / Spike

All figures from git history — not surveys. Team size fell 85%. Engineering output grew 10.7×. Same client, June 2025 – May 2026.

// continued engagement

The monthly retainer — five needs.

01
Agent-ready codebase
More testable, modular, autonomous-friendly. Velocity compounds.
02
Market launches
Blockers patched. Launch becomes a scheduling decision.
03
Migration completion
Architectural guidance against live production systems.
04
Security posture
Secret rotation, scanning, guardrails.
05
AI-ready team
Paired workshops + coached sprints. Muscle that compounds.

We build alongside you.

AI digital workers running in production. Human-led, not autonomous. Single feature → full ægentisk transformation.

// current builds
Active client build — production agentic infrastructure
elprint — lib-electronic-components · Apache 2.0 · Java

elprint: MPN normalisation, 17 specialised similarity calculators (resistors, MOSFETs, MCUs, sensors…), BOM validation, metadata for 135+ manufacturers.

// reference agents
Mímir ( ironclaw0 )
Klaw ( ironclaw1 )

24/7 on AWS EC2.

10–30×
development speed
with controlled quality
// transformation arc · single feature → agentic team → ægentisk company. read the agentic company essay →

Memory as infrastructure.

Most AI-dev setups treat memory as text files you maintain by hand. We treat it as a system — and we'll either implement it on your stack, or license you the pieces.

CONFIGURATION APPROACH
ÆGIS TOOLING
CLAUDE.md, hand-curated skill files
+ Semantic indexing, behavioural scoring
Manual routing and memory maintenance
+ Deterministic, scheduled memory maintenance
Scales to one developer, breaks at team scale
+ Scales to 289+ repos, 66,350 files, 529 skills
Memory rots silently
+ Push-based context: 53–80% fewer tool calls
// 01 — synthesis
Knowledge index across your entire codebase.
  • Lucene-based, sub-second retrieval across tens of thousands of files
  • Knowledge graph of directory purpose & archetype
  • 21 security signal types — incl. AI-specific threats
  • Auto-generates skills from recurring session patterns
1.2s
answer latency
−40%
tool calls
+67%
reasoning time
// 02 — ExoCortex
Declare → execute → verify.

Human-led ægentisk workflow. In the loop at the decisions that matter — out of it everywhere else.

$ exo declare  intent
$ exo execute  --dry-run
$ exo verify   --human
// 03 — kcp
Federated org manifest.

knowledge.yaml → agents understand structure. Saves 33% context.

// principle
Agent memory rots. topic-health + topic-triage run nightly · zero LLM calls · human in the deletion loop.
Freshness beats completeness.
// 04 — skills library
529 skills. 40 years of dev knowledge. Licensed.
// what's inside
  • Java · Spring · Kotlin · TypeScript · Python · React
  • Architecture · security · testing · perf · DX patterns
  • Auto-curated from real production sessions
  • Behavioural scoring — stale skills retired automatically
// licensing
  • Personal license — included with every workshop seat
  • Business license — enquire within
  • Updated weekly · audit-trailed · self-hosted option
// 05 — ai-readiness package
KCP manifest. Signed. Delivered. €5.
// what you receive
  • knowledge.yaml — company, products, team, customers, compliance
  • knowledge.yaml.sig — ED25519 signed, verifiable provenance
  • llms.txt — AI crawler format (llmstxt.org standard)
  • llms-full.txt — full-detail version for agent pipelines
  • CLAUDE.md — company context hub for Claude / Cursor / Zed
  • AGENTS.md — agent instructions (all frameworks)
  • SETUP.md — deploy to web root in minutes
Crawled from your public site. Delivered to your inbox in minutes. One-time payment. No subscription.
// your website
@

full product page →

// 06 — codebase intelligence LAUNCHING SOON
Any codebase, fully understood. 30–60 min. ~€890.
// what you receive
  • Architecture map — directory purposes, patterns, anti-patterns
  • Security analysis — 21 signal types, severity rated
  • Technical debt inventory — quantified and prioritized
  • Modernization roadmap — quick wins + structural changes
  • KCP manifest — drop it in, agents understand your codebase
GitHub repo URL or zip archive. Agent-run analysis via Synthesis + ExoCortex. Works on private repos — nothing leaves our pipeline.
// register interest · launching soon
✓ registered. we'll email you when it launches.
@

full product page →

// 07 — exocortex as a service LAUNCHING SOON
Declare → Execute → Verify. Auto or HITL.
// two tiers
  • Auto — fully agent-run, async delivery, from 25 000 NOK / month
  • HITL — human in the loop at declare, execute, verify, 125 000 NOK / month
  • Works on any codebase — Synthesis indexed, ExoCortex orchestrated
  • Deliverable: PR, report, or deployed artifact
  • Same workflow used in eXOReaction client engagements
You describe the intent. We run the pipeline. You receive the output.
// join the waitlist
✓ you're on the list. we'll email you when it launches.
@

full product page → · ask a question now · from EUR 1 →

Implementation engagement available — we wire these into your stack and hand it back maintained.

Wake up to a synchronised company.

Mímir composes the pulse. Slack channels carry it. No meetings. No status reports. No copy-pasting between tools.

slack · ægis workspace · 09 channels
// every line above is composed by an agent · zero copy-paste · audit-trailed
// writing

From the field.

all writing → wiki.totto.org

Who builds this.

Thor Henning Hetland
Thor Henning Hetland
Founder · Ægis · ægentisk practitioner

Four decades shipping production code across Java, Kotlin, TypeScript, Python and the architectures around them. Spent the last few years using agentic tools every day on real client problems — long enough to have opinions, scars, and a working method.

Ægis is the practice that came out of that. The tooling (Synthesis · ExoCortex · KCP), the workshops, the case studies — all of it is what I do daily, packaged so a team can adopt it without re-living the learning curve.

// 6-week rollout

From zero to ægentisk — in six weeks.

WEEK 0
Core infra
Synthesis workspaces · Mímir Slack channels.
WEEK 1
Dev activation
Claude Code live · codebase indexed · #mimir-dev active.
WEEK 2–3
Role activation
Morning briefings · meeting prep · BD signals live.
WEEK 4
API hardening
CRM and Accounting APIs fully automated.
WEEK 5–6
Polish & showcase
Cross-role query testing · live demo.
// economic threshold

Infra cost ~15,000 NOK/month. Positive ROI the moment each team member saves 20 minutes a day.

// guardrails from day one

Network isolation · financial outputs cite API sources · sensitive queries DM-only · hard spend alerts · documented backup admin · gradual channel rollout.

From scoping call to self-sufficient team.

START
30-min scoping call
Fit · goals · constraints.
WEEK 1–2
Maturity review + workshop
Assess · train · align.
WEEK 3–8
Implementation + agentic build
Ship to production together.
WEEK 9+
Handover · train-the-trainer
Your team keeps the velocity.

Or pick any single offering — talk · workshop · review · build · tooling.

// let's talk

An AI-era codebase.
An AI-era team.
Start with 30 minutes.

$ book scoping call