Joshua Waller

**summon overlord** Just preview of software side. Physical side makes it fun 😋

My automated system services has characters now. All run on a decision model + deterministic code. Calls out to agents w/ LLM only when necessary. Costs are realistic for adoption cross org. System One models do whats needed to keep horses racing on a track vs in the open field

Facts 👇 some of the most important software in Open Source AI and confidential computing sits on Github. I had the pleasure to work with some of the greatest devs over the last 5 years solving problems still prevalent today in the SF AI scene w/ less enterprise BS arch design

Blub Bluuuub Bluuuuuuub

Cloudflare is better at interacting with community and talking about technical implementations with System One models versus TypeSafe. Kinda a shame, but it is easier to introduce which is more responsive to clients when providing options. I have a few products so far all built with GOAT (clef/jev + code-based skills) + Coding Harness: - GOAT Engineering - SDLC Tool Driven by Standards & builds products with structure from inception - Rewrite - Use GOAT skill to autonomously rewrite products within the coding language standards and style of an enterprise - Know How - Patricia Merkle Trie builder to load & replay the state of workflows w/ secure/verifiable handoffs across systems within an enterprise - Overlord - Analyze + Command & Control any system through text, voice, or video inspection - (In Progress) NicNAC - Network Access Control appliance for SMBs & home networks - (In Progress) Dontology - A reusable, evidence-grounded ontology labeling and expansion system. I have other experiments that will start to expand into my past work in confidential compute soon. All PoCs are mainly to pitch & determine demand within enterprises, but will share a few as I publish. Just fun experiments but have been fun understanding different ways to use System One models as a key component of a product.

Your software factories/forges or whatever type of factory do not even know what the software costs to produce & is not flexible enough to determine how your budget is affected by changes to the software. Its more than a technical problem 🙃

🤮 which Fortune 500 company will close their doors due to multiple critical exploits by end of 2026?

Will we get any AI dev cowboys becoming confidential compute experts soon?

The future 🫡 so many useful products will come from this & especially at the costs enterprises need when integrating agentic products into their organizations. Great work!

I swear my audience knows the value of what I preach

Confidential compute for AI is inevitable. Just will take millions in attacks and losses to realize that sub-5% degradation in performance is worth the cost & effort to migrate infra to private compute clouds

Jev for command and control is so nice. I cant believe the progress ive gotten with my tool building tools with jev. With full docs SAD/TAD/ADRs created and reviewed throughout lifecycle. May not be popular but damn, effective engineering

State machines have infiltrated the AI hive mind. Remember AI devs just have to be pushed to blockchain architecture & rediscover a new term to solve their hard problems

Great day ahead 🫡 cheers to progress & great vibes