{"id":148,"date":"2024-11-07T22:25:11","date_gmt":"2024-11-07T18:25:11","guid":{"rendered":"https:\/\/artenatech.com\/?page_id=148"},"modified":"2026-08-24T15:14:53","modified_gmt":"2026-08-24T11:14:53","slug":"applications","status":"publish","type":"page","link":"https:\/\/artenatech.com\/index.php\/applications\/","title":{"rendered":"Built on the Artena Tech Stack \u2014 and Proven by It"},"content":{"rendered":"\n

Every product on this page was built the way we build for clients: agents execute, objective gates verify, humans judge. The games on Google Play, the agent RPG sandbox, the voice experiments \u2014 these are not demos. They are the proving grounds where Reckon’s honesty gates, SkillForge’s skill lifecycle, and Dream Team’s certification were forged on real, shipped code. When you read a metric below, it was measured on these codebases first.<\/p>\n\n\n\n

The Artena Stack \u2014 Proven in the Wild<\/td><\/tr>
Reckon \u2192 SkillForge \u2192 AgentSpace \u2192 Dream Team
\u2193 \u2193 \u2193 \u2193
Verify \u2192 Curate \u2192 Coordinate \u2192 Certify <\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n
How the Stack Builds Our Own Products<\/h5>\n\n\n\n
    \n
  • Agent execution with honest gates.<\/strong> Multi-file edits, migrations, and features are delegated to cost-efficient models through Reckon \u2014 and completion is proven by a passing exit gate and the real working-tree diff, never by the model’s “I’m done.” A handed-off task either passes its objective check or comes back marked NOT DONE.<\/li>\n\n\n\n
  • Skills instead of prompts.<\/strong> The procedures that worked on these codebases \u2014 localization in 4,800-line god-files, parity fixes across dual backends, live-acceptance discipline \u2014 live as named, gate-proven skills in SkillForge, injected only when their trigger matches, retired when a model outgrows them.<\/li>\n\n\n\n
  • QA as a standing routine.<\/strong> Dead-code cleanup, abstraction police, orphaned-test scans, and mutation probes run on schedules across our repositories. The fleet maintains the products; engineers review the pull requests.<\/li>\n\n\n\n
  • Generative assets, human judgment.<\/strong> Where taste matters \u2014 icon style, soundtrack mood, level pacing \u2014 generated candidates are reviewed by humans. Autonomy is a dial, and on aesthetics we keep it deliberately low.<\/li>\n<\/ul>\n\n\n\n
    What Changed When Checks Replaced Promises<\/h5>\n\n\n\n
      \n
    1. Instructions 0\/4. Checks 7\/7.<\/strong> In a controlled experiment on our own codebase, asking the executor to “do it right” worked zero times out of four; verifying the result with code worked seven times out of seven. Since then, every requirement in our products is converted, one by one, into a check.<\/li>\n\n\n\n
    2. Two green suites, both lying.<\/strong> A parity campaign found five hidden divergences between dual backends at 1,900 green tests \u2014 each suite verified only against itself. The cross-backend parity oracle closed them: final measurement, full agreement 10\/10.<\/li>\n\n\n\n
    3. The sealed exam: 19\/19.<\/strong> Hidden answers, pre-sealed requirements revealed one by one, verification by execution \u2014 the chain passed 19 of 19 for about a dollar, catching 10 of 11 deliberate breaks, six of which were never mentioned in the brief.<\/li>\n\n\n\n
    4. Eleven subsystem migrations, verified live.<\/strong> An external tester checked each migration not by green tests but by independent live behavior checks. Six stable failure patterns became six structural protections; the error class that stalled several tasks in a row simply stopped recurring.<\/li>\n\n\n\n
    5. Seven subsystems and a full-stack messenger, built autonomously.<\/strong> Each time the system studied the reference code, wrote the design, built, tested, and kept the build green \u2014 and brought contested calls to human review instead of deciding silently.<\/li>\n<\/ol>\n\n\n\n
      \n\n\n\n

      Examples of developed applications<\/h3>\n\n\n\n

      Products in the Wild \u2014 and the Scanners They Forged<\/h4>\n\n\n\n

      Sky Jumper: Turtles<\/strong> (Google Play) \u2014 a retro platformer where a turtle collects stars and defeats aliens. It is also the birthplace of our game-state scanners: a variable accumulated inside a render()<\/code> loop, a missed reset, a keybind collision, an undo path left untested \u2014 these are exactly the temporal bug classes that pass node --check<\/code> and a render-blind gate, and exactly what Reckon’s structural scanners now catch on every write run. The game stays green; the scanners now protect client code too.<\/p>\n\n\n\n

      Magic Blocks: Match 3 Games<\/strong> (Google Play) \u2014 a match-3 puzzle on floating islands. Its rules engine became our mutation-testing gym: the kind of logic where a weak test passes while a mutant survives, and where the copy-under-test trap (17 green tests, zero coverage) was first caught and made structurally impossible. Level and task generation now runs behind the same honest gates as everything else: generated content ships when the check passes, not when the model says so.<\/p>\n\n\n\n

      Multiplayer RPGs<\/h4>\n\n\n\n
      AGENT Station 14 \u2014 the Agent Sandbox That Became Dream Team<\/h5>\n\n\n\n

      AGENT Station 14<\/strong>, our port of the open-source SS14<\/strong>, began as a multiplayer RPG where NPCs are autonomous agents: they adapt to player behavior, attack, defend, gather resources, hold meaningful conversations, offer quests. It is currently in beta. It is also the environment where our agent-development methodology was born. The SS14 codebase \u2014 hundreds of systems, deep simulation logic \u2014 is where library-relative trigger weighting learned that words like “station” and “system” are boilerplate in every brief; where localization-first checkpoints were validated on ~4,800-line god-files; where agents first trained alongside real developers. What started as a game sandbox is now the direct precursor of Dream Team<\/strong>: the same environment trains, certifies, and recertifies agents before they touch production code \u2014 and production experience flows back into new scenarios.<\/p>\n\n\n\n

      Apps for Audio Assistant<\/h4>\n\n\n\n
      Voice Agents \u2014 an Early Glimpse of AgentSpace<\/h5>\n\n\n\n

      Our voice version of AGENT Station 14<\/strong> for audio assistants (alpha) lets players run single-player sessions by voice: agents respond to commands, complete quests, and interact with the world in real time. It taught us a lesson that now shapes AgentSpace<\/strong>: in a screenless modality, the agent’s only honest output is a verifiable outcome \u2014 so every voice action maps to a game-state change the system can check. Autonomy without a screen forced verification without a screen.<\/p>\n\n\n\n

      Benefits of using Artena Tech solutions in gaming applications<\/h3>\n\n\n\n

      Why Games Are the Perfect Proving Ground<\/p>\n\n\n\n

      Games apply the pressure client systems will feel later: real-time state, temporal bugs, reward-hack temptation (an agent under pressure will edit the oracle that judges it), and players who find every edge case. If a verification layer survives a game, it survives a business workflow. Everything on this page now runs on the same stack we sell: Reckon<\/strong> verifies the work, SkillForge<\/strong> curates what the fleet knows, AgentSpace<\/strong> coordinates it, Dream Team<\/strong> certifies it.<\/p>\n\n\n\n

      Foundations & Related Work<\/h3>\n\n\n\n
        \n
      • Agent Skills open standard<\/strong> \u2014 agentskills.io: the SKILL.md format behind SkillForge and every learned skill in this portfolio.<\/li>\n\n\n\n
      • CodeAlive-AI<\/strong> \u2014 cross-agent skills, safety hooks, and consilium review patterns used across our stack.<\/li>\n\n\n\n
      • A formal reward-hacking taxonomy<\/strong> (arXiv:2605.02964) \u2014 the basis of our log-replay scanners (answer leakage, forged test markers).<\/li>\n\n\n\n
      • SpecBench<\/strong> (arXiv:2605.21384) \u2014 the hardcoded-answer-table pattern our scanners detect.<\/li>\n\n\n\n
      • LLM-as-a-Verifier<\/strong> (arXiv:2607.05391) \u2014 continuous judge scoring via logit expectation in our no-gate selectors.<\/li>\n\n\n\n
      • AgentFold<\/strong> (arXiv:2510.24699) \u2014 plan-boundary context folding, adopted where it pays and refused where it breaks the prefix-cache discount.<\/li>\n\n\n\n
      • To Retain or to Adapt<\/strong> (arXiv:2607.05609) \u2014 transfer-efficiency memory: proof-of-benefit outranks proof-of-selection.<\/li>\n\n\n\n
      • STING-style mutation evidence<\/strong> \u2014 77% of SWE-bench-verified instances have a mutant that passes all existing tests; the reason our gates never trust their own tests.<\/li>\n<\/ul>\n\n\n\n

        <\/p>\n","protected":false},"excerpt":{"rendered":"

        Every product on this page was built the way we build for clients: agents execute, objective gates verify, humans judge. The games on Google Play, the agent RPG sandbox, the voice experiments \u2014 these are not demos. They are the proving grounds where Reckon’s honesty gates, SkillForge’s skill lifecycle, and Dream Team’s certification were forged […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-148","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/artenatech.com\/index.php\/wp-json\/wp\/v2\/pages\/148","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/artenatech.com\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/artenatech.com\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/artenatech.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/artenatech.com\/index.php\/wp-json\/wp\/v2\/comments?post=148"}],"version-history":[{"count":10,"href":"https:\/\/artenatech.com\/index.php\/wp-json\/wp\/v2\/pages\/148\/revisions"}],"predecessor-version":[{"id":337,"href":"https:\/\/artenatech.com\/index.php\/wp-json\/wp\/v2\/pages\/148\/revisions\/337"}],"wp:attachment":[{"href":"https:\/\/artenatech.com\/index.php\/wp-json\/wp\/v2\/media?parent=148"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}